基于YOLOv5s的无人机图像车辆检测
Vehicle Detection in UAV Image Based on YOLOv5s
王涛 1黄丹 1刘禅奕 1朱桃1
作者信息
- 1. 四川轻化工大学自动化与信息工程学院,四川 宜宾 644002;四川轻化工大学人工智能四川省重点实验室,四川 宜宾 644002
- 折叠
摘要
无人机拍摄的车辆图像存在背景复杂、目标尺度变化大的问题,导致现有的网络模型在进行车辆检测时很难检测出小目标物体,容易造成小目标物体误检和漏检.为此,本文基于YOLOv5s网络进行改进.首先,用K-means++算法对数据集进行聚类,得到更优的锚框参数;其次,结合SPD-Conv小目标检测模块,降低误检漏检率,以提高车辆检测时的精度;最后,将原网络的检测头模块替换为检测头解耦模块,对分类和回归任务进行解耦,从而进一步提高分类精度.本文采用无人机拍摄图像数据集VisDrone-2019-DET来进行车辆检测,改进之后的网络均值平均检测精度(mAP)达到53.0%,相比于YOLOv5s模型提高了6.3个百分点,能够有效降低小目标误检漏率,从而能更加精准地进行车辆检测.
Abstract
The problem of complex backgrounds and large variations in target scales in vehicle images captured by unmanned aerial vehicle(UAV)makes it difficult for existing neural network models to detect small target objects when performing vehicle detection,which can easily lead to false detection and missed detection of small target objects.To solve this problem,an improv-eed method based on the YOLOv5s neural network is proposed.Firstly,we use the K-means++algorithm to cluster dataset to ob-tain better anchor.Secondly,the SPD-Conv small target detection module is combined to reduce the false detection and miss de-tection rate,so as to improve the accuracy of vehicle detection.Finally,the detection head module is replaced by a decoupled head module to decouple the classification and regression tasks,thus further improve the classification accuracy.The article uses VisDrone-2019-DET dataset for vehicle detection,the mean average precision(mAP)of the improved network in this paper reaches 53.0%,which is 6.3 percentage points higher than the original YOLOv5s model,and can effectively reduce the probabil-ity of false detection and missed detection of small objects,enable more accurate vehicle detection.
关键词
YOLOv5s/小目标/车辆检测/K-means++/SPD-Conv/检测头解耦模块Key words
YOLOv5s/small object/vehicle detection/K-means++/SPD-Conv/decoupled head model引用本文复制引用
基金项目
四川省科技厅省院省校科技合作项目(2022YFSY0056)
人工智能四川省重点实验室开放基金项目(019RYJ07)
出版年
2024
国家科技期刊平台
NSTL
万方数据