一种改进的YOLOv3-Tiny目标检测算法  

An Improved YOLOv3-Tiny Target Detection Algorithm

作　　者：杨铭 文斌[1] YANG Ming;WEN Bin(College of Communication Engineering,Chengdu University of Information Technology,Chengdu 610225,China)

机构地区：[1]成都信息工程大学通信工程学院,四川成都610225

出　　处：《成都信息工程大学学报》2020年第5期531-536,共6页Journal of Chengdu University of Information Technology

摘　　要：YOLOv3-Tiny作为YOLOv3目标检测算法的简化版本,拥有检测速度快、体积小、易于在边缘设备上部署等优点,同时也存在着识别精度低,定位不准的问题。由此在该算法的基础上进行改进,首先,对网络结构进行改进,在保证实时性的同时设计一个新的主干网络,提高网络的特征提取能力;其次改进目标损失函数和特征融合的策略,使用IOU损失函数代替原先边框位置损失函数,提高定位精度。实验结果表明,改进后的YOLOv3-Tiny算法,在保证实时性的情况下明显优于原算法。As a simplified version of YOLOv3 target detection algorithm,YOLOv3-Tiny has the advantages of fast detection speed,small size,easy to deploy on edge devices and so on.At the same time,it also has the problems of low recognition accuracy and inaccurate positioning.In this paper,the algorithm is improved.First of all,the network structure is improved.A new backbone network is designed on the premise of instantaneity,which improves the feature extraction ability of the network.Secondly,target loss function and border matching strategy are improved,and the IOU loss function is used to replace the original frame position loss function to improve the positioning accuracy.The experimental results show that the improved YOLOV3-Tiny algorithm is better than the original algorithm when the instantaneity is guaranteed.

关 键 词：深度学习 目标检测 YOLOv3-Tiny IOU 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]