Quantitative characterization of surface defects on bridge cable based on improved YOLACT++
The safety and reliability of cables are directly linked to the safe operation of bridges as crucial load-bearing components. The accuracy and efficiency of current methods are still insufficient to segment and quantitatively characterize surface defects on cables. This paper proposes a novel and ef...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Case Studies in Construction Materials |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214509524011045 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846171302768934912 |
|---|---|
| author | Hong Zhang Jiangxia He Xiaogang Jiang Yanfeng Gong Tianyu Hu Tengjiao Jiang Jianting Zhou |
| author_facet | Hong Zhang Jiangxia He Xiaogang Jiang Yanfeng Gong Tianyu Hu Tengjiao Jiang Jianting Zhou |
| author_sort | Hong Zhang |
| collection | DOAJ |
| description | The safety and reliability of cables are directly linked to the safe operation of bridges as crucial load-bearing components. The accuracy and efficiency of current methods are still insufficient to segment and quantitatively characterize surface defects on cables. This paper proposes a novel and efficient method for the refined segmentation and quantitative characterization of bridge cable surface defects based on an improved you only look at coefficients++ (YOLACT++) model. For defect segmentation, several enhancements have been made to the YOLACT++ model, including incorporating the convolutional block attention module (CBAM), optimizing the anchor box generation mechanism, and introducing the smoother Mish activation function, which enhances both the accuracy and speed of defect detection. For quantitative characterization, the method adopts surface correction algorithms, pixel statistics, and crack skeleton extraction, resulting in a more accurate representation of defect areas and the length and width of cracks. Compared to the baseline model, the optimized model achieves a 3.58 % improvement in mean average precision (mAP) and an inference speed of 25.74 frames per second (FPS). The results show that the error is within 10 % compared with the manually measured area, which offers a more objective and comprehensive foundation for cable safety assessment. |
| format | Article |
| id | doaj-art-eec4497cdb73495089a13deee152e52d |
| institution | Kabale University |
| issn | 2214-5095 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Case Studies in Construction Materials |
| spelling | doaj-art-eec4497cdb73495089a13deee152e52d2024-11-11T04:25:33ZengElsevierCase Studies in Construction Materials2214-50952024-12-0121e03953Quantitative characterization of surface defects on bridge cable based on improved YOLACT++Hong Zhang0Jiangxia He1Xiaogang Jiang2Yanfeng Gong3Tianyu Hu4Tengjiao Jiang5Jianting Zhou6State Key Laboratory of Mountain Bridge and Tunnel Engineering, Chongqing Jiaotong University, Chongqing 400074, ChinaSchool of Information Science and Engineering, Chongqing Jiaotong University, Chongqing 400074, ChinaSchool of Information Science and Engineering, Chongqing Jiaotong University, Chongqing 400074, ChinaSchool of Shipping and Naval Architecture, Chongqing Jiaotong University, Chongqing 400074, ChinaState Key Laboratory of Mountain Bridge and Tunnel Engineering, Chongqing Jiaotong University, Chongqing 400074, ChinaDepartment of Structural Engineering, Norwegian University of Science and Technology, Rich. Birkelands vei 1A, Trondheim 7491, Norway; Corresponding author.State Key Laboratory of Mountain Bridge and Tunnel Engineering, Chongqing Jiaotong University, Chongqing 400074, ChinaThe safety and reliability of cables are directly linked to the safe operation of bridges as crucial load-bearing components. The accuracy and efficiency of current methods are still insufficient to segment and quantitatively characterize surface defects on cables. This paper proposes a novel and efficient method for the refined segmentation and quantitative characterization of bridge cable surface defects based on an improved you only look at coefficients++ (YOLACT++) model. For defect segmentation, several enhancements have been made to the YOLACT++ model, including incorporating the convolutional block attention module (CBAM), optimizing the anchor box generation mechanism, and introducing the smoother Mish activation function, which enhances both the accuracy and speed of defect detection. For quantitative characterization, the method adopts surface correction algorithms, pixel statistics, and crack skeleton extraction, resulting in a more accurate representation of defect areas and the length and width of cracks. Compared to the baseline model, the optimized model achieves a 3.58 % improvement in mean average precision (mAP) and an inference speed of 25.74 frames per second (FPS). The results show that the error is within 10 % compared with the manually measured area, which offers a more objective and comprehensive foundation for cable safety assessment.http://www.sciencedirect.com/science/article/pii/S2214509524011045CablesDefect segmentationDefect quantitative characterizationYOLACT++Cylindrical surface correction |
| spellingShingle | Hong Zhang Jiangxia He Xiaogang Jiang Yanfeng Gong Tianyu Hu Tengjiao Jiang Jianting Zhou Quantitative characterization of surface defects on bridge cable based on improved YOLACT++ Case Studies in Construction Materials Cables Defect segmentation Defect quantitative characterization YOLACT++ Cylindrical surface correction |
| title | Quantitative characterization of surface defects on bridge cable based on improved YOLACT++ |
| title_full | Quantitative characterization of surface defects on bridge cable based on improved YOLACT++ |
| title_fullStr | Quantitative characterization of surface defects on bridge cable based on improved YOLACT++ |
| title_full_unstemmed | Quantitative characterization of surface defects on bridge cable based on improved YOLACT++ |
| title_short | Quantitative characterization of surface defects on bridge cable based on improved YOLACT++ |
| title_sort | quantitative characterization of surface defects on bridge cable based on improved yolact |
| topic | Cables Defect segmentation Defect quantitative characterization YOLACT++ Cylindrical surface correction |
| url | http://www.sciencedirect.com/science/article/pii/S2214509524011045 |
| work_keys_str_mv | AT hongzhang quantitativecharacterizationofsurfacedefectsonbridgecablebasedonimprovedyolact AT jiangxiahe quantitativecharacterizationofsurfacedefectsonbridgecablebasedonimprovedyolact AT xiaogangjiang quantitativecharacterizationofsurfacedefectsonbridgecablebasedonimprovedyolact AT yanfenggong quantitativecharacterizationofsurfacedefectsonbridgecablebasedonimprovedyolact AT tianyuhu quantitativecharacterizationofsurfacedefectsonbridgecablebasedonimprovedyolact AT tengjiaojiang quantitativecharacterizationofsurfacedefectsonbridgecablebasedonimprovedyolact AT jiantingzhou quantitativecharacterizationofsurfacedefectsonbridgecablebasedonimprovedyolact |