STCMOT: Spatio-Temporal Cohesion Learning for UAV-Based Multiple Object Tracking

TL;DR

This paper introduces STCMOT, a novel spatio-temporal cohesion framework for UAV-based multiple object tracking that leverages historical features to improve reidentification and detection accuracy under challenging conditions.

Contribution

The paper proposes a new framework that models temporal cues using historical embedding features, enhancing tracking performance in UAV videos.

Findings

Achieves state-of-the-art MOTA and IDF1 on VisDrone2019 and UAVDT datasets.

Introduces a temporal embedding boosting module for better discriminability.

Develops a trajectory embedding propagation method for salient target localization.

Abstract

Multiple object tracking (MOT) in Unmanned Aerial Vehicle (UAV) videos is important for diverse applications in computer vision. Current MOT trackers rely on accurate object detection results and precise matching of target reidentification (ReID). These methods focus on optimizing target spatial attributes while overlooking temporal cues in modelling object relationships, especially for challenging tracking conditions such as object deformation and blurring, etc. To address the above-mentioned issues, we propose a novel Spatio-Temporal Cohesion Multiple Object Tracking framework (STCMOT), which utilizes historical embedding features to model the representation of ReID and detection features in a sequential order. Concretely, a temporal embedding boosting module is introduced to enhance the discriminability of individual embedding based on adjacent frame cooperation. While the trajectory embedding is then propagated by a temporal detection refinement module to mine salient target locations in the temporal field. Extensive experiments on the VisDrone2019 and UAVDT datasets demonstrate our STCMOT sets a new state-of-the-art performance in MOTA and IDF1 metrics. The source codes are released at https://github.com/ydhcg-BoBo/STCMOT.