Missing recognition of highway shading board based on deep convolution segmentation and correction | |
Dong, Yuanshuai3,4,5; Zhang, Yanhong3,4,5; Hou, Yun3,4,5; Tong, Xinlong3,4,5; Wu, Qingquan2; Zhou, Zuofeng1; Cao, Yuxuan3,4,5 | |
2022 | |
会议日期 | 2022-04-14 |
会议地点 | Dalian, China |
关键词 | object detection image segmentation two-dimensional convex hull deep convolution network projection mapping |
DOI | 10.1109/IPEC54454.2022.9777346 |
页码 | 1455-1460 |
英文摘要 | The lack of highway shading panels poses a major hidden danger to driving safety. It is urgent to study a method that can automatically detect the disease of the anti-glare panel and provide help for the maintenance of traffic safety auxiliary facilities. In the method for identifying the absence of shading panels on highways based on deep convolutional image segmentation and correction, the PointRend model based on deep convolutional networks (CNN) is first used to achieve the pixel-level fine segmentation of the shading plate area, and then the multiple images in the same image are segmented. A shading plate area, on the largest outer polygon estimated by the convex hull algorithm, the optimal outer quadrilateral is determined according to the distance between the vertices, and then the shading plate area correction is completed by affine transformation, and finally through the image one-dimensional projection mapping and adjacent shading The distance correlation between the boards realizes the identification and positioning of the missing light-shielding board. The highway shading plate missing recognition method based on deep convolution image segmentation and correction uses the vertex distance to quickly determine the external quadrilateral, which is suitable for estimating the shape of the area in a dynamic scene. After actual testing and verification, it can accurately and efficiently identify the disease of the anti-glare plate. Compared with traditional image segmentation methods, the method using the PointRend target segmentation model has better segmentation quality for target details, and it is more robust when dealing with background interference. © 2022 IEEE. |
产权排序 | 5 |
会议录 | 2022 IEEE Asia-Pacific Conference on Image Processing, Electronics and Computers, IPEC 2022 |
会议录出版者 | Institute of Electrical and Electronics Engineers Inc. |
语种 | 英语 |
ISBN号 | 9781665409025 |
内容类型 | 会议论文 |
源URL | [http://ir.opt.ac.cn/handle/181661/96022] |
专题 | 产业发展处 |
通讯作者 | Tong, Xinlong |
作者单位 | 1.Cas Industrial Development Co., Ltd, Xi'an Institute of Optics and Precision Mechanics, Xi'an; 710000, China 2.Key & Core Technology Innovation Institute of the Greater Bay Area, Guangzhou; 510530, China; 3.R. and D. Ctr. of Transp. Indust. of Technol., Mat. and Equip. of Hwy. Construction and Maintenance, Beijing; 100089, China; 4.China Communications Construction Company Ltd, Research and Development Center on Highway Pavement Maintenance Technology, Beijing; 100089, China; 5.China Highway Engineering Consulting Group Company Ltd, Beijing; 100089, China; |
推荐引用方式 GB/T 7714 | Dong, Yuanshuai,Zhang, Yanhong,Hou, Yun,et al. Missing recognition of highway shading board based on deep convolution segmentation and correction[C]. 见:. Dalian, China. 2022-04-14. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论