Dim-YOLOv5n昏暗场景目标检测算法OA北大核心CSTPCD
Dim-YOLOv5n Dim Scene Object Detection Algorithm
相比于正常光照场景,照明不良昏暗场景干扰因素较多,图像处理较为复杂,且现有的昏暗目标检测,存在参数量大,识别准确率低等不足.针对昏暗场景下目标检测算法中存在误检与漏检等问题,提出以YOLOv5n算法为基础进行改进的昏暗场景目标检测算法Dim-YOLOv5n.利用嵌入全维动态卷积(omni-dimensional dynamic convolution,ODConv)的轻量化主干ODConv-MobileNetV2替换主干网络,在减少计算量的同时提…查看全部>>
Compared with normal lighting scenes,there are many interference factors in poorly illuminated scenes there-fore image processing is more complex,and the existing dim object detection has shortcomings such as large number of parameters and low recognition accuracy.Aiming at the problems of false detection and missing detection in the target detec-tion algorithm in dim scenes,Dim-YOLOv5n,a target detection algorithm in dim scenes based on YOLOv5n algorithm is…查看全部>>
朱晓彤;张荣芬;刘宇红;孙龙
贵州大学 大数据与信息工程学院,贵阳 550025贵州大学 大数据与信息工程学院,贵阳 550025贵州大学 大数据与信息工程学院,贵阳 550025贵州大学 大数据与信息工程学院,贵阳 550025
计算机与自动化
昏暗图像YOLOv5n全维动态卷积(ODConv)MobileNetV2RepGFPNGhostConv
dim imageYOLOv5nomni-dimensional dynamic convolution(ODConv)MobileNetV2reparameterized generalized-FPN(RepGFPN)Ghost convolution(GhostConv)
《计算机工程与应用》 2024 (11)
173-181,9
贵州省基础研究(自然科学)项目(黔科合基础-ZK[2021]重点001).
评论