轻量级动态匿名化让监控视频既保隐私又不影响异常检测
Low-Latency Video Anonymization for Crowd Anomaly Detection: Privacy Versus Performance
- 设计轻量级动态匿名化算法，按需调整保护强度
- 在多个公开数据集上实现高隐私保护且异常检测性能下降小于5%
- 适合边缘设备部署，兼顾隐私与实时性
人工智能在监控应用中潜力巨大，但隐私和模型偏见问题阻碍其在公共场景落地。现有去标识化方法多依赖计算量大的深度学习模型，难以实现实时边缘部署。本文重新审视传统匿名化方案，提出一种面向视频异常检测（VAD）的轻量级自适应匿名化方法（LA3D），通过动态调整实现全身隐私保护。在多个公开数据集上的评估表明，该方法在保持较高隐私保护水平的同时，显著降低对VAD性能的影响，优于传统及深度学习方法。实验结果显示，隐私保护效果提升明显，异常检测准确率下降小于5%。代码已开源。
原文摘要 · Abstract (English)
Recent advancements in artificial intelligence hold ample potential for monitoring applications using surveillance cameras. However, concerns about privacy and model bias have made it challenging to utilize them in public. Although de-identification approaches have been proposed in the literature, aiming to achieve a certain level of anonymization (AN), most of them employ deep learning models that are computationally demanding for real-time edge deployment. This study revisits conventional AN solutions for privacy protection and real-time video anomaly detection (VAD) applications. We propose a lightweight adaptive AN for VAD (LA3D) that employs dynamic adjustment to enhance full-body privacy protection. We have evaluated privacy protection and VAD utility retention efficacy using several publicly available datasets to examine the strengths and weaknesses of different AN methods and highlight the promising leverage of our approach. Our experiment demonstrates that the LA3D enables substantial improvement in privacy AN without severely degrading VAD efficacy, outperforming conventional and deep learning approaches. Code is available at https://github.com/muleina/LA3D .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。