CaTDet: Cascaded Tracked Detector for Efficient Object Detection from Video

Part of Proceedings of Machine Learning and Systems 1 (MLSys 2019)

Bibtex »Metadata »Paper »Supplemental »

Authors

Huizi Mao, Taeyoung Kong, bill dally

Abstract

Detecting objects in a video is a compute-intensive task. In this paper we propose CaTDet, a system to speedup object detection by leveraging the temporal correlation in video. CaTDet consists of two DNN models that form a cascaded detector, and an additional tracker to predict regions of interests based on historic detections. We also propose a new metric, mean Delay(mD), which is designed for latency-critical video applications. Experiments on the KITTI dataset show that CaTDet reduces operation count by 5.1-8.7x with the same mean Average Precision(mAP) as the single-model Faster R-CNN detector and incurs additional delay of 0.3 frame. On CityPersons dataset, CaTDet achieves 13.0x reduction in operations with 0.8 mAP loss.