用人体姿态+文本相似度实现快速异常视频检测
Real-Time Video Anomaly Detection Using YOLO Pose Estimation and CLIP-Based Semantic Scoring
- 先用YOLO检测人体并提取17个关键点，再用CLIP比对行为描述
- 实测每秒处理51帧，速度比基线快3.36倍，准确率超84%
- 无需光流或密度模型，适合实时安防场景部署
我们提出一种轻量级两阶段实时视频异常检测框架。第一阶段使用YOLO v11n-pose在一次前向传播中检测人体并提取17个骨骼关键点。第二阶段通过CLIP ViT-B/32编码裁剪出的人体区域，并计算其与预定义异常行为文本描述之间的余弦相似度。该架构无需光流、独立姿态估计算法及密度评分模块。在CUHK Avenue、ShanghaiTech Campus以及朱拉隆功大学自建的室内数据集上的实验表明，该系统在NVIDIA Titan XP GPU上实现了约51 FPS的端到端吞吐量，相比多特征基线提速3.36倍，同时保持了89.26%、70.26%和84.13%的帧级AUROC值。
原文摘要 · Abstract (English)
We propose a lightweight two-stage framework for real-time video anomaly detection. The first stage employs YOLO v11n-pose to detect persons and extract seventeen skeletal keypoints in a single forward pass. The second stage encodes each cropped person region through CLIP ViT-B/32 and computes cosine similarity against predefined textual descriptions of anomalous behaviors. This architecture eliminates the need for optical flow, standalone pose estimators, and density-based scoring modules. Experiments on CUHK Avenue, ShanghaiTech Campus, and a custom indoor dataset collected at Chulalongkorn University demonstrate an end-to-end throughput of approximately 51 FPS on an NVIDIA Titan XP GPU, a 3.36x speedup over the multi-feature baseline, while maintaining frame-level AUROC values of 89.26%, 70.26%, and 84.13%, respectively.
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。