摘要
YOLOv3目标检测算法检测速度快且精度较高,但存在对小目标检测能力不足、边界框定位不准确等问题。提出了一种基于YOLOv3改进的目标检测算法,该算法在YOLOv3的基础上,对网络中的残差块增加旁路连接,进一步进行特征重用,以提取更多的特征信息。同时,采用GIoUloss作为边界框的损失,使网络朝着预测框与真实框重叠度较高的方向去优化。在损失函数中加入Focal loss,减小正负样本不平衡带来的误差。在PASCAL VOC和COCO数据集上的实验结果表明,该算法能够在不影响YOLOv3算法实时性的前提下,提高目标检测的mAP。该算法在PASCAL VOC 2007测试集上达到83.7mAP(IoU=0.5),在COCO测试集上比YOLOv3算法提升2.27mAP(IoU[0.5,0.95])。
As an object detection algorithm,YOLOv3 can achieve fast detection speed and high detection accuracy.However,YOLOv3 has the problems of low detection accuracy for small objects and inaccurate boundary box location.In this paper,an improved YOLOv3 object detection algorithm is proposed,which increases the bypass connection between residual blocks in darknet-53 and further reuses the features to extract more feature information.At the same time,GIoU loss is used as the loss of bounding box,which can make the network optimize in the direction of high overlap between prediction box and ground truth.In addition,in order to reduce the error caused by the imbalance of positive and negative samples,Focal loss is added to the loss function.The experimental results on PASCAL VOC and COCO datasets show that the improved YOLOv3 algorithm can improve the accuracy of object detection on the premise of real-time performance.Compared with YOLOv3,the improved YOLOv3 algorithm reaches 83.7 mAP(IoU=0.5)in PASCAL VOC 2007 test and improves 2.27mAP(IoU[0.5,0.95])on the COCO datasets.
作者
邹承明
薛榕刚
ZOU Chengming;XUE Ronggang(Hubei Key Laboratory of Transportation Internet of Things,Wuhan 430070,China;School of Computer Science and Technology,Wuhan University of Technology,Wuhan 430070,China;Peng Cheng Laboratory,Shenzhen,Guangdong 518000,China)
出处
《计算机工程与应用》
CSCD
北大核心
2020年第24期214-222,共9页
Computer Engineering and Applications
基金
国家重点研发计划(No.2018YFC0704300)。
