Surveillance cameras are ubiquitous around us. Emerging full-feature object-detection models can analyze surveillance videos with high accuracy but consume much computation. Directly applying these models for practical scenarios with large-scale cameras is prohibitively expensive. This, however, is wasteful and unnecessary considering that user-defined anomalies occur rarely among these videos. Therefore, we propose FFS-VA, a multi-stage Fast Filtering Mechanism for Video Analytics, to make video analytics much cost-effective. FFS-VA filters out the frames without the user-defined events by two stream-specialized filters and a cheap full-function model, to reduce the number of frames reaching the full-feature model. FFS-VA presents a global feedback-queue approach to balance the processing speeds of different filters in intra-stream and inter-stream processes. FFS-VA designs a dynamic batch technique to achieve a trade-off between throughput and latency. FFS-VA can also efficiently scale to multiple GPUs. We evaluate FFS-VA against the state-of-the-art YOLOv3 under the same hardware and video workloads. The experimental results show that under a 12.88 percent target-object occurrence rate on two GPUs, FFS-VA can support up to 30 concurrent video streams (15× more than YOLOv3) in the online case, and obtain 10× speedup when offline analyzing a stream, with an accuracy loss of less than 2 percent.

中文翻译：

---

一种提高大规模视频分析效率的快速过滤机制

监控摄像头在我们身边无处不在。新兴的全功能对象检测模型可以高精度分析监控视频，但会消耗大量计算量。将这些模型直接应用于大型相机的实际场景是非常昂贵的。然而，考虑到用户定义的异常在这些视频中很少发生，这是浪费和不必要的。因此，我们提出 FFS-VA，一种用于视频分析的多级快速过滤机制，使视频分析更具成本效益。FFS-VA 通过两个流专用过滤器和一个廉价的全功能模型过滤掉没有用户定义事件的帧，以减少到达全功能模型的帧数。FFS-VA 提出了一种全局反馈队列方法来平衡流内和流间过程中不同过滤器的处理速度。FFS-VA 设计了一种动态批处理技术来实现吞吐量和延迟之间的权衡。FFS-VA 还可以有效地扩展到多个 GPU。我们在相同的硬件和视频工作负载下针对最先进的 YOLOv3 评估 FFS-VA。实验结果表明，在两个 GPU 上 12.88% 的目标对象发生率下，FFS-VA 在线情况下可以支持多达 30 个并发视频流（比 YOLOv3 多 15 倍），离线分析一个流，精度损失小于 2%。我们在相同的硬件和视频工作负载下针对最先进的 YOLOv3 评估 FFS-VA。实验结果表明，在两个 GPU 上 12.88% 的目标对象发生率下，FFS-VA 在线情况下可以支持多达 30 个并发视频流（比 YOLOv3 多 15 倍），离线分析一个流，精度损失小于 2%。我们在相同的硬件和视频工作负载下针对最先进的 YOLOv3 评估 FFS-VA。实验结果表明，在两个 GPU 上 12.88% 的目标对象发生率下，FFS-VA 在线情况下可以支持多达 30 个并发视频流（比 YOLOv3 多 15 倍），离线分析一个流，精度损失小于 2%。