BoostTrack++: using tracklet information to detect more objects in multiple object tracking

TL;DR

BoostTrack++ enhances multiple object tracking by improving detection confidence boosting through a richer similarity measure and soft confidence updates, leading to state-of-the-art results on MOT datasets.

Contribution

It introduces a novel similarity measure and a soft confidence boosting technique that can be integrated into any MOT algorithm to improve detection accuracy.

Findings

Achieves near state-of-the-art results on MOT17 dataset.

Sets new state-of-the-art HOTA and IDF1 scores on MOT20 dataset.

Demonstrates the effectiveness of the proposed similarity and confidence boost methods.

Abstract

Multiple object tracking (MOT) depends heavily on selection of true positive detected bounding boxes. However, this aspect of the problem is mostly overlooked or mitigated by employing two-stage association and utilizing low confidence detections in the second stage. Recently proposed BoostTrack attempts to avoid the drawbacks of multiple stage association approach and use low-confidence detections by applying detection confidence boosting. In this paper, we identify the limitations of the confidence boost used in BoostTrack and propose a method to improve its performance. To construct a richer similarity measure and enable a better selection of true positive detections, we propose to use a combination of shape, Mahalanobis distance and novel soft BIoU similarity. We propose a soft detection confidence boost technique which calculates new confidence scores based on the similarity measure and the previous confidence scores, and we introduce varying similarity threshold to account for lower similarity measure between detections and tracklets which are not regularly updated. The proposed additions are mutually independent and can be used in any MOT algorithm. Combined with the BoostTrack+ baseline, our method achieves near state of the art results on the MOT17 dataset and new state of the art HOTA and IDF1 scores on the MOT20 dataset. The source code is available at: https://github.com/vukasin-stanojevic/BoostTrack .