MV-YOLO: Motion Vector-aided Tracking by Semantic Object Detection
This work addresses the problem of efficient object tracking for visual analytics systems, but it appears incremental as it builds on existing methods by integrating motion vectors and object detection.
The paper tackles robust and efficient object tracking in real-world video by proposing a hybrid tracker that combines motion information from compressed video streams with a semantic object detector, achieving advantages in speed and/or accuracy on the OTB dataset.
Object tracking is the cornerstone of many visual analytics systems. While considerable progress has been made in this area in recent years, robust, efficient, and accurate tracking in real-world video remains a challenge. In this paper, we present a hybrid tracker that leverages motion information from the compressed video stream and a general-purpose semantic object detector acting on decoded frames to construct a fast and efficient tracking engine. The proposed approach is compared with several well-known recent trackers on the OTB tracking dataset. The results indicate advantages of the proposed method in terms of speed and/or accuracy.Other desirable features of the proposed method are its simplicity and deployment efficiency, which stems from the fact that it reuses the resources and information that may already exist in the system for other reasons.