Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation

4 Jan 2022  ·  Qiankun Liu, Dongdong Chen, Qi Chu, Lu Yuan, Bin Liu, Lei Zhang, Nenghai Yu ·

Occlusion between different objects is a typical challenge in Multi-Object Tracking (MOT), which often leads to inferior tracking results due to the missing detected objects. The common practice in multi-object tracking is re-identifying the missed objects after their reappearance. Though tracking performance can be boosted by the re-identification, the annotation of identity is required to train the model. In addition, such practice of re-identification still can not track those highly occluded objects when they are missed by the detector. In this paper, we focus on online multi-object tracking and design two novel modules, the unsupervised re-identification learning module and the occlusion estimation module, to handle these problems. Specifically, the proposed unsupervised re-identification learning module does not require any (pseudo) identity information nor suffer from the scalability issue. The proposed occlusion estimation module tries to predict the locations where occlusions happen, which are used to estimate the positions of missed objects by the detector. Our study shows that, when applied to state-of-the-art MOT methods, the proposed unsupervised re-identification learning is comparable to supervised re-identification learning, and the tracking performance is further improved by the proposed occlusion estimation module.

PDF Abstract

Results from the Paper


Ranked #6 on Multi-Object Tracking on MOT20 (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Multi-Object Tracking MOT16 OUTrack_fm MOTA 74.2 # 7
IDF1 71.1 # 4
IDs 1324 # 1
Multi-Object Tracking MOT17 OUTrack_fm MOTA 73.5 # 9
IDF1 70.2 # 8
Multi-Object Tracking MOT20 OUTrack_fm MOTA 68.5 # 6
IDF1 69.4 # 6

Methods


No methods listed for this paper. Add relevant methods here