Table of Content

Open Access iconOpen Access

ARTICLE

crossmark

Vehicle Target Detection Method Based on Improved SSD Model

Guanghui Yu1, Honghui Fan1, Hongyan Zhou1, Tao Wu1, Hongjin Zhu1, *

1 College of Computer Engineering, Jiangsu University of Technology, Changzhou, 213001, China.

* Corresponding Author: Hongjin Zhu. Email: email.

Journal on Artificial Intelligence 2020, 2(3), 125-135. https://doi.org/10.32604/jai.2020.010501

Abstract

When we use traditional computer vision Inspection technology to locate the vehicles, we find that the results were unsatisfactory, because of the existence of diversified scenes and uncertainty. So, we present a new method based on improved SSD model. We adopt ResNet101 to enhance the feature extraction ability of algorithm model instead of the VGG16 used by the classic model. Meanwhile, the new method optimizes the loss function, such as the loss function of predicted offset, and makes the loss function drop more smoothly near zero points. In addition, the new method improves cross entropy loss function of category prediction, decreases the loss when the probability of positive prediction is high effectively, and increases the speed of training. In this paper, VOC2012 data set is used for experiment. The results show that this method improves average accuracy of detection and reduces the training time of the model.

Keywords


Cite This Article

APA Style
Yu, G., Fan, H., Zhou, H., Wu, T., Zhu, H. (2020). Vehicle target detection method based on improved SSD model. Journal on Artificial Intelligence, 2(3), 125-135. https://doi.org/10.32604/jai.2020.010501
Vancouver Style
Yu G, Fan H, Zhou H, Wu T, Zhu H. Vehicle target detection method based on improved SSD model. J Artif Intell . 2020;2(3):125-135 https://doi.org/10.32604/jai.2020.010501
IEEE Style
G. Yu, H. Fan, H. Zhou, T. Wu, and H. Zhu "Vehicle Target Detection Method Based on Improved SSD Model," J. Artif. Intell. , vol. 2, no. 3, pp. 125-135. 2020. https://doi.org/10.32604/jai.2020.010501

Citations




cc Copyright © 2020 The Author(s). Published by Tech Science Press.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 2944

    View

  • 1862

    Download

  • 3

    Like

Related articles

Share Link