Online Multi-Object Tracking

28 papers with code • 5 benchmarks • 9 datasets

The goal of Online Multi-Object Tracking is to estimate the spatio-temporal trajectories of multiple objects in an online video stream (i.e., the video is provided frame-by-frame), which is a fundamental problem for numerous real-time applications, such as video surveillance, autonomous driving, and robot navigation.

Source: A Hybrid Data Association Framework for Robust Online Multi-Object Tracking

Libraries

Use these libraries to find Online Multi-Object Tracking models and implementations
2 papers
18

Most implemented papers

PP-YOLOE: An evolved version of YOLO

PaddlePaddle/PaddleDetection 30 Mar 2022

In this report, we present PP-YOLOE, an industrial state-of-the-art object detector with high performance and friendly deployment.

No Blind Spots: Full-Surround Multi-Object Tracking for Autonomous Vehicles using Cameras & LiDARs

ken-power/SensorFusionND-3D-Object-Tracking 23 Feb 2018

In this paper, we present a modular framework for tracking multiple objects (vehicles), capable of accepting object proposals from different sensor modalities (vision and range) and a variable number of sensors, to produce continuous object tracks.

Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification

longcw/MOTDT 12 Sep 2018

Online multi-object tracking is a fundamental problem in time-critical video analysis applications.

Online Multi-Object Tracking Framework with the GMPHD Filter and Occlusion Group Management

SonginCV/GMPHD-OGM_Tracker 31 Jul 2019

In this paper, we propose an efficient online multi-object tracking framework based on the GMPHD filter and occlusion group management scheme where the GMPHD filter utilizes hierarchical data association to reduce the false negatives caused by miss detection.

GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization

IPapakis/GCNNMatch 30 Sep 2020

This new paradigm enables the network to leverage the "context" information of the geometry of objects and allows us to model the interactions among the features of multiple objects.

Large-Scale Pre-training for Person Re-identification with Noisy Labels

dengpanfu/luperson-nl CVPR 2022

Since theses ID labels automatically derived from tracklets inevitably contain noises, we develop a large-scale Pre-training framework utilizing Noisy Labels (PNL), which consists of three learning modules: supervised Re-ID learning, prototype-based contrastive learning, and label-guided contrastive learning.

Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking

ymzis69/HybridSORT 1 Aug 2023

Also, our method shows strong generalization for diverse trackers and scenarios in a plug-and-play and training-free manner.

Online multi-object tracking via robust collaborative model and sample selection

MNaiel/rcmss Computer Vision and Image Understanding 2017

For each frame, we construct an association between detections and trackers, and treat each detected image region as a key sample, for online update, if it is associated to a tracker.

Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking

JunaidCS032/MOTBeyondPixels 26 Feb 2018

This paper introduces geometry and object shape and pose costs for multi-object tracking in urban driving scenarios.

Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers

zhen-he/tracking-by-animation CVPR 2019

To achieve both label-free and end-to-end learning of MOT, we propose a Tracking-by-Animation framework, where a differentiable neural model first tracks objects from input frames and then animates these objects into reconstructed frames.