NeighborTrack: Single Object Tracking by Bipartite Matching with Neighbor Tracklets and Its Applications to Sports

We propose a post-processor, called NeighborTrack, that leverages neighbor information of the tracking target to validate and improve single-object tracking (SOT) results. It requires no additional data or retraining. Instead, it uses the confidence score predicted by the backbone SOT network to aut...

Full description

Saved in:
Bibliographic Details
Main Authors: Chen, Yu-Hsi, Wang, Chien-Yao, Yang, Cheng-Yun, Chang, Hung-Shuo, Lin, Youn-Long, Chuang, Yung-Yu, Liao, Hong-Yuan Mark
Format: Conference Proceeding
Language:English
Subjects:
Conferences
Deformation
Oceans
Robustness
Target tracking
Training data
Transformers
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a post-processor, called NeighborTrack, that leverages neighbor information of the tracking target to validate and improve single-object tracking (SOT) results. It requires no additional data or retraining. Instead, it uses the confidence score predicted by the backbone SOT network to automatically derive neighbor information and then uses this information to improve the tracking results. When tracking an occluded target, its appearance features are untrustworthy. However, a general siamese network often cannot tell whether the tracked object is occluded by reading the confidence score alone, because it could be misled by neighbors with high confidence scores. Our proposed NeighborTrack takes advantage of unoccluded neighbors' information to reconfirm the tracking target and reduces false tracking when the target is occluded. For the VOT challenge dataset commonly used in short-term object tracking, we improve three famous SOT networks, Ocean, TransT, and OSTrack, by an average of 1.92% EAO and 2.11% robustness. For the mid- and long-term tracking experiments based on OSTrack, we achieve state-of-the-art 72.25% AUC on LaSOT and 75.7% AO on GOT-10K. Most of the tracking examples we have used are related to sports.
ISSN:2160-7516
DOI:10.1109/CVPRW59228.2023.00542