Laser & Optoelectronics Progress, Volume. 59, Issue 16, 1610008(2022)
Lightweight YOLOv3 Algorithm for Small Object Detection
To improve the detection speed of the YOLOv3-CS algorithm for remote sensing image target detection, an adaptive sparse factor adjustment algorithm based on the γ parameter of the Batch Normalization (BN) layer is proposed. YOLOv3-CS was pruned to obtain YOLOv3-CSP using γ as the basis for determining the channel importance. The experimental results show that the proposed pruning method reduces the model size by 95.92%, while increasing the detection speed by 173%, when the mean Average Precision (mAP) loss of YOLOv3-CS is 0.22%. The YOLOv3-CSP can be applied to certain occasions requiring high detection accuracy and real-time performance.
Get Citation
Copy Citation Text
Guanrong Zhang, Xiang Chen, Yu Zhao, Jianjun Wang, Guobiao Yi. Lightweight YOLOv3 Algorithm for Small Object Detection[J]. Laser & Optoelectronics Progress, 2022, 59(16): 1610008
Category: Image Processing
Received: Mar. 29, 2021
Accepted: Jul. 13, 2021
Published Online: Jul. 22, 2022
The Author Email: Zhao Yu (5325975@qq.com)