Titlebook: Deep Learning-Based Detection of Catenary Support Component Defect and Fault in High-Speed Railways; Zhigang Liu,Wenqiang Liu,Junping Zhon

吹牛者

reject

2363-5010 ults of the catenary detection.Adopts and improves the advan.This book focuses on the deep learning technologies and their applications in the catenary detection of high-speed railways. As the only source of power for high-speed trains, the catenary‘s service performance directly affects the safe op

細(xì)胞

,Preprocessing of Catenary Support Components’ Images,etection difficulty. In addition, in the process of receiving, transmitting, and processing, the image will also be affected by noise such as electromagnetic interference of the sensor, resulting in a decline in image quality and affecting the detection accuracy.

AGONY

surmount

d-limonene

https://doi.org/10.1007/978-3-531-90356-9asic deep learning frameworks of object detection (e.g., Faster R-CNN, YOLO, and SSD) are introduced in CSC positioning, simultaneous positioning of multiple classes of components with high speed and accuracy is achieved. However, it still faces the following challenges.

去才蔑視

率直

同位素

Positioning of Catenary Support Components,extract handcrafted features (e.g., SIFT, SURF, and HoG) of the template component image and global catenary image and then adapt the feature-matching approach to locate the target component. These methods can only locate one class component at a time and have low accuracy and efficiency. When the b

攤位