TY - GEN
T1 - Weakly Supervised Detection of Overhead Contact System Bolts Based on Improved Proposal Cluster Learning
AU - Qin, Yalan
AU - Wang, Zhipeng
AU - Qin, Yong
AU - Shao, Changhong
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.
PY - 2024
Y1 - 2024
N2 - Bolts are critical components of overhead contact systems (OCS), and their timely detection of looseness or absence is of great significance in maintaining the structural safety and stability of key components of OCS. In response to the characteristics that bolts in the picture are small in size, numerous in quantity, and irregular in shape, making them difficult to annotate, we propose a weakly supervised detection method for bolts based on improved proposal cluster learning, which can accurately locate bolts with only image-level annotations. Specifically, image-level annotations only require labeling the classes of the targets in a given image (e.g., using a binary vector with 0s and 1s to indicate the existence of a particular type of bolt in the image). Compared to instance-level annotations (e.g., bounding boxes) required by fully supervised models, this approach significantly reduces the difficulty of annotation and saves labor costs for creating bolt datasets. Through optimization experiments such as NMS threshold, multi-scale training, and IoU threshold, as well as the design of the weighted loss function, the proposed method achieves detection results with mAP of 27.4% and Corloc of 48.7%.
AB - Bolts are critical components of overhead contact systems (OCS), and their timely detection of looseness or absence is of great significance in maintaining the structural safety and stability of key components of OCS. In response to the characteristics that bolts in the picture are small in size, numerous in quantity, and irregular in shape, making them difficult to annotate, we propose a weakly supervised detection method for bolts based on improved proposal cluster learning, which can accurately locate bolts with only image-level annotations. Specifically, image-level annotations only require labeling the classes of the targets in a given image (e.g., using a binary vector with 0s and 1s to indicate the existence of a particular type of bolt in the image). Compared to instance-level annotations (e.g., bounding boxes) required by fully supervised models, this approach significantly reduces the difficulty of annotation and saves labor costs for creating bolt datasets. Through optimization experiments such as NMS threshold, multi-scale training, and IoU threshold, as well as the design of the weighted loss function, the proposed method achieves detection results with mAP of 27.4% and Corloc of 48.7%.
KW - Deep Learning
KW - High-Speed Railway
KW - Multi-instance Learning
KW - Object Detection
KW - Overhead Contact System Bolts
KW - Weakly Supervised Detection
UR - https://www.scopus.com/pages/publications/85201945331
U2 - 10.1007/978-981-97-3682-9_80
DO - 10.1007/978-981-97-3682-9_80
M3 - 会议稿件
AN - SCOPUS:85201945331
SN - 9789819736812
T3 - Lecture Notes in Electrical Engineering
SP - 863
EP - 872
BT - Developments and Applications in SmartRail, Traffic, and Transportation Engineering - Proceedings of ICSTTE 2023
A2 - Jia, Limin
A2 - Qin, Yong
A2 - Easa, Said
PB - Springer Science and Business Media Deutschland GmbH
T2 - International Conference on SmartRail, Traffic, and Transportation Engineering, ICSTTE 2023
Y2 - 28 July 2023 through 30 July 2023
ER -