Online Multi-Object Tracking with Unsupervised Re-Identification
Learning and Occlusion Estimation
- URL: http://arxiv.org/abs/2201.01297v1
- Date: Tue, 4 Jan 2022 18:59:58 GMT
- Title: Online Multi-Object Tracking with Unsupervised Re-Identification
Learning and Occlusion Estimation
- Authors: Qiankun Liu and Dongdong Chen and Qi Chu and Lu Yuan and Bin Liu and
Lei Zhang and Nenghai Yu
- Abstract summary: Occlusion between different objects is a typical challenge in Multi-Object Tracking (MOT)
In this paper, we focus on online multi-object tracking and design two novel modules to handle these problems.
The proposed unsupervised re-identification learning module does not require any (pseudo) identity information nor suffer from the scalability issue.
Our study shows that, when applied to state-of-the-art MOT methods, the proposed unsupervised re-identification learning is comparable to supervised re-identification learning.
- Score: 80.38553821508162
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Occlusion between different objects is a typical challenge in Multi-Object
Tracking (MOT), which often leads to inferior tracking results due to the
missing detected objects. The common practice in multi-object tracking is
re-identifying the missed objects after their reappearance. Though tracking
performance can be boosted by the re-identification, the annotation of identity
is required to train the model. In addition, such practice of re-identification
still can not track those highly occluded objects when they are missed by the
detector. In this paper, we focus on online multi-object tracking and design
two novel modules, the unsupervised re-identification learning module and the
occlusion estimation module, to handle these problems. Specifically, the
proposed unsupervised re-identification learning module does not require any
(pseudo) identity information nor suffer from the scalability issue. The
proposed occlusion estimation module tries to predict the locations where
occlusions happen, which are used to estimate the positions of missed objects
by the detector. Our study shows that, when applied to state-of-the-art MOT
methods, the proposed unsupervised re-identification learning is comparable to
supervised re-identification learning, and the tracking performance is further
improved by the proposed occlusion estimation module.
Related papers
- Keypoint Promptable Re-Identification [76.31113049256375]
Occluded Person Re-Identification (ReID) is a metric learning task that involves matching occluded individuals based on their appearance.
We introduce Keypoint Promptable ReID (KPR), a novel formulation of the ReID problem that explicitly complements the input bounding box with a set of semantic keypoints.
We release custom keypoint labels for four popular ReID benchmarks. Experiments on person retrieval, but also on pose tracking, demonstrate that our method systematically surpasses previous state-of-the-art approaches.
arXiv Detail & Related papers (2024-07-25T15:20:58Z) - Few-shot Oriented Object Detection with Memorable Contrastive Learning in Remote Sensing Images [11.217630579076237]
Few-shot object detection (FSOD) has garnered significant research attention in the field of remote sensing.
We propose a novel FSOD method for remote sensing images called Few-shot Oriented object detection with Memorable Contrastive learning (FOMC)
Specifically, we employ oriented bounding boxes instead of traditional horizontal bounding boxes to learn a better feature representation for arbitrary-oriented aerial objects.
arXiv Detail & Related papers (2024-03-20T08:15:18Z) - Unsupervised Continual Anomaly Detection with Contrastively-learned
Prompt [80.43623986759691]
We introduce a novel Unsupervised Continual Anomaly Detection framework called UCAD.
The framework equips the UAD with continual learning capability through contrastively-learned prompts.
We conduct comprehensive experiments and set the benchmark on unsupervised continual anomaly detection and segmentation.
arXiv Detail & Related papers (2024-01-02T03:37:11Z) - Object-Centric Multiple Object Tracking [124.30650395969126]
This paper proposes a video object-centric model for multiple-object tracking pipelines.
It consists of an index-merge module that adapts the object-centric slots into detection outputs and an object memory module.
Benefited from object-centric learning, we only require sparse detection labels for object localization and feature binding.
arXiv Detail & Related papers (2023-09-01T03:34:12Z) - Occlusion-Aware Detection and Re-ID Calibrated Network for Multi-Object
Tracking [38.36872739816151]
Occlusion-Aware Attention (OAA) module in the detector highlights the object features while suppressing the occluded background regions.
OAA can serve as a modulator that enhances the detector for some potentially occluded objects.
We design a Re-ID embedding matching block based on the optimal transport problem.
arXiv Detail & Related papers (2023-08-30T06:56:53Z) - The detection and rectification for identity-switch based on unfalsified
control [12.983011293631199]
The purpose of multi-object tracking (MOT) is to continuously track and identify objects detected in videos.
Currently, most methods for multi-object tracking model the motion information and combine it with appearance information to determine and track objects.
In this paper, unfalsified control is employed to address the ID-switch problem in multi-object tracking.
arXiv Detail & Related papers (2023-07-27T02:30:12Z) - Discovery-and-Selection: Towards Optimal Multiple Instance Learning for
Weakly Supervised Object Detection [86.86602297364826]
We propose a discoveryand-selection approach fused with multiple instance learning (DS-MIL)
Our proposed DS-MIL approach can consistently improve the baselines, reporting state-of-the-art performance.
arXiv Detail & Related papers (2021-10-18T07:06:57Z) - Learning to Track with Object Permanence [61.36492084090744]
We introduce an end-to-end trainable approach for joint object detection and tracking.
Our model, trained jointly on synthetic and real data, outperforms the state of the art on KITTI, and MOT17 datasets.
arXiv Detail & Related papers (2021-03-26T04:43:04Z) - Multi-object Tracking with a Hierarchical Single-branch Network [31.680667324595557]
We propose an online multi-object tracking framework based on a hierarchical single-branch network.
Our novel iHOIM loss function unifies the objectives of the two sub-tasks and encourages better detection performance.
Experimental results on MOT16 and MOT20 datasets show that we can achieve state-of-the-art tracking performance.
arXiv Detail & Related papers (2021-01-06T12:14:58Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.