An accurate shared bicycle detection network based on faster R‐CNN. Issue 6 (23rd February 2023)

• Record Type: Journal Article
• Authors: Li, Lingqiao; Wang, Xiangkai; Yang, Mengyu; Zhang, Hongwei
• Is Part Of: IET image processing. Volume 17:Issue 6(2023)
• Page Start: 1919
• Page End: 1930
• Publication Date: 2023-02-23
• Subjects: deformable convolution -- feature fusion -- object detection application -- shared bicycle management; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/ipr2.12766
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract: Detecting shared bicycles is an essential and challenging task. Deep learning has been widely used in object detection tasks in urban scenes, such as vehicle detection. However, deep learning algorithms still face many difficulties and challenges in shared bicycle detection. For example, the problem of large deformation of shared bicycles and the problem of small targets because the camera is far away from the shared bicycles. In order to solve these problems, this study introduces the feature fusion module and deformable convolution into the object detection network, which improves the efficiency of shared bicycle detection. This study proposes an enhanced faster R‐CNN network (A classic two‐stage object detection network) for shared bicycle detection and a shared bicycle dataset (SBD) is constructed for model training and testing. Compared with the original faster R‐CNN, the mean average precision (mAP) of the enhanced method on SBD is improved by 13%, which indicates that the method provided in this study is more suitable for detecting shared bicycles. This study also conducts experiments on the Microsoft Common Objects (COCO) dataset, where this method achieves 40.2% of the mAP, which is 5.8% higher than faster R‐CNN before improvement. Abstract : This study proposes an enhanced faster R‐CNN network for shared bicycle detection to address these issues. At the same time, a shared bicycle dataset (SBD) is constructed for model training and testing. Compared with the original faster R‐CNN, the mean average precision (mAP) of the enhanced method on SBD is improved by 13%, which indicates that the method provided in this study is more suitable for detecting shared bicycles in urban scenes. This study also conducts experiments on the Microsoft Common Objects (COCO) dataset, where the method achieves 40.2% of mAP, which is 5.8% higher than faster R‐CNN before improvement.