Open Access

ARTICLE

CNN-Based Multi-Object Tracking Networks with Position Correction and IMM in Intelligent Transportation System

by

1 Guangdong Atv Academy For Performing Arts, Guangdong, China
2 Department of Computer Science, Baoji University of Arts and Sciences, Baoji, China
3 Software Convergence Engineering Department, Kunsan National University, Gunsan, Korea
*: Correspondence
Email: renchengjuan163@163.com

Revista Internacional de Métodos Numéricos para Cálculo y Diseño en Ingeniería 2023, 39(4), 1-12. https://doi.org/10.23967/j.rimni.2023.11.001

Abstract

In multi-object tracking of Intelligent Transportation System, there are objects of different sizes in images or videos, especially pedestrian and traffic lights with low resolution in the image. Meantime, objects are subject to occlusion or loss in object tracking. All of the above-mentioned situations may lead to unsatisfactory multi-object tracking results. Attracted by the effect of deep convolution neural networks, the paper proposes a multi-object tracking network, CNN-Based Multi-Object Tracking Networks with Position Correction and IMM (CNN_PC_IMM) to solve those problems. Our proposed method consists of object detection module and object tracking module. Compared to other networks, our proposed network has several main contributions that play an essential role in achieving state-of-the-art object tracking performance. In the detection phase, the feature fusion technique is used. We add a scale branch to the YOLOv3 network to increase the accuracy of small object prediction and import a residual structure to enhance gradient propagation and avoid gradient disappearance and explosion for the whole network. In addition, we determine the size of the anchor box based on the size of the object in the dataset to better detect and track the objects. In the tracking phase, IMM is used to calculate the motion state information of the object at a certain moment. Next, the optimization algorithm is proposed to fine-tune object position when the tracking object is occluded due to dense multi-object in traffic scenes or lost due to incomplete object information. Finally, experimental results and analysis are performed on the MOT16 benchmark dataset with several popular tracking algorithms used to compare the performance with the proposed algorithm in the paper. It is demonstrated that the proposed network has better performance on MOPA, MOTP, ML.

---

Keywords

---