Improved lightweight road damage detection based on YOLOv5
Improved lightweight road damage detection based on YOLOv5
Chang Liu,Yu Sun,2 Authors,Fengchao Wang
2025 · DOI: 10.1007/s11801-025-4125-6
Optoelectronics Letters · 5 Citations
TLDR
The convolutional neural network + ghosting bottleneck + ghosting bottleneck architecture is utilized to reduce redundant feature maps and the number of parameters and model size of the improved algorithm have been reduced by nearly half compared to the YOLOv5s.
