摘要
针对YOLOv3网络模型在交通场景中的目标检测指标优化问题,通过在网络训练过程中结合多种策略和技巧对模型指标进一步优化,同时提出了一种基于Cutout改进的抗遮挡策略。优化工作不涉及YOLOv3网络结构改动,并且优化后的模型不影响帧率指标。选用PASCAL VOC数据集和KITTI 2D数据集进行对比实验,结果表明,所采用的策略和技巧能够显著提升YOLOv3网络模型性能指标。实验完整代码已公布在以下链接,请点击查看或下载:https://github.com/LiweiDai/YOLOv3-training-optimization-with-applying-ACDC。
On the issue about optimizing the indices of object detection for YOLOv3 model in traffic scenes,we make the model indices further optimized by combining various strategies and tricks in the process of training,meanwhile,and we propose an improved anti-occlusion strategy based on Cutout.The optimization does not involve changes of the original YOLOv3 network structure,and there is no impact on FPS after optimizing.Comparison experiments are conducted on both PASCAL VOC and KITTI 2D,the obtained results show that these strategies and tricks can significantly improve the performance of YOLOv3 model.Full code has been released,click to view or download at:https://github.com/LiweiDai/YOLOv3-training-optimization-with-applying-ACDC.
作者
戴立伟
黄山
Dai Liwei;Huang Shan(College of Electrical Engineering,Sichuan University,Chengdu,Sichuan 610065,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2020年第14期336-344,共9页
Laser & Optoelectronics Progress
关键词
机器视觉
目标检测
图像处理
深度学习
machine vision
object detection
image processing
deep learning