Research on Algorithm for Improving Infrared Image Defect Segmentation of Power Equipment
The existing infrared image processing technology mainly relies on the traditional segmentation algorithm, which is not only inefficient, but also has problems such as blurred edges, poor segmentation accuracy, and insufficient extraction of key power equipment features for the infrared image defect...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/7/1588 |
| _version_ | 1797608140545458176 |
|---|---|
| author | Jingwen Zhang Wu Zhu |
| author_facet | Jingwen Zhang Wu Zhu |
| author_sort | Jingwen Zhang |
| collection | DOAJ |
| description | The existing infrared image processing technology mainly relies on the traditional segmentation algorithm, which is not only inefficient, but also has problems such as blurred edges, poor segmentation accuracy, and insufficient extraction of key power equipment features for the infrared image defect segmentation of power equipment. A CS_DeeplabV3+ network for the accurate segmentation of the infrared image defect segmentation of power equipment is designed for the situation of leakage and false detection after segmentation by traditional algorithms. The ASPP module is improved in the encoder part to enable the network to obtain a denser pixel sampling, an improved attention mechanism is introduced to enhance the sensitivity and accuracy of the network for feature extraction, and a semantic segmentation feature enhancement module—the structured feature enhancement module (SFEM)—is introduced in the decoder part to enhance the feature processing to improve the segmentation accuracy. The CS_DeeplabV3+ network is validated using the dataset, and the experimental comparison proves that the improved model has finer contours compared with other models for segmenting infrared images of power equipment defects, and MPA is improved by 5.6% and MIOU is improved by 7.3% compared with the DeeplabV3+ network. |
| first_indexed | 2024-03-11T05:40:23Z |
| format | Article |
| id | doaj.art-fda1cfd3555141aa98ae3019549fe996 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T05:40:23Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-fda1cfd3555141aa98ae3019549fe9962023-11-17T16:32:45ZengMDPI AGElectronics2079-92922023-03-01127158810.3390/electronics12071588Research on Algorithm for Improving Infrared Image Defect Segmentation of Power EquipmentJingwen Zhang0Wu Zhu1Department of Electronics and Information Engineering, Shanghai University of Electric Power, Shanghai 201306, ChinaDepartment of Electronics and Information Engineering, Shanghai University of Electric Power, Shanghai 201306, ChinaThe existing infrared image processing technology mainly relies on the traditional segmentation algorithm, which is not only inefficient, but also has problems such as blurred edges, poor segmentation accuracy, and insufficient extraction of key power equipment features for the infrared image defect segmentation of power equipment. A CS_DeeplabV3+ network for the accurate segmentation of the infrared image defect segmentation of power equipment is designed for the situation of leakage and false detection after segmentation by traditional algorithms. The ASPP module is improved in the encoder part to enable the network to obtain a denser pixel sampling, an improved attention mechanism is introduced to enhance the sensitivity and accuracy of the network for feature extraction, and a semantic segmentation feature enhancement module—the structured feature enhancement module (SFEM)—is introduced in the decoder part to enhance the feature processing to improve the segmentation accuracy. The CS_DeeplabV3+ network is validated using the dataset, and the experimental comparison proves that the improved model has finer contours compared with other models for segmenting infrared images of power equipment defects, and MPA is improved by 5.6% and MIOU is improved by 7.3% compared with the DeeplabV3+ network.https://www.mdpi.com/2079-9292/12/7/1588power equipmentinfrared thermalDeeplabV3+attention mechanismsemantic segmentation feature enhancement |
| spellingShingle | Jingwen Zhang Wu Zhu Research on Algorithm for Improving Infrared Image Defect Segmentation of Power Equipment Electronics power equipment infrared thermal DeeplabV3+ attention mechanism semantic segmentation feature enhancement |
| title | Research on Algorithm for Improving Infrared Image Defect Segmentation of Power Equipment |
| title_full | Research on Algorithm for Improving Infrared Image Defect Segmentation of Power Equipment |
| title_fullStr | Research on Algorithm for Improving Infrared Image Defect Segmentation of Power Equipment |
| title_full_unstemmed | Research on Algorithm for Improving Infrared Image Defect Segmentation of Power Equipment |
| title_short | Research on Algorithm for Improving Infrared Image Defect Segmentation of Power Equipment |
| title_sort | research on algorithm for improving infrared image defect segmentation of power equipment |
| topic | power equipment infrared thermal DeeplabV3+ attention mechanism semantic segmentation feature enhancement |
| url | https://www.mdpi.com/2079-9292/12/7/1588 |
| work_keys_str_mv | AT jingwenzhang researchonalgorithmforimprovinginfraredimagedefectsegmentationofpowerequipment AT wuzhu researchonalgorithmforimprovinginfraredimagedefectsegmentationofpowerequipment |