Multi-Scale Feature Fusion Model for Bridge Appearance Defect Detection
Although the Faster Region-based Convolutional Neural Network (Faster R-CNN) model has obvious advantages in defect recognition, it still cannot overcome challenging problems, such as time-consuming, small targets, irregular shapes, and strong noise interference in bridge defect detection. To deal w...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2024-03-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2022.9020048 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832545274389594112 |
|---|---|
| author | Rong Pang Yan Yang Aiguo Huang Yan Liu Peng Zhang Guangwu Tang |
| author_facet | Rong Pang Yan Yang Aiguo Huang Yan Liu Peng Zhang Guangwu Tang |
| author_sort | Rong Pang |
| collection | DOAJ |
| description | Although the Faster Region-based Convolutional Neural Network (Faster R-CNN) model has obvious advantages in defect recognition, it still cannot overcome challenging problems, such as time-consuming, small targets, irregular shapes, and strong noise interference in bridge defect detection. To deal with these issues, this paper proposes a novel Multi-scale Feature Fusion (MFF) model for bridge appearance disease detection. First, the Faster R-CNN model adopts Region Of Interest (ROI) pooling, which omits the edge information of the target area, resulting in some missed detections and inaccuracies in both detecting and localizing bridge defects. Therefore, this paper proposes an MFF based on regional feature Aggregation (MFF-A), which reduces the missed detection rate of bridge defect detection and improves the positioning accuracy of the target area. Second, the Faster R-CNN model is insensitive to small targets, irregular shapes, and strong noises in bridge defect detection, which results in a long training time and low recognition accuracy. Accordingly, a novel Lightweight MFF (namely MFF-L）model for bridge appearance defect detection using a lightweight network EfficientNetV2 and a feature pyramid network is proposed, which fuses multi-scale features to shorten the training speed and improve recognition accuracy. Finally, the effectiveness of the proposed method is evaluated on the bridge disease dataset and public computational fluid dynamic dataset. |
| format | Article |
| id | doaj-art-f48274e86c594082bb8cc501d6d41205 |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2024-03-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-f48274e86c594082bb8cc501d6d412052025-02-03T07:26:26ZengTsinghua University PressBig Data Mining and Analytics2096-06542024-03-017111110.26599/BDMA.2022.9020048Multi-Scale Feature Fusion Model for Bridge Appearance Defect DetectionRong Pang0Yan Yang1Aiguo Huang2Yan Liu3Peng Zhang4Guangwu Tang5School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, China, and with China Merchants Chongqing Road Engineering Inspection Center Co., Ltd., Chongqing 400067, China, and also with State Key Laboratory of Bridge Engineering Structural Dynamics, Chongqing 400067, ChinaSchool of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, ChinaSchool of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, ChinaSchool of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, ChinaChina Merchants Chongqing Road Engineering Inspection Center Co., Ltd., Chongqing 400067, China, and with State Key Laboratory of Bridge Engineering Structural Dynamics, Chongqing 400067, ChinaState Key Laboratory of Bridge Engineering Structural Dynamics, Chongqing 400067, ChinaAlthough the Faster Region-based Convolutional Neural Network (Faster R-CNN) model has obvious advantages in defect recognition, it still cannot overcome challenging problems, such as time-consuming, small targets, irregular shapes, and strong noise interference in bridge defect detection. To deal with these issues, this paper proposes a novel Multi-scale Feature Fusion (MFF) model for bridge appearance disease detection. First, the Faster R-CNN model adopts Region Of Interest (ROI) pooling, which omits the edge information of the target area, resulting in some missed detections and inaccuracies in both detecting and localizing bridge defects. Therefore, this paper proposes an MFF based on regional feature Aggregation (MFF-A), which reduces the missed detection rate of bridge defect detection and improves the positioning accuracy of the target area. Second, the Faster R-CNN model is insensitive to small targets, irregular shapes, and strong noises in bridge defect detection, which results in a long training time and low recognition accuracy. Accordingly, a novel Lightweight MFF (namely MFF-L）model for bridge appearance defect detection using a lightweight network EfficientNetV2 and a feature pyramid network is proposed, which fuses multi-scale features to shorten the training speed and improve recognition accuracy. Finally, the effectiveness of the proposed method is evaluated on the bridge disease dataset and public computational fluid dynamic dataset.https://www.sciopen.com/article/10.26599/BDMA.2022.9020048defect detectionmulti-scale feature fusion (mff)region of interest (roi) alignmentlightweight network |
| spellingShingle | Rong Pang Yan Yang Aiguo Huang Yan Liu Peng Zhang Guangwu Tang Multi-Scale Feature Fusion Model for Bridge Appearance Defect Detection Big Data Mining and Analytics defect detection multi-scale feature fusion (mff) region of interest (roi) alignment lightweight network |
| title | Multi-Scale Feature Fusion Model for Bridge Appearance Defect Detection |
| title_full | Multi-Scale Feature Fusion Model for Bridge Appearance Defect Detection |
| title_fullStr | Multi-Scale Feature Fusion Model for Bridge Appearance Defect Detection |
| title_full_unstemmed | Multi-Scale Feature Fusion Model for Bridge Appearance Defect Detection |
| title_short | Multi-Scale Feature Fusion Model for Bridge Appearance Defect Detection |
| title_sort | multi scale feature fusion model for bridge appearance defect detection |
| topic | defect detection multi-scale feature fusion (mff) region of interest (roi) alignment lightweight network |
| url | https://www.sciopen.com/article/10.26599/BDMA.2022.9020048 |
| work_keys_str_mv | AT rongpang multiscalefeaturefusionmodelforbridgeappearancedefectdetection AT yanyang multiscalefeaturefusionmodelforbridgeappearancedefectdetection AT aiguohuang multiscalefeaturefusionmodelforbridgeappearancedefectdetection AT yanliu multiscalefeaturefusionmodelforbridgeappearancedefectdetection AT pengzhang multiscalefeaturefusionmodelforbridgeappearancedefectdetection AT guangwutang multiscalefeaturefusionmodelforbridgeappearancedefectdetection |