Education, Science, Technology, Innovation and Life
Open Access
Sign In

Target Detection based on K-means Algorithm

Download as PDF

DOI: 10.23977/ESAC2020042


Bohao Chen, Rong Fu, Yifan Ding

Corresponding Author

Bohao Chen


In recent years, the application of deep learning to the safety of high-speed rail has been a hot research topic. In this paper, we have developed an improved yolov3 foreign body intrusion detection algorithm based on K-means++, which can realize accurate and fast identification of high-speed rail perimeter intrusion. In addition, we use K-means++ algorithm to improve yolov3 algorithm. After comparing the relevant precision indexes, we have obtained that the improved yolov3 algorithm with K++ is obviously better than the traditional image recognition algorithm, which can realize the precise prevention and control of high-speed rail perimeter intrusion.


Rail transportation security; perimeter intrusion; deep learning; K-means algorithm; yolov3

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.