Fast Self-Supervised depth and mask aware Association for Multi-Object Tracking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Khanchi, Milad, Amer, Maria, Poullis, Charalambos
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908587511513088
author Khanchi, Milad
Amer, Maria
Poullis, Charalambos
author_facet Khanchi, Milad
Amer, Maria
Poullis, Charalambos
contents Multi-object tracking (MOT) methods often rely on Intersection-over-Union (IoU) for association. However, this becomes unreliable when objects are similar or occluded. Also, computing IoU for segmentation masks is computationally expensive. In this work, we use segmentation masks to capture object shapes, but we do not compute segmentation IoU. Instead, we fuse depth and mask features and pass them through a compact encoder trained self-supervised. This encoder produces stable object representations, which we use as an additional similarity cue alongside bounding box IoU and re-identification features for matching. We obtain depth maps from a zero-shot depth estimator and object masks from a promptable visual segmentation model to obtain fine-grained spatial cues. Our MOT method is the first to use the self-supervised encoder to refine segmentation masks without computing masks IoU. MOT can be divided into joint detection-ReID (JDR) and tracking-by-detection (TBD) models. The latter are computationally more efficient. Experiments of our TBD method on challenging benchmarks with non-linear motion, occlusion, and crowded scenes, such as SportsMOT and DanceTrack, show that our method outperforms the TBD state-of-the-art on most metrics, while achieving competitive performance on simpler benchmarks with linear motion, such as MOT17.
format Preprint
id arxiv_https___arxiv_org_abs_2510_09878
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fast Self-Supervised depth and mask aware Association for Multi-Object Tracking
Khanchi, Milad
Amer, Maria
Poullis, Charalambos
Computer Vision and Pattern Recognition
Multi-object tracking (MOT) methods often rely on Intersection-over-Union (IoU) for association. However, this becomes unreliable when objects are similar or occluded. Also, computing IoU for segmentation masks is computationally expensive. In this work, we use segmentation masks to capture object shapes, but we do not compute segmentation IoU. Instead, we fuse depth and mask features and pass them through a compact encoder trained self-supervised. This encoder produces stable object representations, which we use as an additional similarity cue alongside bounding box IoU and re-identification features for matching. We obtain depth maps from a zero-shot depth estimator and object masks from a promptable visual segmentation model to obtain fine-grained spatial cues. Our MOT method is the first to use the self-supervised encoder to refine segmentation masks without computing masks IoU. MOT can be divided into joint detection-ReID (JDR) and tracking-by-detection (TBD) models. The latter are computationally more efficient. Experiments of our TBD method on challenging benchmarks with non-linear motion, occlusion, and crowded scenes, such as SportsMOT and DanceTrack, show that our method outperforms the TBD state-of-the-art on most metrics, while achieving competitive performance on simpler benchmarks with linear motion, such as MOT17.
title Fast Self-Supervised depth and mask aware Association for Multi-Object Tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.09878