Real-Time Obstacle Detection Method in the Driving Process of Driverless Rail Locomotives Based on DeblurGANv2 and Improved YOLOv4

Real-Time Obstacle Detection Method in the Driving Process of Driverless Rail Locomotives Based on DeblurGANv2 and Improved YOLOv4

In order to improve the detection accuracy of an algorithm in the complex environment of a coal mine, including low-illumination, motion-blur, occlusions, small-targets, and background-interference conditions; reduce the number of model parameters; improve the detection speed of the algorithm; and m...

Full description

Bibliographic Details
Main Authors: Wenshan Wang, Shuang Wang, Yanqiu Zhao, Jiale Tong, Tun Yang, Deyong Li
Format: Article
Language:English
Published: MDPI AG 2023-03-01
Series:Applied Sciences
Subjects:
YOLOv4 algorithm
Mobilenetv2
SA attention mechanism
focal loss function
K-means++
DeblurGANv2
Online Access:https://www.mdpi.com/2076-3417/13/6/3861

Similar Items

Similar Items