基于无人机视觉的河道漂浮垃圾分类检测技术研究  

Study on Classification and Detection Technology of River Floating Garbage Based on UAV Vision

作　　者：李德鑫 闫志刚[1] 孙久运 LI Dexin;YAN Zhigang;SUN Jiuyun(School of Environment Science and Spatial Informatics,China University of Mining and Technology,Xuzhou 221116,China)

机构地区：[1]中国矿业大学环境与测绘学院,江苏徐州221116

出　　处：《金属矿山》2021年第9期199-205,共7页Metal Mine

基　　金：国家自然科学基金项目(编号:41971370)。

摘　　要：传统人工河道漂浮垃圾巡检耗时耗力,无人机、无人船河道巡检成为主要方式,目前尚局限于河道漂浮垃圾图像人工判读或简单计算机目标检测,缺乏对漂浮垃圾的自动分类检测。基于无人机航拍影像构建了研究区河道漂浮垃圾数据集,使用深度学习方法对垃圾进行分类识别。顾及河道漂浮垃圾类别不均衡以及在无人机影像中占比较小等情况,在多尺度检测以及数据增强等方面对YOLOv5s目标检测算法进行了针对性改进,经试验验证,改进后算法相较于原始算法,提升了对小目标的检测精度,其类别均衡准确率提高了3.47%。研究表明:将深度学习方法与无人机技术相结合能够高效、准确地对垃圾进行识别和分类,为治理河道漂浮垃圾提供决策依据。The traditional manual inspection of river floating garbage is time-consuming and labor-consuming. UAVsand unmanned boats have become the main methods of river inspections. At present,it is limited to manual interpretation ofriver floating garbage images or simple computer target detection,and there is a lack of automatic classification and detectionof floating garbage. In this paper,a dataset of floating garbage in the river channel of the study area is constructed based ondrone aerial images,and a deep learning method is used to classify and recognize garbage. Taking into account the unbal-anced types of floating garbage in the river and the relatively small proportion in UAV images,the YOLOv5s target detectionalgorithm has been improved in terms of multi-scale detection and data enhancement. The experimental results show that theimproved algorithm improves the mean average precision by 3.47% compared with the original algorithm. The study resultsshow that the combination of deep learning methods and drone technology can efficiently and accurately identify and classifygarbage,and provide a basis for decision-making in the treatment of floating garbage in the river.

关 键 词：无人机 漂浮垃圾 分类检测 深度学习 小目标 

分 类 号：TD17[矿业工程—矿山地质测量] P234[天文地球—摄影测量与遥感]