We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
MEI)IATrack: Advanced Matching Strategy for Detection-Based Multi-Object Tracking.
- Authors
WEI-SHAN CHANG; JUN-WEI HSIE; CHUAN-WANG CHANG; KUO-CHIN FAN
- Abstract
Multi-object tracking (MOT) technology is widely applied to traffic flow monitoring, human flow- monitoring, pedestrian tracking, or tactical analysis of players on the courts. It associates the detection boxes with tracklets for each frame in the video. The challenges of MOT include long-term occlusions, missing detections, and complex scenes. Although many trackers have proposed to solve these problems, the tracking results still have room for improvement. In this paper. we propose a solution named MEDIATrack (Matching Embedding Distance & IOU Association Track), a two-stage online multi-object tracking method based on ByteTrack. We replace the Kalman Filter with the NSA Kalman Filter, introduce appearance features for track association, and design a punishment mechanism to alleviate errors in complex scenes. In addition, we remove the nonactivated strategy, and the high-score unmatched detection boxes are directly added to the tracklets. On MOI 17, we achieve 79.3 MOTA, 76.5 IDFI,and state-of-the-art performance.
- Subjects
KALMAN filtering; OBJECT tracking (Computer vision); TRAFFIC monitoring; TRAFFIC flow; PROBLEM solving; PUNISHMENT
- Publication
Journal of Information Science & Engineering, 2024, Vol 40, Issue 3, p507
- ISSN
1016-2364
- Publication type
Article
- DOI
10.6688/JISE.202405_40(3).0005