Improved YOLOv3-Based Bridge Surface Defect Detection by Combining High- and Low-Resolution Feature Images

Improved YOLOv3-Based Bridge Surface Defect Detection by Combining High- and Low-Resolution Feature Images

Automatic bridge surface defect detection is of wide concern; it can save human resources and improve work efficiency. The object detection algorithm, especially the You Only Look Once (YOLO) series of networks, has important potential in real-time object detection because of its fast detection spee...

Full description

Bibliographic Details
Main Authors: Shuai Teng, Zongchao Liu, Xiaoda Li
Format: Article
Language:English
Published: MDPI AG 2022-08-01
Series:Buildings
Subjects:
YOLO network
surface defect
transfer learning
data augmentation
detection precision and speed
Online Access:https://www.mdpi.com/2075-5309/12/8/1225

Internet

https://www.mdpi.com/2075-5309/12/8/1225

Similar Items