[1]顾晨亮,杨恒,刘友波,等.基于自适应局部斥力与归一化面积损失的工程车辆目标检测*[J].中国安全生产科学技术,2021,17(11):40-47.[doi:10.11731/j.issn.1673-193x.2021.11.006]
GU Chenliang,YANG Heng,LIU Youbo,et al.Object detection of engineering vehicles based on self-adaptive local exclusion loss and normalized area loss[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(11):40-47.[doi:10.11731/j.issn.1673-193x.2021.11.006]
点击复制
基于自适应局部斥力与归一化面积损失的工程车辆目标检测*
GU Chenliang,YANG Heng,LIU Youbo,et al.Object detection of engineering vehicles based on self-adaptive local exclusion loss and normalized area loss[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(11):40-47.[doi:10.11731/j.issn.1673-193x.2021.11.006]
《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]
- 卷:
- 17
- 期数:
- 2021年11期
- 页码:
- 40-47
- 栏目:
- 学术论著
- 出版日期:
- 2021-11-30
文章信息/Info
- Title:
- Object detection of engineering vehicles based on self-adaptive local exclusion loss and normalized area loss
- 文章编号:
- 1673-193X(2021)-11-0040-08
- Keywords:
- engineering vehicle; construction supervision; object detection; self-adaptive local exclusion; normalized area loss
- 分类号:
- X947
- 文献标志码:
- A
- 摘要:
- 为加强施工场景下的工程车辆安全监管，针对施工场景下工程车辆易互相遮挡、局部特征与全局特征相似以及场景环境复杂的问题，提出一种基于自适应局部斥力与归一化面积损失的工程车辆目标检测算法。其中自适应局部斥力损失可使待检测工程车辆与其他工程车辆目标框相排斥；归一化面积损失使网络学习集中在面积具有相对较大预测误差的工程车辆上；并结合聚类算法设定更适合工程车辆的锚框。研究结果表明：算法可实现在困难场景下对压路机、挖掘机、装载机3类工程车辆的快速准确检测与识别，具有较高的工程应用价值。
- Abstract:
- In order to strengthen the safety supervision of engineering vehicles under the construction scene,aiming at the problems that the engineering vehicles are easy to obscure each other,the local features are similar to the global features,and the scene environment is complex under the construction scene,an object detection algorithm of engineering vehicles base on the self-adaptive local exclusion loss and normalized area loss was proposed.The self-adaptive local exclusion loss could make the target box of engineering vehicle to be detected to repel with those of other engineering vehicles.The normalized area loss could make the network learning focus on the engineering vehicles with relatively large prediction error of area.Combined with the clustering algorithm,the anchor box being more suitable for the engineering vehicles was set.The results showed that the algorithm could realize the rapid and accurate detection and identification of three types of engineering vehicles,namely road roller,excavator and loader in difficult scenarios,and it has high engineering application value.
参考文献/References:
［1］徐友全，贾美珊.物联网在智慧工地安全管控中的应用［J］.建筑经济,2019,40(12):101-106.
XU Youquan,JIA Meishan.The application of internet of things in the safety management of smart sites［J］.Construction Economy,2019,40(12):101-106.
［2］武金婷，赵晓光，袁德才.无人机巡检输电走廊施工车辆识别方法研究［J］.控制工程,2019,26(2):246-250.
WU Jinting,ZHAO Xiaoguang,YUAN Decai.Detection of construction vehicles under the transmission corridor in UAV inspection［J］.Control Engineering of China,2019,26(2):246-250.
［3］张全发，蒲宝明，李天然，等.基于HOG特征和机器学习的工程车辆检测［J］.计算机系统应用,2013(7):104-107.
ZHANG Quanfa,PU Baoming,LI Tianran,et al.Vehicles detection based on histograms of oriented gradients and machine Learning［J］.Computer Systems & Applications,2013(7):104-107.
［4］邵宇，张全发，蒲宝明.智能监控中的工程车辆识别算法［J］.小型微型计算机系统,2013,34(4):864-867.
SHAO Yu,ZHANG Quanfa,PU Baoming.Vehicle detection algorithm used in intelligent surveillance ［J］.Journal of Chinese Computer Systems,2013,34(4):864-867.
［5］毛亮，薛月菊，林焕凯，等.一种基于视频图像的挖掘机工作状态识别方法［J］.系统工程理论与实践,2019,39(3):797-804.
MAO Liang,XUE Yueju,LIN Huankai,et al.A recognition method of working state of excavator based on video image［J］.Systems Engineering Theory & Practice,2019,39(3):797-804.
［6］王世凯.特定目标识别技术在工业无人机应用上的研究［D］.长春:长春理工大学,2019.
［7］REN S,HE K,GIRSHICK R,et al.Faster R-CNN:To-wards real-time object detection with region proposal networks ［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
［8］李千登,王廷春,崔靖文,等.基于深度学习算法的叉车危险操作行为检测［J］.中国安全生产科学技术,2020,16(5):155-159.
LI Qiandeng,WANG Tingchun,CUI Jingwen,et al.Detection on dangerous operation behavior of forklift based on deep learning algorithm ［J］.Journal of Safety Science and Technology,2020,16(5):155-159.
［9］冯小雨，梅卫，胡大帅.基于改进Faster R-CNN的空中目标检测［J］.光学学报,2018,38(6):250-258.
FENG Xiaoyu,MEI Wei,HU Dashuai.Aerial target detection based on improved Faster R-CNN［J］.Acta Optica Sini-ca,2018,38(6):250-258.
［10］马永杰,马芸婷,程时升,等.基于改进YOLO v3模型与Deep-SORT算法的道路车辆检测方法［J］.交通运输工程学报,2021,21(2):222-231.
MA Yongjie,MA Yunting,CHENG Shisheng,et al.Road vehicle detection method based on improved YOLO v3 model and deep-SORT algorithm［J］.Journal of Traffic and Transportation Engineering,2021,21(2):222-231.
［11］孔烜,张杰,邓露,等.基于机器视觉的车辆检测与参数识别研究进展［J］.中国公路学报,2021,34(4):13-30.
KONG Xuan,ZHANG Jie,DENG Lu,et al.Research advances on vehicle parameter identification based on machine vision［J］.China Journal of Highway and Transport,2021,34(4):13-30.
［12］龙劲峄,周骅.基于AlexNet神经网络的户外车位实时检测［J］.中国科技论文,2021,16(3):295-300.
LONG Jinyi,ZHOU Hua.Real-time detection of outdoor parking space based on AlexNet neural network［J］.China Sciencepaper,2021,16(3):295-300.
［13］WANG X,XIAO T,JIANG Y,et al.Repulsion loss:Detecting pedestrians in a crowd［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:7774-7783.
［14］REDMON J，FARHADI A.YOLOv3:an incremental improvement［R］.Ithaca:Cornell University，2018.
［15］LIU W,ANGUELOV D,ERHAN D,et al.Ssd:Single shot multibox detector［C］// Proceedings of the European conference on computer vision.2016:21-37.
［16］LAW H,DENG J.Cornernet:Detecting objects as paired keypoints［C］//Proceedings of the European conference on computer vision.2018:734-750.
［17］TIAN Z,SHEN C,CHEN H,et al.Fcos:Fully convolutional one-stage object detection［C］//Proceedings of the IEEE International Conference on Computer Vision.2019:9627-9636.
［18］HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition［C］//Proceedings of the IEEE conference on computer vision and pattern recognition.2016:770-778.
［19］HARTIGAN J A,WONG M A.A K-means clustering algorithm［J］.Journal of the Royal Statistical Society:Series C (Applied Statistics),1979,28(1):100-108.
［20］EVERINGHAM M,VAN GOOL L,WILLIAMS C,et al.The pascal visual object classes (VOC) challenge［J］.International Journal of Computer Vision.2010,88:303-338.
相似文献/References:
备注/Memo
- 备注/Memo:
-
收稿日期： 2021-05-19
* 基金项目： 国家自然科学基金项目(51977133)；国网四川省电力公司科技项目(52191918003L)
作者简介： 顾晨亮，硕士研究生，主要研究方向为人工智能与图像处理。
通信作者： 何凌，博士，副教授，主要研究方向为图像处理与语音信号处理。
