With the continuous development of science and technology, more and more fields are applying emerging video surveillance technology to ensure public safety. Compared with the way of manually processing video, the video monitoring technology based on deep learning also has the advantages of higher efficiency, high accuracy and intelligence when processing more and more massive video image data. In this paper, aiming at the detection requirements of personnel intrusion in the perimeter of high-speed railways, it realizes cross-region tracking of suspicious persons. It studies the application of deep learning cross-region tracking algorithm based on ResNet-50 in high-speed railway perimeter intrusion detection, and analyzes its reliability and optimizes accuracy. The degree reached 88%. Compared with the results of other cross-region tracking algorithms, the detection accuracy is still high. Therefore, it can be seen that the high-speed rail perimeter cross-region target tracking based on deep learning is feasible and efficient.
Research on the Algorithm of Cross-region Target Tracking in the Perimeter of High Speed Railway Based on Deep Learning
Lect. Notes Electrical Eng.
International Conference on Electrical and Information Technologies for Rail Transportation ; 2021 October 21, 2021 - October 23, 2021
Proceedings of the 5th International Conference on Electrical Engineering and Information Technologies for Rail Transportation (EITRT) 2021 ; Kapitel : 19 ; 176-183
2022-02-19
8 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
British Library Conference Proceedings | 2022
|Intrusion Detection for High-Speed Railway Perimeter Obstacle
British Library Conference Proceedings | 2018
|Target Tracking for High-Speed Railway Catenary Based on Correlation Filtering Algorithm
Springer Verlag | 2022
|Target Tracking for High-Speed Railway Catenary Based on Correlation Filtering Algorithm
British Library Conference Proceedings | 2022
|