Pavement Disease Visual Detection by Structure Perception and Feature Attention Network
Balancing detection performance and computational efficiency is critical for sustainable pavement disease detection in energy-constrained scenarios. However, existing visual methods often struggle to adapt to structural transformations and capture critical features of pavement diseases in complex en...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/551 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589251622993920 |
|---|---|
| author | Bin Lv Shuo Zhang Haixia Gong Hongbo Zhang Bin Dong Jianzhu Wang Cong Du Jianqing Wu |
| author_facet | Bin Lv Shuo Zhang Haixia Gong Hongbo Zhang Bin Dong Jianzhu Wang Cong Du Jianqing Wu |
| author_sort | Bin Lv |
| collection | DOAJ |
| description | Balancing detection performance and computational efficiency is critical for sustainable pavement disease detection in energy-constrained scenarios. However, existing visual methods often struggle to adapt to structural transformations and capture critical features of pavement diseases in complex environments, while their computational demands can be resource-intensive. To address these challenges, this paper proposes a structure perception and feature attention network (SPFAN). The network includes a structure perception module that employs the updated deformable convolution technique. This technique enables the model to dynamically adjust and focus on the actual pavement disease regions, improving the accuracy of feature extraction, especially for diseases with irregular shapes and sizes. Additionally, the convolutional block attention module (CBAM) is integrated to optimize feature map attention across channel and spatial dimensions, enhancing the model focus on critical disease features without significantly increasing complexity. To further improve robustness, the generalized intersection over union (GIoU) loss function is adopted, ensuring better stability across targets of varying shapes and sizes. Experimental results on real-world pavement disease images show that the mAP@0.5 of the proposed SPFAN increases from 66.2% to 71.2%, an improvement of 7.55%, while the F1-score also increases by 9.03%, compared to the baseline YOLOv8n model. Furthermore, while achieving significant accuracy improvements, the proposed method maintains a similar parameter count as the baseline, preserving its low computational demands and high efficiency, making it suitable for real-time pavement damage detection in energy-constrained environments. |
| format | Article |
| id | doaj-art-42a1d4d7486d499cba23403a2d2ec057 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-42a1d4d7486d499cba23403a2d2ec0572025-01-24T13:19:47ZengMDPI AGApplied Sciences2076-34172025-01-0115255110.3390/app15020551Pavement Disease Visual Detection by Structure Perception and Feature Attention NetworkBin Lv0Shuo Zhang1Haixia Gong2Hongbo Zhang3Bin Dong4Jianzhu Wang5Cong Du6Jianqing Wu7Jihe Operation Management Center, Qilu Expressway Co., Ltd., Jinan 250002, ChinaSchool of Qilu Transportation, Shandong University, Jinan 250061, ChinaJihe Operation Management Center, Qilu Expressway Co., Ltd., Jinan 250002, ChinaSchool of Qilu Transportation, Shandong University, Jinan 250061, ChinaJihe Operation Management Center, Qilu Expressway Co., Ltd., Jinan 250002, ChinaSchool of Qilu Transportation, Shandong University, Jinan 250061, ChinaSchool of Qilu Transportation, Shandong University, Jinan 250061, ChinaSchool of Qilu Transportation, Shandong University, Jinan 250061, ChinaBalancing detection performance and computational efficiency is critical for sustainable pavement disease detection in energy-constrained scenarios. However, existing visual methods often struggle to adapt to structural transformations and capture critical features of pavement diseases in complex environments, while their computational demands can be resource-intensive. To address these challenges, this paper proposes a structure perception and feature attention network (SPFAN). The network includes a structure perception module that employs the updated deformable convolution technique. This technique enables the model to dynamically adjust and focus on the actual pavement disease regions, improving the accuracy of feature extraction, especially for diseases with irregular shapes and sizes. Additionally, the convolutional block attention module (CBAM) is integrated to optimize feature map attention across channel and spatial dimensions, enhancing the model focus on critical disease features without significantly increasing complexity. To further improve robustness, the generalized intersection over union (GIoU) loss function is adopted, ensuring better stability across targets of varying shapes and sizes. Experimental results on real-world pavement disease images show that the mAP@0.5 of the proposed SPFAN increases from 66.2% to 71.2%, an improvement of 7.55%, while the F1-score also increases by 9.03%, compared to the baseline YOLOv8n model. Furthermore, while achieving significant accuracy improvements, the proposed method maintains a similar parameter count as the baseline, preserving its low computational demands and high efficiency, making it suitable for real-time pavement damage detection in energy-constrained environments.https://www.mdpi.com/2076-3417/15/2/551pavement disease detectionstructure perceptionfeature attentionGIoUYOLO |
| spellingShingle | Bin Lv Shuo Zhang Haixia Gong Hongbo Zhang Bin Dong Jianzhu Wang Cong Du Jianqing Wu Pavement Disease Visual Detection by Structure Perception and Feature Attention Network Applied Sciences pavement disease detection structure perception feature attention GIoU YOLO |
| title | Pavement Disease Visual Detection by Structure Perception and Feature Attention Network |
| title_full | Pavement Disease Visual Detection by Structure Perception and Feature Attention Network |
| title_fullStr | Pavement Disease Visual Detection by Structure Perception and Feature Attention Network |
| title_full_unstemmed | Pavement Disease Visual Detection by Structure Perception and Feature Attention Network |
| title_short | Pavement Disease Visual Detection by Structure Perception and Feature Attention Network |
| title_sort | pavement disease visual detection by structure perception and feature attention network |
| topic | pavement disease detection structure perception feature attention GIoU YOLO |
| url | https://www.mdpi.com/2076-3417/15/2/551 |
| work_keys_str_mv | AT binlv pavementdiseasevisualdetectionbystructureperceptionandfeatureattentionnetwork AT shuozhang pavementdiseasevisualdetectionbystructureperceptionandfeatureattentionnetwork AT haixiagong pavementdiseasevisualdetectionbystructureperceptionandfeatureattentionnetwork AT hongbozhang pavementdiseasevisualdetectionbystructureperceptionandfeatureattentionnetwork AT bindong pavementdiseasevisualdetectionbystructureperceptionandfeatureattentionnetwork AT jianzhuwang pavementdiseasevisualdetectionbystructureperceptionandfeatureattentionnetwork AT congdu pavementdiseasevisualdetectionbystructureperceptionandfeatureattentionnetwork AT jianqingwu pavementdiseasevisualdetectionbystructureperceptionandfeatureattentionnetwork |