| 本文已被：浏览 2082次 下载 5220次 |
码上扫一扫！ |
|
|
| 基于宽容训练和隐私保护的快速监控视频检索模型 |
|
覃浩1,2, 王平辉1,2, 张若非1,2, 覃遵颖3
|
|
1.西安交通大学 网络空间安全学院, 陕西 西安 710049;2.智能网络与网络安全教育部重点实验室(西安交通大学), 陕西 西安 710049;3.西安交通大学 软件学院, 陕西 西安 710049
|
|
| 摘要: |
| 监控视频关键帧检索和属性查找在交通、安防、教育等领域具有众多应用场景，应用深度学习模型处理海量视频数据在一定程度上缓解了人力消耗，但是存在隐私泄露、计算资源消耗大、时间长等特点.基于上述场景，提出了一个面向大规模监控视频的安全、快速的视频检索模型.具体地，根据云端算力大、监控摄像头算力规模小的特点，在云端部署重量级模型，并使用所提出的宽容训练策略对其进行定制化知识蒸馏，将蒸馏后的轻量级模型部署在监控摄像头内，同时使用局部加密算法对图像敏感部分进行加密，结合云端TEE技术和用户授权机制，在极低资源消耗的情况下实现隐私保护.通过合理控制蒸馏策略的“容忍度”，能够较好地平衡摄像头视频输入阶段和云端检索阶段的耗时，在保证极高准确率的前提下，保证极低的检索时延.相比于传统检索方法，该模型具有安全高效、可伸缩、低延时的特点.实验结果显示，在多个公开数据集上，该模型相比于传统检索方法提供9x-133x的加速. |
| 关键词: 视频检索 隐私保护 知识蒸馏 课程学习 |
| DOI：10.13328/j.cnki.jos.006790 |
| 分类号: |
| 基金项目:国家自然科学基金（61902305，61922067）；深圳基础研究资助项目（JCYJ20170816100819428）；教育部-中国移动“人工智能”项目（MCM20190701） |
|
| Fast Surveillance Video Retrieval Model Based on Tolerant Training and Privacy Protection |
|
QIN Hao1,2, WANG Ping-Hui1,2, ZHANG Ruo-Fei1,2, QIN Zun-Ying3
|
|
1.School of Cyber Science and Engineering, Xi'an Jiaotong University, Xi'an 710049, China;2.Ministry of Education Key Laboratory for Intelligent Networks and Network Security (Xi'an Jiaotong University), Xi'an 710049, China;3.School of Software Engineering, Xi'an Jiaotong University, Xi'an 710049, China
|
| Abstract: |
| Surveillance video keyframe retrieval and attribute search have many application scenarios in traffic, security, education and other fields. The application of deep learning model to process massive video data to a certain extent alleviates manpower consumption, but it is characterized by privacy disclosure, large consumption of computing resources and long time. Based on the above scenarios, this study proposes a safe and fast video retrieval model for mass surveillance video. In particular, according to the characteristics of large computing power in the cloud and small scale of computing power in the surveillance camera, heavyweight model is deployed in the cloud, and the proposed tolerance training strategy is used for customized knowledge distillation, the distilled lightweight model is then deployed inside a surveillance camera, at the same time using local encryption algorithm to encrypt sensitive to image part, combined with cloud TEE technology and user authorization mechanism, privacy protection can be achieved with very low resource consumption. By reasonably controlling the "tolerance" of distillation strategy, the time-consuming of camera video input stage and cloud retrieval stage can be balanced, and extremely low retrieval delay is ensured on the premise of extremely high accuracy. Compared with traditional retrieval methods, the proposed model has the characteristics of security, efficiency, scalability and low latency. Experimental results show that the proposed model provides 9×-133× acceleration compared with traditional retrieval methods on multiple open data sets. |
| Key words: video retrieval privacy protection knowledge distillation curriculum learning |
