We propose a data-driven approach to online multi-object tracking (MOT) that uses a convolutional neural network (CNN) for data association in a tracking-by-detection framework. The problem of multi-target tracking aims to assign noisy detections to a-priori unknown and time-varying number of tracked objects across a sequence of frames. A majority of the existing solutions focus on either tediously designing cost functions or formulating the task of data association as a complex optimization problem that can be solved effectively. Instead, we exploit the power of deep learning to formulate the data association problem as inference in a CNN. To this end, we propose to learn a similarity function that combines cues from both image and spatial features of objects. Our solution learns to perform global assignments in 3D purely from data, handles noisy detections and varying number of targets, and is easy to train. We evaluate our approach on the challenging KITTI dataset and show competitive results. Our code is available at https://git.uwaterloo.ca/wise-lab/fantrack.
FANTrack: 3D Multi-Object Tracking with Feature Association Network
2019 IEEE Intelligent Vehicles Symposium (IV) ; 1426-1433
01.06.2019
3749537 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
FANTRACK: 3D MULTI-OBJECT TRACKING WITH FEATURE ASSOCIATION NETWORK
British Library Conference Proceedings | 2019
|AIAA | 2023
|Fast Multi-Feature Pyramids for Scale-Adaptive Object Tracking
British Library Online Contents | 2016
|Multi-feature Fusion Based Particle Filter Algorithm for Object Tracking
British Library Online Contents | 2012
|