Motion Vector Extrapolation for Video Object Detection.

Abstract

Despite the continued successes of computationally efficient deep neural network architectures for video object detection, performance continually arrives at the great trilemma of speed versus accuracy versus computational resources (pick two). Current attempts to exploit temporal information in video data to overcome this trilemma are bottlenecked by the state of the art in object detection models. This work presents motion vector extrapolation (MOVEX), a technique which performs video object detection through the use of off-the-shelf object detectors alongside existing optical flow-based motion estimation techniques in parallel. This work demonstrates that this approach significantly reduces the baseline latency of any given object detector without sacrificing accuracy performance. Further latency reductions up to 24 times lower than the original latency can be achieved with minimal accuracy loss. MOVEX enables low-latency video object detection on common CPU-based systems, thus allowing for high-performance video object detection beyond the domain of GPU computing.