paper-with-me

Papers

Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation

2022-01-04 · Qiankun Liu, Dongdong Chen, Qi Chu, Lu Yuan, Bin Liu, Lei Zhang, Nenghai Yu

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.

📄 PDF Abstract BibTeX arXiv:2201.01297

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Object TrackingObjectObject TrackingOcclusion EstimationOnline Multi-Object Tracking

Similar Papers 제목 키워드 기반

Simple online and real-time tracking with occlusion handling

2021-03-06 · Mohammad Hossein Nasseri, Hadi Moradi, Reshad Hosseini, Mohammadreza Babaee

Multiple object tracking is a challenging problem in computer vision due to difficulty in dealing with motion prediction, occlusion handling, and object re-identification. Many recent algorithms use motion and appearance…

motion predictionMultiple Object TrackingObjectObject Tracking+1

Supervised and Unsupervised Detections for Multiple Object Tracking in Traffic Scenes: A Comparative Study

2020-03-30 · Hui-Lee Ooi, Guillaume-Alexandre Bilodeau, Nicolas Saunier

In this paper, we propose a multiple object tracker, called MF-Tracker, that integrates multiple classical features (spatial distances and colours) and modern features (detection labels and re-identification features) in…

Multiple Object TrackingObjectObject Tracking

Memory Based Online Learning of Deep Representations from Video Streams

2017-11-17 · CVPR 2018 6 · Federico Pernici, Federico Bartoli, Matteo Bruni, Alberto del Bimbo

We present a novel online unsupervised method for face identity learning from video streams. The method exploits deep face descriptors together with a memory based learning mechanism that takes advantage of the temporal …

Face Identification

Online Metric-Weighted Linear Representations for Robust Visual Tracking

2015-07-21 · Xi Li, Chunhua Shen, Anthony Dick, Zhongfei Zhang 외

In this paper, we propose a visual tracker based on a metric-weighted linear representation of appearance. In order to capture the interdependence of different feature dimensions, we develop two online distance metric le…

Metric LearningObjectObject TrackingVisual Tracking

Simple Unsupervised Multi-Object Tracking

2020-06-04 · Shyamgopal Karthik, Ameya Prabhu, Vineet Gandhi

Multi-object tracking has seen a lot of progress recently, albeit with substantial annotation costs for developing better and larger labeled datasets. In this work, we remove the need for annotated datasets by proposing …

Multi-Object TrackingObjectObject Tracking