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.
LibrariesUse these libraries to find Online Multi-Object Tracking models and implementations
Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification
Online multi-object tracking is a fundamental problem in time-critical video analysis applications.
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.
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.
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.
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.
This paper introduces geometry and object shape and pose costs for multi-object tracking in urban driving scenarios.
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.
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.