30 October 2020 Data association framework based on biconnected gated recurrent unit network for multiple object tracking
Zaifeng Shi, Huizheng Ren, Qingjie Cao, Boyu Fan, Qiangqiang Fan
Author Affiliations +
Abstract

In the tracking-by-detection scheme of multiple object tracking (MOT), the data association process in which existing tracking data and new detections are matched over time is very important. A framework is proposed to solve the data association problem in MOT in scenarios where there are potential target interactions and occlusions in crowded environments. This framework consists of an input layer and an association layer. The input layer is an end-to-end feature-map extraction model that incorporates a simplified Siamese convolutional neural network, which effectively distinguishes similar objects based on their appearance and motion. The association layer is composed of a bidirectional gated recurrent unit network with three layers of fully connected networks (FCNs), whose outputs are fed into the FCNs and transformed into an association matrix that reflects the matching scores between the detections and existing tracks. The matrix is then used to minimize the loss of the framework. The experimental results show that the proposed framework demonstrates outstanding performance for MOT, with its accuracy and precision in MOT reaching values as high as 26.1% and 71.2%, respectively.

© 2020 SPIE and IS&T 1017-9909/2020/$28.00© 2020 SPIE and IS&T
Zaifeng Shi, Huizheng Ren, Qingjie Cao, Boyu Fan, and Qiangqiang Fan "Data association framework based on biconnected gated recurrent unit network for multiple object tracking," Journal of Electronic Imaging 29(5), 053017 (30 October 2020). https://doi.org/10.1117/1.JEI.29.5.053017
Received: 20 February 2020; Accepted: 15 October 2020; Published: 30 October 2020
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Video

Data processing

Target detection

Convolutional neural networks

Data modeling

Video surveillance

Machine vision

Back to Top