FasterVideo: Efficient Online Joint Object Detection and Tracking

Object detection and tracking in videos represent essential computationally demanding building blocks for current future visual perception systems. In order to reduce the efficiency gap between available methods computational requirements of real-world applications, we propose re-think one most successful image object detection, Faster R-CNN, extend it video domain. Specifically, framework learn instance-level embeddings which prove beneficial data association re-identification purposes. Focusing on aspects tracking, our proposed method reaches a very high necessary relevant while still managing compete with recent state-of-the-art as shown experiments conduct standard benchmarks