基于DSGIoU损失与双分支坐标注意力的目标检测算法  

Object detection algorithm based on DSGIoU loss and dual branch coordinate attention

作　　者：马素刚 李宁博[1] 侯志强 余旺盛 杨小宝[1] MA Sugang;LI Ningbo;HOU Zhiqiang;YU Wangsheng;YANG Xiaobao(School of Computer Science&Technology,Xi’an University of Posts&Telecommunications,Xi’an 710121,China;Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing,Xi’an University of Posts&Telecommunications,Xi’an 710121,China;School of Information and Navigation,Air Force Engineering University,Xi’an 710077,China)

机构地区：[1]西安邮电大学计算机学院,西安710121 [2]西安邮电大学陕西省网络数据分析与智能处理重点实验室,西安710121 [3]空军工程大学信息与导航学院,西安710077

出　　处：《北京航空航天大学学报》2025年第4期1085-1095,共11页Journal of Beijing University of Aeronautics and Astronautics

基　　金：国家自然科学基金(62072370);陕西省自然科学基金(2023-JC-YB-598);西安市科技计划(22GXFW0125)。

摘　　要：针对YOLOX算法中边界框回归损失效果有限和多尺度特征表示能力不足,导致检测结果不准确的问题,提出一种基于距离形状广义交并比(DSGIoU)损失与双分支坐标注意力的目标检测算法。在交并比(IoU)损失项的基础上,通过添加真实框与预测框之间的非重叠面积、中心点距离及宽高比3个惩罚项,优化边界框的回归收敛效果;通过平均池化和最大池化沿着2个方向对特征进行编码,获取方向感知信息和位置信息,从而对特征进行增强。为验证所提算法的检测性能,分别以网络大小为Tiny、S、M的YOLOX为基准,在PASCAL VOC和KITTI数据集上进行测试。实验结果表明:所提算法在PASCAL VOC数据集上的检测精度分别达到80.0%、82.6%、85.8%,相比基准算法YOLOX提升了1.5%、1.6%、2.0%;在KITTI数据集上的检测精度分别达到87.7%、89.7%、90.7%,相比基准算法YOLOX提升了1.7%、2.9%、1.3%。所提算法能够优化网络收敛性,提高多尺度特征的表示能力,有效提高检测精度。The bounding box regression loss effect is limited,and the multi-scale feature representation ability is insufficient in the YOLOX algorithm,which leads to inaccurate detection results.To address this issue,an object detection algorithm based on distance shape of generalized intersection over union(DSGIoU)loss and dual branch coordinate attention was proposed.Based on the intersection over union(IoU)loss term,the regression convergence effect of the bounding box was optimized by adding three penalty terms:non-overlapping area,distance from the center,and aspect ratio between the true box and the predicted box.Meanwhile,the feature was encoded in two directions by using average pooling and max pooling to obtain directional perception information and position information,so as to enhance the feature.To demonstrate the detection performance of the proposed algorithm,YOLOX with network sizes of Tiny,S,and M was used as the benchmark to carry out tests on PASCAL VOC and KITTI datasets.The experimental results show that the detection accuracy of the proposed algorithm on the PASCAL VOC dataset reaches 80.0%,82.6%,and 85.8%,respectively,which is 1.5%,1.6%,and 2.0%higher than the YOLOX as the benchmark.On the KITTI dataset,the detection accuracy reaches 87.7%,89.7%,and 90.7%,which is increased by 1.7%,2.9%,and 1.3%,respectively.The proposed algorithm can optimize the network convergence,improve the representation ability of multi-scale features,and significantly boost the detection accuracy.

关 键 词：目标检测 损失函数 边界框回归 坐标注意力 YOLOX 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]