基于自适应聚焦CRIoU损失的目标检测算法  

Object detection algorithm based on adaptive focal CRIoU loss

作　　者：肖振久[1] 赵昊泽 张莉莉 夏羽 郭杰龙 俞辉 李成龙 王俐文 XIAO Zhen-jiu;ZHAO Hao-ze;ZHANG Li-li;XIA Yu;GUO Jie-long;YU Hui;LI Cheng-long;WANG Li-wen(College of Software Engineering,Liaoning Technical University,Huludao 125000,China;Air Ammunition Research Institute Co.Ltd.,NORINCO Group,Haerbin 150000,China;Shanghai Institute of Aerospace System Engineer,Shanghai 201100,China;Quanzhou Institute of Equipment Manufacturing,Haixi Institutes,Chinese Academy of Sciences,Quanzhou 362000,China)

机构地区：[1]辽宁工程技术大学软件学院,辽宁葫芦岛125000 [2]中国兵器工业集团航空弹药研究院有限公司,黑龙江哈尔滨150000 [3]上海宇航系统工程研究所,上海201100 [4]中国科学院海西研究院泉州装备制造研究中心,福建泉州362000

出　　处：《液晶与显示》2023年第11期1468-1480,共13页Chinese Journal of Liquid Crystals and Displays

基　　金：福建省科技计划项目(No.2021T3003);泉州市科技计划项目(No.2021C065L)。

摘　　要：在目标检测任务中,传统的边界框回归损失函数所回归的内容与评价标准IoU(Intersection over Union)之间存在不相关性,并且对于边界框的回归属性存在一定不合理性,使得回归属性不完整,降低了检测精度和收敛速度,甚至还会造成回归阻碍的情况。并且在回归任务中也存在样本不均衡的情况,大量的低质量样本影响了损失收敛。为了提高检测精度和回归收敛速度提出了一种新的边界框回归损失函数。首先确定设计思想并设计IoU系列损失函数的范式;其次在IoU损失的基础上引入两中心点形成矩形的周长和两框形成的最小闭包矩形周长的比值作为边界框中心点距离惩罚项,并且将改进的IoU损失应用到非极大值抑制(Non-Maximum Suppression,NMS)处理中。接着引入两框的宽高误差和最小外包框的宽高平方作为宽高惩罚项,确定CRIoU(Complete Relativity IoU,CRIoU)损失函数。最后在CRIoU的基础上加入自适应加权因子,对高质量样本的回归损失加权,定义了自适应聚焦CRIoU(Adaptive focal CRIoU,AF-CRIoU)。实验结果表明,使用AF-CRIoU损失函数对比传统非IoU系列损失的检测精度最高相对提升了8.52%,对比CIoU系列损失的检测精度最高相对提升了2.69%,使用A-CRIoU-NMS(Around CRIoU NMS)方法对比原NMS方法的检测精度提升0.14%。将AF-CRIoU损失应用到安全帽检测中,也达到了很好的检测效果。In the object detection task,there is no correlation between the regression content of the traditional bounding box regression loss function and the evaluation standard IoU(Intersection over Union),and there is some irrationality for the regression attribute of the bounding box,which reduces the detection accuracy and convergence speed.In addition,the sample imbalance also exists in the regression task,and a large number of low-quality samples affect the loss function convergence.In this paper,a novel loss function,termed as CRIoU(Complete Relativity Intersection over Union),is proposed to improve the detection accuracy and convergence speed.Firstly,this work determines the design idea and determines the improved IoU loss function normal form.Secondly,on the basis of IoU loss,the ratio of the perimeter of the rectangle formed by the two center points and the minimum closure area formed by the two frames is introduced as the penalty term for the distance between the center points of the bounding box,and the improved IoU loss is applied to the non-maximum suppression.Then,the side error of the two frames and the side square of the minimum bounding box are introduced as the side penalty term,a novel loss function,termed as CRIoU(Complete Relativity Intersection over Union),is proposed.Finally,on the basis of CRIoU,an adaptive weighting factor is added to weight the regression loss of high-quality samples,and an AF-CRIoU(Adaptive focal CRIoU)is defined.The experimental results show that the detection accuracy of the AF-CRIoU loss function compared with the traditional non IoU series loss is up to 8.52%,the detection accuracy of the CIoU series loss is up to 2.69%,and the A-CRIoU NMS(Around CRIoU Non Maximum Suppression)method compared with the original NMS method is up to 0.14%.In addition,AF-CRIoU loss is applied to the detection of safety helmet,which also achieves good detection results.

关 键 词：目标检测 边界框回归 IoU损失函数 非极大值抑制 自适应聚焦损失 

分 类 号：TP389.1[自动化与计算机技术—计算机系统结构]