| 223 | 3 | 520 |
| 下载次数 | 被引频次 | 阅读次数 |
小流域河道整治中施工废水等会给河道水体带来污染，且工区往往沿长线性河道呈点状分布形态，交通不便，人工巡检难以保证施工水污染管控的时效性。目前通常采用智能巡检手段对水面漂浮物进行图像识别，但对于污水、水华等水污染的识别仍存在困难。针对上述问题提出基于无人机航拍与深度学习的河道施工水污染异常图像智能识别与定位方法。利用无人机巡检采集工区航拍图像，基于SENet注意力机制优化的MBConv模块，建立了施工水污染图像的智能快速识别分类EfficientNet-B0模型，并利用迁移学习方法进行模型训练，可以使模型提取的污染相关特征指向性更强，提升模型的训练速度及精度；同时，基于Grad-CAM(Class Activation Mapping,类激活热力图)方法和全连接条件随机场(Conditional Random Fields, CRF)方法得到的污染区域特征图，可修正错分区域，实现更为精细的污染区域快速标记定位。实例应用表明，水污染图像分类准确率可达98%,追踪标记评价指标ORI值可达96.91%。结果表明：研究成果能够为工程管理人员快速管控长线性河道整治工程的施工水污染提供了先进的技术手段。
Abstract：Construction wastewater of small watersheds regulation projects cause river pollution. As a long-line project, river regulation often shows a scattered distribution, with inconvenient transportation, manual inspection is difficult to guarantee the efficiency of construction water pollution control. At present, intelligent inspection is usually used to identify floating objects, which is difficult to identify water pollution such as sewage and water bloom. This paper proposed an intelligent recognition and positioning method for anomaly images of water pollution in river regulation projects based on UAV aerial photography and deep learning. The aerial images of working area are collected by UAV inspection, and an EfficientNet-B0 model of intelligent identification and classification of construction water pollution image is established based on the MBConv module optimized by the SENet attention mechanism. Transfer learning is used to train the model, which can make the pollution-related features extracted by the model more directional, and improve the training speed and accuracy of the model. Then, the feature map of pollution area based on Grad-CAM(Class Activation Mapping) and fully connected CRF(Conditional Random Fields) can modify the misclassification area that achieve more refined fast marking and positioning of pollution area.The practical application result show that the classification accuracy of water pollution images is 98% and the evaluation index ORI of the positioning method is 96.91%. This study can provide advanced technical means for project managers to quickly control the water pollution of long-line river regulation projects.
[1] 赵宇，杨清伟.基于CNKI的中国河流重金属污染研究进展分析[J].重庆交通大学学报(自然科学版),2020,39(4):104-109.
[2] 张金良，李岩，白玉川，等.黄河下游花园口-高村河段泥沙时空分布及地貌演变[J].水利学报，2021,52(7):759-769.
[3] LIU D,CHEN J,HU D,et al.Dynamic BIM-augmented UAV safety inspection for water diversion project[J].Computers in Industry,2019,108:163-177.
[4] 李宁，王雨萱，徐守坤，等.基于AlexNet的小样本水面漂浮物识别[J].计算机应用与软件，2019,36(2):245-251.
[5] 雷李义，艾矫燕，彭婧，等.基于深度学习的水面漂浮物目标检测评估[J].环境与发展，2019,31(6):117-120.
[6] TOPOUZELIS K,PAPAGEORGIOU D,SUARIA G,et al.Floating marine litter detection algorithms and techniques using optical remote sensing data:A review[J].Marine Pollution Bulletin,2021,170:112675.
[7] JIN X,NIU P,LIU L.A GMM-based segmentation method for the detection of water surface floats[J].IEEE Access,2019,7:119018-119025.
[8] LIN F,HOU T,JIN Q,et al.Improved YOLO based detection algorithm for floating debris in waterway[J].Entropy,2021,23(9):1111.
[9] CHEN J,LIU D.Detecting,extracting and classifying foreign objects in inter-basin channels to ensure water supply safety[J].Journal of Hydroinformatics,2022,24(1):113-127.
[10] TERVEN J,CóRDOVA-ESPARZA D M,ROMERO-GONZáLEZ J A.A comprehensive review of yolo architectures in computer vision:From yolov1 to yolov8 and yolo-nas[J].Machine Learning and Knowledge Extraction,2023,5(4):1680-1716.
[11] FANG B,YU J,CHEN Z,et al.Artificial intelligence for waste management in smart cities:A review[J].Environmental Chemistry Letters,2023,21(4):1959-1989.
[12] 陈诚，李寿千，王新，等.河道安全巡检中的船舶可视化监测方法[J].水利水电科技进展，2020,40(6):66-70.
[13] 高友文，周本君，胡晓飞.基于数据增强的卷积神经网络图像识别研究[J].计算机技术与发展，2018,28(8):62-65.
[14] 陈荣敏，王皓冉，汪双，等.基于无人机的坝面裂纹缺陷智能检测方法[J].水利水电科技进展，2021,41(6):7-12.
[15] 陈智超，焦海宁，杨杰，等.基于改进MobileNet v2的垃圾图像分类算法[J].浙江大学学报(工学版),2021,55(8):1490-1499.
[16] 周天宇，朱启兵，黄敏，等.基于轻量级卷积神经网络的载波芯片缺陷检测[J].计算机工程与应用，2022,58(7):213-219.
[17] ZHUANG F,QI Z,DUAN K,et al.A comprehensive survey on transfer learning[J].Proceedings of the IEEE,2021,109(1):43-76.
[18] RUSSAKOVSKY O,DENG J,SU H,et al.ImageNet large scale visual recognition challenge[J].International Journal of Computer Vision,2015,115(3):211-252.
[19] SELVARAJU R R,COGSWELL M,DAS A,et al.Grad-CAM:Visual explanations from deep networks via Gradient-based localization[J].International Journal of Computer Vision,2020,128(2):336-359.
[20] LIU T,HUANG X,MA J.Conditional random fields for image labeling[J].Mathematical Problems in Engineering,2016,2016:1-15.
[21] KAMNITSAS K,LEDIG C,NEWCOMBE V F J,et al.Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation[J].Medical Image Analysis,2017,36:61-78.
[22] KR?HENBüHL P,KOLTUN V.Efficient inference in fully connected CRFs with Gaussian edge potentials[J].Advances in Neural Information Processing Systems,2011,24:109-117.
[23] FAWCETT T.An introduction to ROC analysis[J].Pattern Recognition Letters,2006,27(8):861-874.
基本信息:
DOI：10.13928/j.cnki.wrahe.2025.S1.012
中图分类号:X52;TV85;TP391.41
引用信息:
[1]侯建刚,马子茹,刘东海,等.基于无人机航拍的河道施工水污染图像智能识别与定位[J].水利水电技术(中英文),2025,56(S1):67-75.DOI:10.13928/j.cnki.wrahe.2025.S1.012.
基金信息:
中国长江三峡集团有限公司企业科研项目(202103551)
2025-03-20
2025-03-20