Online Multi-Object Tracking

20 papers with code • 4 benchmarks • 5 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


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

Most implemented papers

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.

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.

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 30 Mar 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.

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.

Joint Monocular 3D Vehicle Detection and Tracking

ucbdrive/3d-vehicle-tracking ICCV 2019

The framework can not only associate detections of vehicles in motion over time, but also estimate their complete 3D bounding box information from a sequence of 2D images captured on a moving platform.

Online Multi-Object Tracking with Dual Matching Attention Networks

jizhu1023/DMAN_MOT ECCV 2018

In this paper, we propose an online Multi-Object Tracking (MOT) approach which integrates the merits of single object tracking and data association methods in a unified framework to handle noisy detections and frequent interactions between targets.

FANTrack: 3D Multi-Object Tracking with Feature Association Network

wise-lab/fantrack 7 May 2019

Instead, we exploit the power of deep learning to formulate the data association problem as inference in a CNN.