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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

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




    Publication date :

    2019-06-01


    Size :

    3749537 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    FANTRACK: 3D MULTI-OBJECT TRACKING WITH FEATURE ASSOCIATION NETWORK

    Baser, Erkan / Balasubramanian, Venkateshwaran / Bhattacharyya, Prarthana et al. | British Library Conference Proceedings | 2019



    Fast Multi-Feature Pyramids for Scale-Adaptive Object Tracking

    Yang, Yuan / Ku, Tao / Zha, Yufei et al. | British Library Online Contents | 2016



    Multi-feature Fusion Based Particle Filter Algorithm for Object Tracking

    Liu, S. / Zhu, W. / Yang, F. et al. | British Library Online Contents | 2012