Environment Understanding Algorithm for Substation Inspection Robot Based on Improved DeepLab V3+
Compared with traditional manual inspection, inspection robots can not only meet the all-weather, real-time, and accurate inspection needs of substation inspection, they also reduce the work intensity of operation and maintenance personnel and decrease the probability of safety accidents. For the ur...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/8/10/257 |
| _version_ | 1797472449656258560 |
|---|---|
| author | Ping Wang Chuanxue Li Qiang Yang Lin Fu Fan Yu Lixiao Min Dequan Guo Xinming Li |
| author_facet | Ping Wang Chuanxue Li Qiang Yang Lin Fu Fan Yu Lixiao Min Dequan Guo Xinming Li |
| author_sort | Ping Wang |
| collection | DOAJ |
| description | Compared with traditional manual inspection, inspection robots can not only meet the all-weather, real-time, and accurate inspection needs of substation inspection, they also reduce the work intensity of operation and maintenance personnel and decrease the probability of safety accidents. For the urgent demand of substation inspection robot intelligence enhancement, an environment understanding algorithm is proposed in this paper, which is an improved DeepLab V3+ neural network. The improved neural network replaces the original dilate rate combination in the ASPP (atrous spatial pyramid pooling) module with a new dilate rate combination with better segmentation accuracy of object edges and adds a CBAM (convolutional block attention module) in the two up-samplings, respectively. In order to be transplanted to the embedded platform with limited computing resources, the improved neural network is compressed. Multiple sets of comparative experiments on the standard dataset PASCAL VOC 2012 and the substation dataset have been made. Experimental results show that, compared with the DeepLab V3+, the improved DeepLab V3+ has a mean intersection-over-union (mIoU) of eight categories of 57.65% on the substation dataset, with an improvement of 6.39%, and the model size of 13.9 M, with a decrease of 147.1 M. |
| first_indexed | 2024-03-09T20:01:54Z |
| format | Article |
| id | doaj.art-6736f89bacd54cb2831eab601033d74a |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-09T20:01:54Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-6736f89bacd54cb2831eab601033d74a2023-11-24T00:41:29ZengMDPI AGJournal of Imaging2313-433X2022-09-0181025710.3390/jimaging8100257Environment Understanding Algorithm for Substation Inspection Robot Based on Improved DeepLab V3+Ping Wang0Chuanxue Li1Qiang Yang2Lin Fu3Fan Yu4Lixiao Min5Dequan Guo6Xinming Li7School of Network & Communication Engineering, Chengdu Technological University, Chengdu 610031, ChinaSchool of Network & Communication Engineering, Chengdu Technological University, Chengdu 610031, ChinaSchool of Automation, Chengdu University of Information Technology, Chengdu 610225, ChinaSchool of Network & Communication Engineering, Chengdu Technological University, Chengdu 610031, ChinaSchool of Computer & Network Security (Oxford Brooke College), Chengdu University of Technology, Chengdu 610059, ChinaSchool of Automation, Chengdu University of Information Technology, Chengdu 610225, ChinaSchool of Automation, Chengdu University of Information Technology, Chengdu 610225, ChinaSchool of Automation, Chengdu University of Information Technology, Chengdu 610225, ChinaCompared with traditional manual inspection, inspection robots can not only meet the all-weather, real-time, and accurate inspection needs of substation inspection, they also reduce the work intensity of operation and maintenance personnel and decrease the probability of safety accidents. For the urgent demand of substation inspection robot intelligence enhancement, an environment understanding algorithm is proposed in this paper, which is an improved DeepLab V3+ neural network. The improved neural network replaces the original dilate rate combination in the ASPP (atrous spatial pyramid pooling) module with a new dilate rate combination with better segmentation accuracy of object edges and adds a CBAM (convolutional block attention module) in the two up-samplings, respectively. In order to be transplanted to the embedded platform with limited computing resources, the improved neural network is compressed. Multiple sets of comparative experiments on the standard dataset PASCAL VOC 2012 and the substation dataset have been made. Experimental results show that, compared with the DeepLab V3+, the improved DeepLab V3+ has a mean intersection-over-union (mIoU) of eight categories of 57.65% on the substation dataset, with an improvement of 6.39%, and the model size of 13.9 M, with a decrease of 147.1 M.https://www.mdpi.com/2313-433X/8/10/257environment understanding algorithmsubstation inspection robotDeepLab V3+ASPPCBAM |
| spellingShingle | Ping Wang Chuanxue Li Qiang Yang Lin Fu Fan Yu Lixiao Min Dequan Guo Xinming Li Environment Understanding Algorithm for Substation Inspection Robot Based on Improved DeepLab V3+ Journal of Imaging environment understanding algorithm substation inspection robot DeepLab V3+ ASPP CBAM |
| title | Environment Understanding Algorithm for Substation Inspection Robot Based on Improved DeepLab V3+ |
| title_full | Environment Understanding Algorithm for Substation Inspection Robot Based on Improved DeepLab V3+ |
| title_fullStr | Environment Understanding Algorithm for Substation Inspection Robot Based on Improved DeepLab V3+ |
| title_full_unstemmed | Environment Understanding Algorithm for Substation Inspection Robot Based on Improved DeepLab V3+ |
| title_short | Environment Understanding Algorithm for Substation Inspection Robot Based on Improved DeepLab V3+ |
| title_sort | environment understanding algorithm for substation inspection robot based on improved deeplab v3 |
| topic | environment understanding algorithm substation inspection robot DeepLab V3+ ASPP CBAM |
| url | https://www.mdpi.com/2313-433X/8/10/257 |
| work_keys_str_mv | AT pingwang environmentunderstandingalgorithmforsubstationinspectionrobotbasedonimproveddeeplabv3 AT chuanxueli environmentunderstandingalgorithmforsubstationinspectionrobotbasedonimproveddeeplabv3 AT qiangyang environmentunderstandingalgorithmforsubstationinspectionrobotbasedonimproveddeeplabv3 AT linfu environmentunderstandingalgorithmforsubstationinspectionrobotbasedonimproveddeeplabv3 AT fanyu environmentunderstandingalgorithmforsubstationinspectionrobotbasedonimproveddeeplabv3 AT lixiaomin environmentunderstandingalgorithmforsubstationinspectionrobotbasedonimproveddeeplabv3 AT dequanguo environmentunderstandingalgorithmforsubstationinspectionrobotbasedonimproveddeeplabv3 AT xinmingli environmentunderstandingalgorithmforsubstationinspectionrobotbasedonimproveddeeplabv3 |