paper-with-me

홈 › Papers

Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification

2023-02-23 · Gerard Maggiolino, Adnan Ahmad, Jinkun Cao, Kris Kitani

Motion-based association for Multi-Object Tracking (MOT) has recently re-achieved prominence with the rise of powerful object detectors. Despite this, little work has been done to incorporate appearance cues beyond simple heuristic models that lack robustness to feature degradation. In this paper, we propose a novel way to leverage objects' appearances to adaptively integrate appearance matching into existing high-performance motion-based methods. Building upon the pure motion-based method OC-SORT, we achieve 1st place on MOT20 and 2nd place on MOT17 with 63.9 and 64.9 HOTA, respectively. We also achieve 61.3 HOTA on the challenging DanceTrack benchmark as a new state-of-the-art even compared to more heavily-designed methods. The code and models are available at \url{https://github.com/GerardMaggiolino/Deep-OC-SORT}.

📄 PDF Abstract BibTeX arXiv:2302.11813

Code (3)

gerardmaggiolino/deep-oc-sort 공식 구현 pytorch
mikel-brostrom/boxmot pytorch
noahcao/OC_SORT pytorch

Tasks

Multi-Object TrackingObjectObject Tracking

Similar Papers 제목 키워드 기반

Comparative study of multi-person tracking methods

2023-10-07 · Denis Mbey Akola

This paper presents a study of two tracking algorithms (SORT~\cite{7533003} and Tracktor++~\cite{2019}) that were ranked first positions on the MOT Challenge leaderboard (The MOTChallenge web page: https://motchallenge.n…

Pedestrian Detection

OccluTrack: Rethinking Awareness of Occlusion for Enhancing Multiple Pedestrian Tracking

2023-09-19 · Jianjun Gao, Yi Wang, Kim-Hui Yap, Kratika Garg 외

Multiple pedestrian tracking faces the challenge of tracking pedestrians in the presence of occlusion. Existing methods suffer from inaccurate motion estimation, appearance feature extraction, and association due to occl…

Motion Estimation

MAML MOT: Multiple Object Tracking based on Meta-Learning

2024-05-12 · Jiayi Chen, Chunhua Deng

With the advancement of video analysis technology, the multi-object tracking (MOT) problem in complex scenes involving pedestrians is gaining increasing importance. This challenge primarily involves two key tasks: pedest…

Meta-LearningMulti-Object TrackingMultiple Object TrackingObject+2

BoT-SORT: Robust Associations Multi-Pedestrian Tracking

2022-06-29 · Nir Aharon, Roy Orfaig, Ben-Zion Bobrovsky

The goal of multi-object tracking (MOT) is detecting and tracking all the objects in a scene, while keeping a unique identifier for each object. In this paper, we present a new robust state-of-the-art tracker, which can …

Multi-Object TrackingObjectObject Tracking

Deep Person Re-identification for Probabilistic Data Association in Multiple Pedestrian Tracking

2018-10-19 · Brian H. Wang, Yan Wang, Kilian Q. Weinberger, Mark Campbell

We present a data association method for vision-based multiple pedestrian tracking, using deep convolutional features to distinguish between different people based on their appearances. These re-identification (re-ID) fe…

Person Re-IdentificationTranslation