A Bayesian Filter for Multi-view 3D Multi-object Tracking with Occlusion Handling
This paper proposes an online multi-camera multi-object tracker that only requires monocular detector training, independent of the multi-camera configurations, allowing seamless extension/deletion of cameras without retraining effort. The proposed algorithm has a linear complexity in the total number of detections across the cameras, and hence scales gracefully with the number of cameras. It operates in the 3D world frame, and provides 3D trajectory estimates of the objects. The key innovation is a high fidelity yet tractable 3D occlusion model, amenable to optimal Bayesian multi-view multi-object filtering, which seamlessly integrates, into a single Bayesian recursion, the sub-tasks of track management, state estimation, clutter rejection, and occlusion/misdetection handling. The proposed algorithm is evaluated on the latest WILDTRACKS dataset, and demonstrated to work in very crowded scenes on a new dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Multi-Object TrackingManagementMulti-Object TrackingObject TrackingOcclusion HandlingState EstimationSimilar Papers 제목 키워드 기반
Three-dimensional Tracking of a Large Number of High Dynamic Objects from Multiple Views using Current Statistical Model
Three-dimensional tracking of multiple objects from multiple views has a wide range of applications, especially in the study of bio-cluster behavior which requires precise trajectories of research objects. However, there…
Track Initialization and Re-Identification for~3D Multi-View Multi-Object Tracking
We propose a 3D multi-object tracking (MOT) solution using only 2D detections from monocular cameras, which automatically initiates/terminates tracks as well as resolves track appearance-reappearance and occlusions. More…
3D Multi-Object TrackingMulti-Object TrackingObjectObject Tracking+1GNN-PMB: A Simple but Effective Online 3D Multi-Object Tracker without Bells and Whistles
Multi-object tracking (MOT) is among crucial applications in modern advanced driver assistance systems (ADAS) and autonomous driving (AD) systems. The global nearest neighbor (GNN) filter, as the earliest random vector-b…
Autonomous DrivingMulti-Object TrackingObject TrackingMulti-view Sensor Fusion by Integrating Model-based Estimation and Graph Learning for Collaborative Object Localization
Collaborative object localization aims to collaboratively estimate locations of objects observed from multiple views or perspectives, which is a critical ability for multi-agent systems such as connected vehicles. To ena…
Autonomous DrivingGraph LearningObjectObject Localization+2Activity Recognition in Assembly Tasks by Bayesian Filtering in Multi-Hypergraphs
We study sensor-based human activity recognition in manual work processes like assembly tasks. In such processes, the system states often have a rich structure, involving object properties and relations. Thus, estimating…
Activity RecognitionHuman Activity Recognition