Vehicle Orientation Detection Using CNN
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Vehicle orientation detection is a challenging task because the orientations of vehicles can vary in a wide rangein captured images. The existing methods for oriented vehicle detection require too much computation time to beapplied to a real-time system. We propose Rotate YOLO, which has a set of anchor boxes with multiple scales,ratios, and angles to predict bounding boxes. For estimating the orientation angle, we applied angle-related IoUwith CIoU loss to solve the underivable problem from the calculation of SkewIoU. Evaluation results on threepublic datasets DLR Munich, VEDAI and UCAS-AOD demonstrate the efficiency of our approach
Abstract
Vehicle orientation detection is a challenging task because the orientations of vehicles can vary in a wide rangein captured images. The existing methods for oriented vehicle detection require too much computation time to beapplied to a real-time system. We propose Rotate YOLO, which has a set of anchor boxes with multiple scales,ratios, and angles to predict bounding boxes. For estimating the orientation angle, we applied angle-related IoUwith CIoU loss to solve the underivable problem from the calculation of SkewIoU. Evaluation results on threepublic datasets DLR Munich, VEDAI and UCAS-AOD demonstrate the efficiency of our approach
참고문헌 (16)
- R. Girshick, "Fast R-CNN", Proc. IEEE Int. Conf. Comput. Vis. (ICCV), pp.1440~1448 (2015)
- S. Ren, "Faster R-CNN: Towards real-time object detection with region proposal networks", IEEE Trans. Pattern Anal. Mach. Intell, 39(6), pp.1137~1149 (2017)[DOI]
- W. Liu, "SSD: Single shot multibox detector", Proc. Eur. Conf. Comput. Vis, pp.21~37 (2016)
- Chien-Yao Wang, "Scaled-YOLOv4: Scaling Cross Stage Partial Network", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021)
- J. Redmon, "YOLO9000:Better, faster, stronger", Proc. IEEE Conf. Comput. Vis. Pattern Recognition (CVPR), pp.7263~7271 (2017)
- Alexey Bochkovskiy, "YOLOv4: Optimal speed and accuracy of object detection" (2020)
- Yang, Xue, "R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object", Proc. IEEE Conf. Comput. Vis. Pattern Recognition (CVPR) (2019)
- Furong Shi, "Orientation-Aware Vehicle Detection in Aerial Images via an Anchor-Free Object Detection Approach", IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 59(6), pp.2021~ (2021)[DOI]
- Lei Liu, "Learning a Rotation Invariant Detector with Rotatable Bounding box", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)
- "Public Datasets"[URL]
- "Vehicle Detection in Aerial Imagery (VEDAI)"[URL]
- "UCAS-AOD dataset"[URL]
- J. Ma, "Arbitrary-oriented scene text detection via rotation proposals", IEEE Trans. Multimedia, 20(11), pp.3111~3122 (2018)
- T. Tang, "Arbitrary-oriented vehicle detection in aerial imagery with single convolutional neural networks", Remote Sens, 9(11), pp.1170~2017 (2017)
- P. Dollar, "Fast feature pyramids for object detection", IEEE Trans. Pattern Anal. Mach. Intell., 36(8), pp.1532~1545 (2014)
- S. Razakarivony, "Vehicle detection in aerial imagery : A small target detection benchmark", J. Vis. Commun. Image Represent., 34, pp.187~203 (2016)