AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributes

TL;DR

This paper introduces AttMOT, a large synthetic dataset with pedestrian attributes, and proposes a method to incorporate these attributes into multi-object tracking, improving performance on benchmarks like MOT17 and MOT20.

Contribution

The paper presents the first pedestrian attribute-enriched dataset for MOT and a novel attribute fusion method that enhances tracking accuracy.

Findings

AttMOT dataset contains over 80k frames and 6 million pedestrian IDs.

Attribute fusion improves MOTA, HOTA, and IDF1 scores on MOT benchmarks.

The proposed method achieves consistent performance gains with state-of-the-art trackers.

Abstract

Multi-object tracking (MOT) is a fundamental problem in computer vision with numerous applications, such as intelligent surveillance and automated driving. Despite the significant progress made in MOT, pedestrian attributes, such as gender, hairstyle, body shape, and clothing features, which contain rich and high-level information, have been less explored. To address this gap, we propose a simple, effective, and generic method to predict pedestrian attributes to support general Re-ID embedding. We first introduce AttMOT, a large, highly enriched synthetic dataset for pedestrian tracking, containing over 80k frames and 6 million pedestrian IDs with different time, weather conditions, and scenarios. To the best of our knowledge, AttMOT is the first MOT dataset with semantic attributes. Subsequently, we explore different approaches to fuse Re-ID embedding and pedestrian attributes, including attention mechanisms, which we hope will stimulate the development of attribute-assisted MOT. The proposed method AAM demonstrates its effectiveness and generality on several representative pedestrian multi-object tracking benchmarks, including MOT17 and MOT20, through experiments on the AttMOT dataset. When applied to state-of-the-art trackers, AAM achieves consistent improvements in MOTA, HOTA, AssA, IDs, and IDF1 scores. For instance, on MOT17, the proposed method yields a +1.1 MOTA, +1.7 HOTA, and +1.8 IDF1 improvement when used with FairMOT. To encourage further research on attribute-assisted MOT, we will release the AttMOT dataset.