基于YOLOv3的定向目标检测算法  

Directional Target Detection Algorithm Based on YOLOv3

作　　者：辛月兰 朱杰 谢琪琦 XIN Yue-lan;ZHU Jie;XIE Qi-qi(School of Physical and Electronic Information Engineering,Qinghai Normal University,Xining Qinghai 810008,China;State Key Laboratory of Tibetan Inteligent Information Processing and Application,Xining Qinghai 810001,China)

机构地区：[1]青海师范大学物理与电子信息工程学院,青海西宁810008 [2]省部共建藏语智能信息处理及应用国家重点实验室,青海西宁810001

出　　处：《计算机仿真》2024年第5期251-257,共7页Computer Simulation

基　　金：国家自然科学基金项目(61662062);青海省自然科学基金面上项目(2022-ZJ-929)。

摘　　要：为解决YOLOv3目标检测算法中无法对旋转物体进行定向目标检测的问题,提出一种基于YOLOv3的定向目标检测算法。首先,使用多维坐标对训练集的图像进行定向标定,以适应网络训练;其次使用最小外接矩形对网络输出的矩形框进行修正优化,以获得更加准确贴合的检测框;然后对网络的损失函数进行改进,使其适应多维坐标的回归;最后,对改进后的网络进行训练。在UCAS-AOD数据集上的实验结果表明,目标检测的能力在改进后有了明显提升,比原始YOLOv3算法精确率提高了6.1%,召回率提高了3.2%。In order to solve the problem that the YOLOv3 target detection algorithm cannot detect the directional target of rotating objects,this paper proposes a directional target detection algorithm based on YOLOv3.Firstly,this method used the multi-dimensional coordinate to align the training set to suit the training of the network.Scoendly,the rectangular box output from the network was optimized using the minimum outer rectangle to obtain a more accurate fit of the detection box.Next,the loss function of the network was improved to adapt it to the regression of multidimensional coordinates.Finally,the improved network wais trained.The experimental results on the UCAS-AOD dataset show that the ability of target detection is significantly improved after the improvement,with a 6.1%increase in accuracy and a 3.2%increase in recall over the original YOLOv3 algorithm.

关 键 词：定向目标检测 多维坐标 最小外接矩形 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]