人脸识别的两大系统方案PK，结果是…
<section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 10px;margin-bottom: 10px;max-width: 100%;box-sizing: border-box;text-align: justify;word-wrap: break-word !important;"></section></section><p><br></p><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 10px;margin-bottom: 10px;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;width: 668px;transform: rotate(0deg);word-wrap: break-word !important;"><section style="max-width: 100%;box-sizing: border-box;width: 50px;height: 4px;background-color: rgb(160, 160, 160);word-wrap: break-word !important;"></section></section><section class="" style="margin-top: -4px;padding: 10px;max-width: 100%;box-sizing: border-box;background-color: rgb(239, 239, 239);word-wrap: break-word !important;"><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;font-size: 14px;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;text-align: justify;word-wrap: break-word !important;">2017年，视频监控领域最热最火的技术和产品应该是人脸识别。目前市场上人脸识别系统主要分为两种方案：</p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;text-align: justify;word-wrap: break-word !important;">前端抓拍+中心分析的前后端智能相结合的模式和基于实时视频流的中心分析模式。海康威视认为，前后端智能相结合的人脸识别方案才是未来安防行业人脸应用的主流趋势。</p></section></section></section></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;text-align: center;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;display: inline-block;width: 534.391px;vertical-align: top;word-wrap: break-word !important;"><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.5em;margin-bottom: 0.5em;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.2em;max-width: 100%;box-sizing: border-box;display: inline-block;float: left;width: 240.469px;border-width: 1px;border-style: solid;border-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin-top: 0.2em;max-width: 100%;box-sizing: border-box;display: inline-block;float: right;width: 240.469px;border-width: 1px;border-style: solid;border-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin: auto;max-width: 100%;box-sizing: border-box;width: 0.3em;height: 0.3em;border-radius: 100%;background-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;text-align: left;color: rgb(239, 72, 58);font-size: 18px;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;text-align: center;word-wrap: break-word !important;"><strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;">总述</strong></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.5em;margin-bottom: 0.5em;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;border-bottom: 2px solid rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin: auto;max-width: 100%;box-sizing: border-box;width: 0px;border-top: 1em solid rgb(253, 198, 32);word-wrap: break-word !important;border-left: 0.8em solid transparent !important;border-right: 0.8em solid transparent !important;"></section></section></section></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;text-align: justify;font-size: 14px;color: rgb(60, 54, 54);word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;white-space: normal;word-wrap: break-word !important;">人脸图片获取是人脸识别系统的第一环。基于视频流的中心分析模式，往往给大家一种错觉：不需要进行前端点位建设，使用现有治安监控点位即可实现人脸识别应用。而实际上，要使得人脸识别系统的准确率达到实战应用的要求，画面中人脸双眼瞳距要求能达到<span style="max-width: 100%;box-sizing: border-box;color: rgb(19, 19, 19);word-wrap: break-word !important;"><strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;">40个像素点以上</strong></span>，这对摄像机架设的<strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;color: rgb(19, 19, 19);word-wrap: break-word !important;">高度和角度</span></strong>都有一定要求。现有的90%以上的治安监控点位，即便拥有200万像素甚至更高分辨率，但由于架设高度、监控角度并非专为人脸识别而建设，依旧无法直接用于人脸抓拍。</p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;white-space: normal;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;display: inline-block;vertical-align: top;width: 334px;word-wrap: break-word !important;"><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 10px;margin-bottom: 10px;max-width: 100%;box-sizing: border-box;transform: translate3d(0px, 0px, 0px);word-wrap: break-word !important;"></section></section></section><section class="" style="max-width: 100%;box-sizing: border-box;display: inline-block;vertical-align: top;width: 334px;word-wrap: break-word !important;"><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 10px;margin-bottom: 10px;max-width: 100%;box-sizing: border-box;text-align: right;transform: translate3d(0px, 0px, 0px);word-wrap: break-word !important;"></section></section></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;text-align: center;font-size: 11px;color: rgb(160, 160, 160);word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;">普通治安监控点位效果 <span style="max-width: 100%;box-sizing: border-box;letter-spacing: 0px;word-wrap: break-word !important;">人脸抓拍点位效果</span></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"> </p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;text-align: justify;font-size: 14px;color: rgb(60, 54, 54);word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;white-space: normal;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;">因而，建设人脸识别系统、新建专门用作人脸抓拍的点位是必不可少的，而<strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;color: rgb(19, 19, 19);word-wrap: break-word !important;">安装人脸抓拍摄像机则有着纯中心分析无法替代的优势</span></strong>。</span></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;text-align: center;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;display: inline-block;width: 534.391px;vertical-align: top;word-wrap: break-word !important;"><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.5em;margin-bottom: 0.5em;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.2em;max-width: 100%;box-sizing: border-box;display: inline-block;float: left;width: 240.469px;border-width: 1px;border-style: solid;border-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin-top: 0.2em;max-width: 100%;box-sizing: border-box;display: inline-block;float: right;width: 240.469px;border-width: 1px;border-style: solid;border-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin: auto;max-width: 100%;box-sizing: border-box;width: 0.3em;height: 0.3em;border-radius: 100%;background-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;text-align: left;color: rgb(239, 72, 58);font-size: 18px;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;text-align: center;word-wrap: break-word !important;"><strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;">优势 1 . 实时性更高</strong><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.5em;margin-bottom: 0.5em;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;border-bottom: 2px solid rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin: auto;max-width: 100%;box-sizing: border-box;width: 0px;border-top: 1em solid rgb(253, 198, 32);word-wrap: break-word !important;border-left: 0.8em solid transparent !important;border-right: 0.8em solid transparent !important;"></section></section></section></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;text-align: justify;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;white-space: normal;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;color: rgb(60, 54, 54);font-size: 14px;word-wrap: break-word !important;">人脸识别系统在公安行业中，非常重要的一块业务是对重点人员进行动态布控预警，这要求系统有非常高的实时性。目前主流厂家均采用深度学习的方法来做人脸识别，基于视频的中心分析、人脸识别和人脸建模比对都依赖于中心服务器，在大规模部署的情况下，<strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;color: rgb(19, 19, 19);word-wrap: break-word !important;">中心服务器的计算压力无疑是巨大的</span></strong>，计算资源不足，实时性就难以保证。</span></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;white-space: normal;word-wrap: break-word !important;"><strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;font-size: 14px;color: rgb(19, 19, 19);word-wrap: break-word !important;">前端抓拍+中心分析的前后端智能相结合的模式</span></strong><span style="max-width: 100%;box-sizing: border-box;color: rgb(60, 54, 54);font-size: 14px;word-wrap: break-word !important;">，<strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;color: rgb(19, 19, 19);word-wrap: break-word !important;">则是将人脸识别智能算法前置</span></strong>，在前端摄像机内置高性能智能芯片，通过边缘计算，将人脸识别抓图的<strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;color: rgb(19, 19, 19);word-wrap: break-word !important;">压力分摊</span></strong>到前端，<strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;color: rgb(19, 19, 19);word-wrap: break-word !important;">解放中心的计算资源</span></strong>，以集中优势计算资源做更高效的分析。</span></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;white-space: normal;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;color: rgb(60, 54, 54);font-size: 14px;word-wrap: break-word !important;">在实际的项目测试中，纯中心分析模式下，报警延时在15~20s，而前端抓拍+中心分析模式下，<strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;color: rgb(19, 19, 19);word-wrap: break-word !important;">报警延时不超过3s</span></strong>，这短短的十几秒对于出警抓捕来说则是至关重要的。随着前端点位数增加到一定规模，前端抓拍+中心分析这一模式的实时性优势将进一步突出。</span></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;text-align: center;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;display: inline-block;width: 534.391px;vertical-align: top;word-wrap: break-word !important;"><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.5em;margin-bottom: 0.5em;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.2em;max-width: 100%;box-sizing: border-box;display: inline-block;float: left;width: 240.469px;border-width: 1px;border-style: solid;border-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin-top: 0.2em;max-width: 100%;box-sizing: border-box;display: inline-block;float: right;width: 240.469px;border-width: 1px;border-style: solid;border-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin: auto;max-width: 100%;box-sizing: border-box;width: 0.3em;height: 0.3em;border-radius: 100%;background-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;text-align: left;color: rgb(239, 72, 58);font-size: 18px;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;text-align: center;word-wrap: break-word !important;"><strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;">优势 2 . 场景适应性更好</strong></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.5em;margin-bottom: 0.5em;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;border-bottom: 2px solid rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin: auto;max-width: 100%;box-sizing: border-box;width: 0px;border-top: 1em solid rgb(253, 198, 32);word-wrap: break-word !important;border-left: 0.8em solid transparent !important;border-right: 0.8em solid transparent !important;"></section></section></section></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;font-size: 14px;color: rgb(60, 54, 54);word-wrap: break-word !important;">不同的人脸布控场景对摄像机的形态和安装位置要求不尽相同。普通监控摄像机在产品设计定位上主要用于治安监控，难以满足场景多样化的需求。而海康威视的人脸抓拍机家族则根据各类场景的人脸抓拍需求，设计了各种形态的产品以达到最佳的人脸抓拍效果。</span></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;font-size: 14px;color: rgb(60, 54, 54);word-wrap: break-word !important;"><br></span></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;font-size: 14px;color: rgb(60, 54, 54);word-wrap: break-word !important;">一：</span><strong><span style="max-width: 100%;box-sizing: border-box;font-size: 14px;color: rgb(60, 54, 54);word-wrap: break-word !important;"></span>针对大场景</strong></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;font-size: 14px;color: rgb(60, 54, 54);word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;">人脸抓拍机有普通人脸抓拍机和全局相机二种前端设备，后者可以解决普通人脸相机建设场景单一、覆盖区域小的问题。以全局相机为例，单个摄像机，<strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;color: rgb(19, 19, 19);word-wrap: break-word !important;">既能做治安监控，又能进行开放式场景全局人脸抓拍</span></strong>。它解决了一般中心分析方案无法覆盖的广场，路口等大场景的人脸抓拍问题。</p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="margin-top: 10px;margin-bottom: 10px;max-width: 100%;box-sizing: border-box;text-align: center;word-wrap: break-word !important;"></p><p style="margin-top: 10px;margin-bottom: 10px;max-width: 100%;box-sizing: border-box;text-align: center;word-wrap: break-word !important;"><br></p></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;display: inline-block;vertical-align: bottom;width: 407.469px;word-wrap: break-word !important;"><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 7px;margin-bottom: 7px;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><strong>二：针对通道，截面式场景</strong></p></section></section></section></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;font-size: 14px;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;">火车站、车站、地铁站、机场等交通枢纽出入口，人行横道、非机动车道，商场、超市出入口等这类场景，人群较为集中，且人员行进方向单一，是人脸布控较为有效的场景。针对这一类的场景，一方面，海康威视人脸抓拍机采用了深度学习算法，内置高性能智能芯片，<strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;color: rgb(19, 19, 19);word-wrap: break-word !important;">每秒可识别30张人脸，在低头、侧脸、部分遮挡人脸的情况下，能最大程度捕获角度、光线最佳的人脸照片</span></strong>；另一方面，海康威视人脸抓拍机<strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;color: rgb(19, 19, 19);word-wrap: break-word !important;">有各种分辨率、焦距、形态可选</span></strong>。</p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;">比如，针对不同抓拍宽度，可选择不同分辨率，2.5米以内的场景可选200万像素的人脸抓拍机，更大抓拍宽度时，可选600万甚至更高分辨率。针对不同抓拍距离，摄像机有多个焦距段可选，支持自动调焦，方便调试。针对一些室内环境，可以选择枪机，小型筒机，半球等形态较小的产品。针对室外道路场景，还有护罩一体机、大型筒机等形态选择。</p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;min-height: 1em;text-align: center;box-sizing: border-box !important;word-wrap: break-word !important;"></p><p style="max-width: 100%;min-height: 1em;text-align: center;box-sizing: border-box !important;word-wrap: break-word !important;"><br></p><p style="max-width: 100%;min-height: 1em;text-align: left;box-sizing: border-box !important;word-wrap: break-word !important;"><strong>三：针对夜间场景</strong></p><p style="max-width: 100%;min-height: 1em;text-align: left;box-sizing: border-box !important;word-wrap: break-word !important;"><br></p></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;text-align: justify;color: rgb(60, 54, 54);font-size: 14px;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;white-space: normal;word-wrap: break-word !important;">普通摄像机在夜间拍摄时多为红外补光，画面呈黑白效果，无法用于人脸比对，纯中心比对的人脸识别方案在夜间难以发挥效用。海康威视人脸抓拍机<span style="max-width: 100%;color: rgb(0, 0, 0);box-sizing: border-box !important;word-wrap: break-word !important;"><strong style="max-width: 100%;box-sizing: border-box !important;word-wrap: break-word !important;">自带一体化白光补光灯</strong></span>，<strong style="max-width: 100%;box-sizing: border-box !important;word-wrap: break-word !important;"><span style="max-width: 100%;color: rgb(0, 0, 0);box-sizing: border-box !important;word-wrap: break-word !important;">无需单独安装</span></strong>，能在夜间场景中对人脸有效补光，夜间人脸捕获率高、人脸效果良好。</p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;text-align: center;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;display: inline-block;width: 534.391px;vertical-align: top;word-wrap: break-word !important;"><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.5em;margin-bottom: 0.5em;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.2em;max-width: 100%;box-sizing: border-box;display: inline-block;float: left;width: 240.469px;border-width: 1px;border-style: solid;border-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin-top: 0.2em;max-width: 100%;box-sizing: border-box;display: inline-block;float: right;width: 240.469px;border-width: 1px;border-style: solid;border-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin: auto;max-width: 100%;box-sizing: border-box;width: 0.3em;height: 0.3em;border-radius: 100%;background-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;text-align: left;color: rgb(239, 72, 58);font-size: 18px;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;text-align: center;word-wrap: break-word !important;"><strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;">优势 3 . 抓拍质量更佳</strong></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.5em;margin-bottom: 0.5em;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;border-bottom: 2px solid rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin: auto;max-width: 100%;box-sizing: border-box;width: 0px;border-top: 1em solid rgb(253, 198, 32);word-wrap: break-word !important;border-left: 0.8em solid transparent !important;border-right: 0.8em solid transparent !important;"></section></section></section></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;color: rgb(60, 54, 54);font-size: 14px;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;">前端人脸识别基于压缩前的原始码流分析，避免了压缩的损失，提供给中心的图片质量更高。高质量的人脸图片是保证系统准确度的关键因素。海康威视深眸人脸抓拍机为人脸识别算法<span style="max-width: 100%;color: rgb(0, 0, 0);box-sizing: border-box !important;word-wrap: break-word !important;"><strong style="max-width: 100%;box-sizing: border-box !important;word-wrap: break-word !important;">专门设计图像的ISP算法，</strong></span><strong style="max-width: 100%;box-sizing: border-box !important;word-wrap: break-word !important;"><span style="max-width: 100%;color: rgb(0, 0, 0);box-sizing: border-box !important;word-wrap: break-word !important;">成像的人脸图片对人脸识别的准确率有5%-10%的提升</span></strong>。</p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 10px;margin-bottom: 10px;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="padding-top: 10px;padding-bottom: 10px;max-width: 100%;box-sizing: border-box;display: inline-block;width: 668px;vertical-align: top;background-color: rgb(253, 252, 248);word-wrap: break-word !important;"><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-bottom: 10px;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="padding-right: 6px;padding-left: 6px;max-width: 100%;box-sizing: border-box;display: inline-block;width: 668px;border-width: 0px 0px 0px 6px;border-style: solid;border-left-color: rgb(253, 198, 32);border-right-color: rgb(253, 198, 32);word-wrap: break-word !important;"><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;">噪声控制</strong></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;font-size: 14px;word-wrap: break-word !important;">脸部区域块状效应不明显，人脸更加细腻，人脸图像识别效果更佳；</span></p></section></section></section></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 10px;margin-bottom: 10px;max-width: 100%;box-sizing: border-box;text-align: center;word-wrap: break-word !important;"></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;text-align: center;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;font-size: 12px;word-wrap: break-word !important;">↑噪声大小比对</span></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;font-size: 10px;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;letter-spacing: 0px;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></span></span></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-bottom: 10px;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="padding-right: 6px;padding-left: 6px;max-width: 100%;box-sizing: border-box;display: inline-block;width: 668px;border-width: 0px 0px 0px 6px;border-style: solid;border-left-color: rgb(253, 198, 32);border-right-color: rgb(253, 198, 32);word-wrap: break-word !important;"><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;">运动模糊</strong></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;font-size: 14px;color: rgb(60, 54, 54);word-wrap: break-word !important;">相较普通摄像机出现的运动模糊的情况，人脸抓拍机能根据人员的行走速度自动调整合理曝光时间，在保证合理亮度下，去掉运动模糊。</span></p></section></section></section></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 10px;margin-bottom: 10px;max-width: 100%;box-sizing: border-box;text-align: center;word-wrap: break-word !important;"></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;text-align: center;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;font-size: 12px;word-wrap: break-word !important;">运动模糊明显改善 <span style="max-width: 100%;box-sizing: border-box;letter-spacing: 0px;word-wrap: break-word !important;">运动模糊严重</span></span></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"> </p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-bottom: 10px;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="padding-right: 6px;padding-left: 6px;max-width: 100%;box-sizing: border-box;display: inline-block;width: 668px;border-width: 0px 0px 0px 6px;border-style: solid;border-left-color: rgb(253, 198, 32);border-right-color: rgb(253, 198, 32);word-wrap: break-word !important;"><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;">逆光环境</strong></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;font-size: 14px;color: rgb(60, 54, 54);word-wrap: break-word !important;">逆光环境下要确保人脸成像清晰，传统方式是通过开启宽动态，根据前景和背景自动调整曝光倍率，提升整幅图像成像质量，但人脸区域的图像质量还不够理想。海康威视深眸人脸抓拍机采用宽动态+人脸区域曝光技术，当光照发生变化时，自动调节曝光参数，确保逆光情况下抓拍的人脸仍较清晰。</span></p></section></section></section></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 10px;margin-bottom: 10px;max-width: 100%;box-sizing: border-box;text-align: center;word-wrap: break-word !important;"></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;text-align: center;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;font-size: 12px;word-wrap: break-word !important;">宽动态+人脸区域曝光关闭 <span style="max-width: 100%;box-sizing: border-box;letter-spacing: 0px;word-wrap: break-word !important;">宽动态+人脸区域曝光开启</span></span></p></section></section></section></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;text-align: center;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;display: inline-block;width: 534.391px;vertical-align: top;word-wrap: break-word !important;"><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.5em;margin-bottom: 0.5em;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.2em;max-width: 100%;box-sizing: border-box;display: inline-block;float: left;width: 240.469px;border-width: 1px;border-style: solid;border-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin-top: 0.2em;max-width: 100%;box-sizing: border-box;display: inline-block;float: right;width: 240.469px;border-width: 1px;border-style: solid;border-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin: auto;max-width: 100%;box-sizing: border-box;width: 0.3em;height: 0.3em;border-radius: 100%;background-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;text-align: left;color: rgb(239, 72, 58);font-size: 18px;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;text-align: center;word-wrap: break-word !important;"><strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;">优势 4 . 数据连续性更优</strong></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.5em;margin-bottom: 0.5em;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;border-bottom: 2px solid rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin: auto;max-width: 100%;box-sizing: border-box;width: 0px;border-top: 1em solid rgb(253, 198, 32);word-wrap: break-word !important;border-left: 0.8em solid transparent !important;border-right: 0.8em solid transparent !important;"></section></section></section></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;font-size: 14px;color: rgb(60, 54, 54);word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;">中心分析取实时视频流的方式易造成断网，网络不稳定时还存在丢帧等情况，直接影响人脸的检出率，极可能导致在案件研判时无法获取关键点位的人脸信息，导致检索轨迹不全甚至分析结果失真等后果。</p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;">前端人脸抓拍<strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;color: rgb(19, 19, 19);word-wrap: break-word !important;">支持断网续传</span></strong>。网络中断，不会影响摄像机抓拍人脸，人脸图片可存储在摄像机的SD卡中，等网络恢复后，将人脸图片回传到中心进行分析，保证整个人脸识别系统的整体准确率和稳定性。</p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;text-align: center;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;display: inline-block;width: 534.391px;vertical-align: top;word-wrap: break-word !important;"><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.5em;margin-bottom: 0.5em;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.2em;max-width: 100%;box-sizing: border-box;display: inline-block;float: left;width: 240.469px;border-width: 1px;border-style: solid;border-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin-top: 0.2em;max-width: 100%;box-sizing: border-box;display: inline-block;float: right;width: 240.469px;border-width: 1px;border-style: solid;border-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin: auto;max-width: 100%;box-sizing: border-box;width: 0.3em;height: 0.3em;border-radius: 100%;background-color: rgb(253, 198, 32);word-wrap: break-word !important;"></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;text-align: left;color: rgb(239, 72, 58);font-size: 18px;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;text-align: center;word-wrap: break-word !important;"><strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;">优势 5 . 网络宽带压力更小</strong></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 0.5em;margin-bottom: 0.5em;max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;border-bottom: 2px solid rgb(253, 198, 32);word-wrap: break-word !important;"></section><section class="" style="margin: auto;max-width: 100%;box-sizing: border-box;width: 0px;border-top: 1em solid rgb(253, 198, 32);word-wrap: break-word !important;border-left: 0.8em solid transparent !important;border-right: 0.8em solid transparent !important;"></section></section></section></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;font-size: 14px;color: rgb(60, 54, 54);word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></span></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;font-size: 14px;color: rgb(60, 54, 54);word-wrap: break-word !important;">中心分析模式下，传输的是7*24小时不间断的实时视频流。前端抓拍+中心分析模式下，<strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;color: rgb(19, 19, 19);word-wrap: break-word !important;">传输的是图片流</span></strong>，仅在有人脸抓拍图片的情况下才需要占用带宽。</span></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;font-size: 14px;color: rgb(60, 54, 54);word-wrap: break-word !important;">以一典型公安市级人脸识别方案为例，如下拓扑图所示，前端抓拍+中心分析模式下，区县一级的点位视频一般直接存储在区县派出所，仅需将人脸抓拍图片上传地市，做中心分析；而在纯中心分析的模式下，区县一级的视频流需要实时传输到地市。在前端数达到一定规模的情况下，其传输的压力是巨大的，且会占用流媒体资源，影响当前业务。</span></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 10px;margin-bottom: 10px;max-width: 100%;box-sizing: border-box;text-align: center;word-wrap: break-word !important;"></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;text-align: center;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;font-size: 14px;background-color: rgb(255, 218, 81);word-wrap: break-word !important;">中心分析拓扑图<span style="max-width: 100%;box-sizing: border-box;letter-spacing: 0px;word-wrap: break-word !important;">(视频)↑</span></span></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;text-align: center;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;font-size: 12px;letter-spacing: 0px;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box !important;word-wrap: break-word !important;"></span></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;font-size: 10px;letter-spacing: 0px;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></span></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="margin-top: 10px;margin-bottom: 10px;max-width: 100%;box-sizing: border-box;text-align: center;word-wrap: break-word !important;"></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;font-size: 10px;word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;text-align: center;word-wrap: break-word !important;"><span style="max-width: 100%;font-size: 14px;background-color: rgb(255, 218, 81);box-sizing: border-box !important;word-wrap: break-word !important;">前端抓拍+中心分析拓扑图<span style="max-width: 100%;box-sizing: border-box;letter-spacing: 0px;word-wrap: break-word !important;">（图片、数据） ↑</span></span></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></p><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;word-wrap: break-word !important;"><br style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></p></section></section></section><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;font-size: 14px;color: rgb(60, 54, 54);word-wrap: break-word !important;"><p style="max-width: 100%;box-sizing: border-box;min-height: 1em;line-height: 25.2px;white-space: normal;widows: 1;background-color: rgb(255, 255, 255);word-wrap: break-word !important;">除了以上几个方面的优势，海康威视前后端智能结合模式还能够做到系统云分析下沉，防止中心服务器臃肿堆叠，<strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;color: rgb(19, 19, 19);word-wrap: break-word !important;">节省中心计算资源及机房场地</span></strong>；在“人、车、物”方面的融合应用，海康有能力做资源的整合与大数据的<strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;color: rgb(19, 19, 19);word-wrap: break-word !important;">融合应用</span></strong>；全国各省、市都设有分公司、办事处，用户需求、系统<strong style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><span style="max-width: 100%;box-sizing: border-box;color: rgb(19, 19, 19);word-wrap: break-word !important;">运维的相应快，服务更优</span></strong>。</p><section style="max-width: 100%;box-sizing: border-box;line-height: 25.2px;white-space: normal;widows: 1;background-color: rgb(255, 255, 255);word-wrap: break-word !important;"><section class="" powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"><section class="" style="max-width: 100%;box-sizing: border-box;word-wrap: break-word !important;"></section></section></section></section></section></section></section><p><br></p></section><section style="background-color: rgb(255, 255, 255);box-sizing: border-box;"><section class="Powered-by-XIUMI V5" style="box-sizing: border-box;" powered-by="xiumi.us"><section class="" style="margin: 40px 0% 10px;text-align: center;box-sizing: border-box;"><section class="" style="display: inline-block;width: 90%;border-width: 1px;border-style: dotted;border-color: rgb(160, 160, 160);padding: 10px;border-radius: 0px;box-sizing: border-box;"><section class="Powered-by-XIUMI V5" style="box-sizing: border-box;" powered-by="xiumi.us"><section class="" style="transform: translate3d(20px, 0px, 0px);text-align: left;font-size: 11px;margin-top: -55px;margin-right: 0%;margin-left: 0%;box-sizing: border-box;"><section class="" style="box-sizing: border-box;width: 7em;height: 7em;display: inline-block;vertical-align: bottom;border-radius: 100%;border-width: 5px;border-style: none;border-color: rgb(160, 160, 160);background-position: center center;background-repeat: no-repeat;background-size: cover;background-image: url("https://neice.26x.net/UploadFile/common/wechat//2023/02-19/316973d7-4fc7-4c53-9481-b508440f4d39.png");"><section class="" style="width: 100%;height: 100%;overflow: hidden;box-sizing: border-box;"></section></section></section></section><section class="Powered-by-XIUMI V5" style="box-sizing: border-box;" powered-by="xiumi.us"><section class="" style="box-sizing: border-box;"><section class="group-empty" style="display: inline-block;vertical-align: top;width: 5%;box-sizing: border-box;"></section><section class="" style="display: inline-block;vertical-align: top;width: 80%;box-sizing: border-box;"><section class="Powered-by-XIUMI V5" style="box-sizing: border-box;" powered-by="xiumi.us"><section class="" style="margin-right: 0%;margin-left: 0%;box-sizing: border-box;"><section class="" style="text-align: right;font-size: 12px;color: rgb(160, 160, 160);line-height: 1.6;letter-spacing: 1px;box-sizing: border-box;"><p style="box-sizing: border-box;">科普知识|配置指导|疑难解答|方法介绍<br style="box-sizing: border-box;"></p></section></section></section><section class="Powered-by-XIUMI V5" style="box-sizing: border-box;" powered-by="xiumi.us"><section class="" style="margin-top: 0.5em;margin-bottom: 0.5em;box-sizing: border-box;"><section class="" style="background-color: rgb(160, 160, 160);height: 1px;box-sizing: border-box;"></section></section></section></section></section></section><section class="Powered-by-XIUMI V5" style="box-sizing: border-box;" powered-by="xiumi.us"><section class="" style="box-sizing: border-box;"><section class="" style="display: inline-block;vertical-align: middle;width: 61.8%;box-sizing: border-box;"><section class="Powered-by-XIUMI V5" style="box-sizing: border-box;" powered-by="xiumi.us"><section class="" style="box-sizing: border-box;"><section class="" style="font-size: 12px;color: rgb(249, 110, 87);line-height: 1.9;letter-spacing: 1px;box-sizing: border-box;"><p style="box-sizing: border-box;">看视频，学配置</p><p style="box-sizing: border-box;">长按二维码扫描</p><p style="box-sizing: border-box;">最新视频教程我们会实时更新</p></section></section></section></section><section class="" style="display: inline-block;vertical-align: middle;width: 38.2%;box-sizing: border-box;"><section class="Powered-by-XIUMI V5" style="box-sizing: border-box;" powered-by="xiumi.us"><section class="" style="margin-right: 0%;margin-left: 0%;box-sizing: border-box;"></section></section></section></section></section></section></section></section></section>
页:
[1]