With the rapid development of high-speed railway technology, ensuring its operational safety has become a critical issue. In particular, real-time monitoring of the high-speed railway pantograph system is of utmost importance for preventing failures and reducing the incidence of accidents. The aim of this research is to enhance the intelligent detection performance of the high-speed railway pantograph network status, especially in the detection of bird nests, through an improved MobileNetV3 algorithm. The research methodology includes the application of deep learning and image processing technologies, focusing on optimizing the MobileNetV3 algorithm to increase its detection accuracy in complex environments, particularly its ability to identify bird nests in complex scenes and adapt to dynamic environments. It is expected that these improvements will enable more accurate and efficient monitoring of the status of high-speed railway pantographs, thereby enhancing the safe operation level of high-speed railways.
Research on Key Technologies for Bird's Nest Detection in High-Speed Railway Catenary Systems Based on Deep Learning
2024-11-15
1250441 byte
Conference paper
Electronic Resource
English
Engineering Index Backfile | 1933
|Lightning Protection Research and Simulation of High-Speed Railway Catenary
Trans Tech Publications | 2014
|Overview of Detection and Estimation of High-Speed Railway Catenary
Springer Verlag | 2016
|High-speed railway catenary dropper calibration special operation vehicle
European Patent Office | 2021
|