基于改进YOLOv5m的弱小目标识别方法 |
| |
引用本文: | 杨文涛,张维光.基于改进YOLOv5m的弱小目标识别方法[J].计算机测量与控制,2022,30(12):218-223. |
| |
作者姓名: | 杨文涛 张维光 |
| |
作者单位: | 西安工业大学光电工程学院, |
| |
基金项目: | 航空科学基金(202000190U1002) |
| |
摘 要: | 针对空对地观测弱小目标识别与跟踪技术需求,提出了一种改进型YOLOv5m网络的多目标识别检测方法,以提升对所占像素个数小于10*10弱小目标的识别能力;分析了网络结构输入端Mosaic数据增强、Anchor计算、Focus模块及SPP模块对弱小目标的影响;在深度学习网络Prediction层引入距离交并比非极大值抑制(DIoU-NMS)代替传统非极大值抑制(NMS),引入距离交并比损失函数(DIoU_Loss)代替广义化交并比损失函数(GIoU_Loss),加快边界框回归速率,提高定位精度,消除重叠检测,并在网络中引入4*4以上像素的目标识别层,提升对遮挡重叠弱小目标识别的准确率;实验结果表明,改进的深度学习网络算法与经典的YOLOv5m网络相比,目标识别的均值平均精度mAP指标达到89.7%,对比原网络提高了4.1%,实现了对图像像素个数小于10*10的弱小目标高精度识别,有效提升了深度学习网络对弱小目标的适应性和应用价值。
|
关 键 词: | 多目标识别 yolov5m 损失函数 目标识别层 深度学习 |
收稿时间: | 2022/5/5 0:00:00 |
修稿时间: | 2022/5/31 0:00:00 |
Weak and Small Targets Recognition Method Based on Improved YOLOv5m |
| |
Abstract: | Aiming at the needs of air-to-earth observation weak and small target recognition and tracking technology, an improved multi-target recognition and detection method of YOLOv5m network is proposed to improve the recognition ability of weak and small targets with less than 10*10 pixels; The influence of Mosaic data enhancement, Anchor calculation, Focus module and SPP module on weak and small targets at the input end of the network structure is analyzed; In the Prediction layer of the deep learning network, the distance intersection over union non-maximum suppression (DIoU-NMS) is introduced to replace the traditional non-maximum suppression (NMS), and the distance intersection over union loss function (DIoU_Loss) is introduced to replace the generalized intersection over union loss function (GIoU_Loss), speed up the bounding box regression rate, improve the positioning accuracy, eliminate overlapping detection, and introduce a target recognition layer with more than 4*4 pixels in the network to improve the accuracy of occlusion overlapping weak and small targets; The experimental results show that, compared with the classic YOLOv5m network, the improved deep learning network algorithm achieves an average average precision mAP index of 89.7%, which is 4.1% higher than the original network, and realizes the image pixel number less than 10*10. The high-precision identification of weak and small targets effectively improves the adaptability and application value of the deep learning network to weak and small targets. |
| |
Keywords: | multi-target recognition yolov5m loss function object recognition layer deep learning |
|
| 点击此处可从《计算机测量与控制》浏览原始摘要信息 |
|
点击此处可从《计算机测量与控制》下载全文 |
|