采用雷视融合方法的灌溉风险区异物入侵风险预警

doi:10.6040/j.issn.1672-3961.0.2023.092

摘要/Abstract

摘要： 针对传统灌溉渠异物入侵监测方法检测精度低、时效性差、夜间巡检不全面、危险性高等问题,提出一种基于雷视融合的灌溉区异物入侵监测方法。针对灌溉区周边行人、动物等小目标误检及特征提取能力不足等问题,提出一种基于YOLOv5改进的小目标识别算法,提高对灌溉区周边小目标检测能力。通过实际场景测试试验,本研究提出的灌溉区雷视融合监测方法和改进的基于YOLOv5的小目标识别算法,识别精确度达到93.26%,监测范围是设备周围360°,有效提升了不同时间段下的异物入侵监测能力,验证了该方法的准确性。

关键词: 激光雷达, 摄像机, 融合, 灌溉区目标检测, 小目标检测

中图分类号:

U414

陈晓燕,王川,齐明杰,张宁,林晓龙,霍延强,刘世杰,田源. 采用雷视融合方法的灌溉风险区异物入侵风险预警[J]. 山东大学学报 (工学版), 2024, 54(3): 115-121.

CHEN Xiaoyan, WANG Chuan, QI Mingjie, ZHANG Ning, LIN Xiaolong, HUO Yanqiang, LIU Shijie, TIAN Yuan. Early warning of foreign object intrusion risk in irrigation risk areas using the mine-view fusion method[J]. Journal of Shandong University(Engineering Science), 2024, 54(3): 115-121.

参考文献

[1] 朱梦瑞, 牛宏侠. 改进YOLOv3模型的铁路异物入侵识别算法[J]. 北京交通大学学报, 2022, 46(2): 37-45. ZHU Mengrui, NIU Hongxia. Improved YOLOv3 model for railway foreign body intrusion recognition algorithm[J]. Journal of Beijing Jiaotong University, 2022, 46(2): 37-45.
[2] 张楠. 基于视频的铁路异物入侵检测技术研究[D].杭州: 浙江大学, 2022. ZHANG Nan. Research on railway foreign object intrusion detection technology based on video[D]. Hangzhou: Zhejiang University, 2022.
[3] 何自芬, 陈光晨, 王森, 等. 融合自注意力特征嵌入的夜间机场跑道异物入侵检测[J]. 光学精密工程, 2022, 30(13): 1591-1605. HE Zifen, CHEN Guangchen, WANG Sen, et al. Detection of foreign object debris on night airport runway fusion with self-attentional feature embedding[J]. Optics and Precision Engineering, 2022, 30(13): 1591-1605.
[4] 肖曾翔, 徐启峰. 基于改进卷积神经网络的变电站异物入侵识别[J]. 科学技术与工程, 2022, 22(4): 1465-1471. XIAO Zengxiang, XU Qifeng. Cognition of foreign objects intrusion in substation based on improved convolutional neural network[J]. Science Technology and Engineering, 2022, 22(4): 1465-1471.
[5] 杨剑锋, 秦钟, 庞小龙, 等. 基于深度学习网络的输电线路异物入侵监测和识别方法[J]. 电力系统保护与控制, 2021, 49(4): 37-44. YANG Jianfeng, QIN Zhong, PANG Xiaolong, et al. Foreign body intrusion monitoring and recognition method based on Dense-YOLOv3 deep learning network[J]. Power System Protection and Control, 2021, 49(4): 37-44.
[6] 谢谨. 基于射频感知的轨道异物入侵检测方法研究[D]. 长沙: 长沙理工大学, 2021. XIE Jin. Research on instrusion detection method of railway foreign objects based on radio frequency sensing[D]. Changsha: Changsha University of Science & Technology, 2021.
[7] 曾金, 刘清鸿, 丁梓楠, 等. 基于激光雷达的变电站空域异物入侵检测策略与系统设计[J]. 科技视界, 2020(3): 21-23. ZENG Jin, LIU Qinghong, DING Zinan, et al. Foreign body intrusion detection strategy and system design of substation airspace based on LiDAR[J]. Science & Technology Vision, 2020(3): 21-23.
[8] 曹长飞. 视觉与雷达融合落物监测系统研究[D]. 南京:南京理工大学, 2021. CAO Changfei. Research on visual and radar fusion monitoring system for falling objects[D]. Nanjing: Nanjing University of Science & Technology, 2021.
[9] 尹成斐, 刘尚昆, 张世红, 等. 轨道作业车周边异物侵线监测技术[J]. 铁道建筑, 2022, 30(13): 46-48. YIN Chengfei, LIU Shangkun, ZHANG Shihong, et al. Monitoring technology of foreign matter intrusion around rail operation vehicle[J]. Railway Engineering, 2022, 30(13): 46-48.
[10] 陈锴迪. 隧道线路异物检测系统研究[D]. 北京:北京交通大学, 2020. CHEN Kaidi. Research on foreign body detection system of tunnel line[D]. Beijing: Beijing Jiaotong Univer-sity, 2020.
[11] 梅天灿,左治江,王刚,等. 危险边坡智能监测及预报警综合系统的构建[J]. 江汉大学学报(自然科学版), 2020, 48(2): 86-96. MEI Tiancan, ZUO Zhijiang, WANG Gang, et al. Construction of intelligent monitoring and warning system for dangerous slope[J]. Journal of Jianghan University(Natural Science Edition), 2020, 48(2): 86-96.
[12] WANG Linfeng, WAN Heng, TANG Xuliang, et al. Recurrent attention convolutional neural network optimise track foreign body detection[J]. IET Communications, 2023, 17(1): 1-11.
[13] YE T, ZHANG J, ZHAO Z, et al. Foreign body detection in rail transit based on a multi-mode feature-enhanced convolutional neural network[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(10): 18051-18063.
[14] 李慧鹏, 黄道春, 邓永清, 等. 无人机巡检变电设备研究进展与展望[J]. 湖南电力, 2022, 42(6): 32-39. LI Huipeng, HUANG Daochun, DENG Yongqing, et al. Research process and prospect of UAV inspection of substation equipment[J]. Hunan Electric Power, 2022, 42(6): 32-39.
[15] 周可慧, 肖剑, 张可人, 等. 变压器套管运行状态自动检测技术现状分析[J]. 湖南电力, 2020,40(6): 40-44. ZHOU Kehui, XIAO Jian, ZHANG Keren, et al. Analysis on current situation of operating status automatic detection technology for transformer bushing[J]. Hunan Electric Power, 2020, 40(6): 40-44.
[16] 张家盛, 梁进兴. 基于深度学习的无人机巡检架空输电线路金具锈蚀缺陷检测方法[J]. 湖南电力, 2022, 42(5): 75-78. ZHANG Jiasheng, LIANG Jinxing. Detection method of metal fitting rust defects for overhead transmission lines based on UAV patrol of deep learning[J]. Hunan Electric Power, 2022, 42(5): 75-78.
[17] 陈富荣, 肖明明. 基于YOLOv5的改进小目标监测算法研究[J]. 现代信息科技, 2023, 7(3):55-60. CHEN Furong, XIAO Mingming. Research on improved algorithm of small target detection based on YOLOv5[J]. Modern Information Technology, 2023, 7(3):55-60.
[18] 王祥雪, 王全. 基于多模态信息融合的铁路异物侵限预警系统设计[J]. 电子技术, 2022, 51(12):344-345. WANG Xiangxue, WANG Quan. Design of railway foreign object intrusion warning system based on multi-mode information fusion[J]. Electronic Technique, 2022, 51(12): 344-345.
[19] 郭磊, 王邱龙, 薛伟, 等. 基于改进YOLOv5的小目标检测算法[J]. 电子科技大学学报, 2022, 51(2): 251-258. GUO Lei, WANG Qiulong, XUE Wei, et al. A small object detection algorithm based on improved YOLOv5[J]. Journal of University of Electronic Science and Technology of China, 2022, 51(2): 251-258.
[20] 王术剑, 阎宗尧, 刘世杰, 等. 路侧激光雷达与摄像机时间和空间同步方法[J]. 山东大学学报(工学版), 2022, 52(6):56-62. WANG Shujian, YAN Zongyao, LIU Shijie, et al. Method for time and space synchronization between roadside LiDAR and camera[J]. Journal of Shandong University(Engineering Science), 2022, 52(6): 56-62.
[21] 董方新, 蔡军, 解杨敏. 立体视觉和三维激光系统的联合标定方法[J]. 仪器仪表学报, 2017, 38(10): 2589-2596. DONG Fangxin, CAI Jun, XIE Yangmin. Joint calibration method for stereo vision system and 3D laser system[J]. Journal of Instruments and Meters, 2017, 38(10): 2589-2596.
[22] 魏克全, 时兆峰, 李晗,等. 单目摄像机与三维激光雷达联合标定的研究[J]. 导航定位与授时, 2015, 2(6):69-74. WEI Kequan, SHI Zhaofeng, LI Han, et al. Research on the joint calibration of monocular camera and 3D LiDAR[J]. Navigation Positioning and Timing, 2015, 2(6): 69-74.
[23] LANG A H, VORA S, CARSAR H, et al. Pointpillars: fast encoders for object detection from point clouds[C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE Computer Society, 2019: 12697-12705.

相关文章 15

[1]	聂秀山,巩蕊,董飞,郭杰,马玉玲. 短视频场景分类方法综述[J]. 山东大学学报 (工学版), 2024, 54(3): 1-11.
[2]	索大翔,李波. 基于Gromov-Wasserstein最优传输的输电线路小目标检测方法[J]. 山东大学学报 (工学版), 2024, 54(3): 22-29.
[3]	陈晓燕,齐明杰,程之恒,张昱,庄绪彩,陈亮,田源. 基于岸基激光雷达的水位智能监测技术[J]. 山东大学学报 (工学版), 2024, 54(2): 90-95.
[4]	杨巨成, 魏峰, 林亮, 贾庆祥, 刘建征. 驾驶员疲劳驾驶检测研究综述[J]. 山东大学学报 (工学版), 2024, 54(2): 1-12.
[5]	李明键,李卫军,王海荣. 融合词汇信息与GlobalPointer的实体识别[J]. 山东大学学报 (工学版), 2024, 54(1): 91-99.
[6]	迟云浩,杨璐,郭杰,郝凡昌,聂秀山. 基于注意力特征融合网络的手指静脉图像质量评价方法[J]. 山东大学学报 (工学版), 2023, 53(6): 56-62.
[7]	唐洋,肖枭,关绵涛,倪申童,雷波,杨鑫. 多源信号融合往复式压缩机故障诊断方法[J]. 山东大学学报 (工学版), 2023, 53(5): 10-19.
[8]	李颖,王建坤. 基于监督图正则化和信息融合的轻度认知障碍分类方法[J]. 山东大学学报 (工学版), 2023, 53(4): 65-73.
[9]	周勇,兰晓伟,吕斌,栗剑. 基于路侧激光雷达的雪天点云降噪算法[J]. 山东大学学报 (工学版), 2023, 53(4): 30-36.
[10]	于畅,伍星,邓秋菊. 基于深度学习的多视角螺钉缺失智能检测算法[J]. 山东大学学报 (工学版), 2023, 53(4): 104-112.
[11]	刘行,杨璐,郝凡昌. 基于多特征融合的手指静脉图像检索方法[J]. 山东大学学报 (工学版), 2023, 53(2): 118-126.
[12]	宋佳芮,陈艳平,王凯,黄瑞章,秦永彬. 基于Affix-Attention的命名实体识别语义补充方法[J]. 山东大学学报 (工学版), 2023, 53(2): 70-76.
[13]	周勇,吕琛,侯福金,郭鑫铭,宋修广. 基于坐标转换的多路侧激光雷达数据配准方法[J]. 山东大学学报 (工学版), 2022, 52(6): 41-49.
[14]	王术剑,阎宗尧,刘世杰,田源. 路侧激光雷达与摄像机时间和空间同步方法[J]. 山东大学学报 (工学版), 2022, 52(6): 56-62.
[15]	沈鑫杰,黄嘉爽,丁卫平,孙颖,王海鹏,鞠恒荣. 基于双通路卷积融合网络的脑龄分布预测[J]. 山东大学学报 (工学版), 2022, 52(6): 131-138.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed