This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Optimization on Roadside Perception Algorithm Based on Cascade R-CNN
Technical Paper
2022-01-7112
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
Owing to many categories, various scales, complex backgrounds and object occlusion of traffic participants in the RGB images of roadside perception, there are a certain number of object false detection and missed detection. Cascade R-CNN, a two-stage object detection network, is an image algorithm with better effect. In this paper, we makes several optimizations to improve the detection accuracy based on this network. The specific improvements are as follows: ResNeXt50 is used as the backbone structure to replace the original ResNet50. We obtain the aspect ratio that meets the requirements of roadside perception image by counting the aspect ratio of the annotation box. By expanding the feature pyramid network to PANet, we further integrate multi-scale information, which contributes to improve the ability to extract low-level object information. Since the bounding box coordinates calculated by Smooth L1 Loss are independent, we introduce GIoU to optimize the regression accuracy of the bounding box.. In order to evaluate the roadside perception algorithm more comprehensively and accurately, this paper adds quantitative metrics such as detection rate, correct detection rate, missed detection rate, false detection rate on the basis of common metrics (AP, Precision, Recall). On the self-built roadside dataset Vanjee_RS_2D, in the case of the same FLOPS, the mAP increased by 0.95% as just using ResNeXt50. After adding GIoU and PANet, the mAP increased by 0.32%and 0.76%. The mAP of the optimized model is 2.03% higher, where other metrics are also optimized accordingly.
Authors
- Qijun Zhang - Vanjee Suzhou Internet of Vehicle technology Co., Ltd. Beiji
- Dengjiang Wang - Beijing VanJee Technology Co., Ltd.
- Bing Ma - Vanjee Suzhou Internet of Vehicle technology Co., Ltd.
- Jinying Wu - Beijing VanJee Technology Co., Ltd.
- Yajun Wang - Beijing VanJee Technology Co., Ltd.
- Jianchao Liu - Beijing VanJee Technology Co., Ltd.
Topic
Citation
Zhang, Q., Wang, D., Ma, B., Wu, J. et al., "Optimization on Roadside Perception Algorithm Based on Cascade R-CNN," SAE Technical Paper 2022-01-7112, 2022, https://doi.org/10.4271/2022-01-7112.Also In
References
- Ye , X. , Shu , M. , Li , H. et al. Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022
- Dalal , N. and Triggs , B. Histograms of Oriented Gradients for Human Detection IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) 2005
- Lowe , D.G. Distinctive Image Features from Scale-Invariant Keypoints International Journal of Computer Vision 60 2 2004 91 110
- Papageorgiou , C.P. , Oren , M. , and Poggio , T. A General Framework for Object Detection Sixth International Conference on Computer Vision (IEEE Cat. No. 98CH36271) 2002
- Platt , J.C. Fast Training of Support Vector Machines Using Sequential Minimal Optimization Advances in Kernel Methods 1999
- Felzenszwalb , P.F. , Girshick , R.B. , Mcallester , D.A. Visual Object Detection with Deformable Part Models IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010 San Francisco, CA 2010
- Milind , N. , Shuo , W. , Anastasiu , D.C. , Zheng , T. et al. The 5th AI City Challenge IEEE Conference on Computer Vision and Pattern Recognition 4263 4273 2021
- Bochkovskiy , A. , Wang , C.Y. , Liao , H. 2020
- Ren , S. , He , K. , Girshick , R. et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Advances in Neural Information Processing Systems 2015 91 99
- Zhaowei , C. and Nuno , V. 10.1109/CVPR.2018.00644
- Simonyan , K. and Zisserman , A. Very Deep Convolutional Networks for Large-Scale Image Recognition 2014
- Kaiming , H. Xiangyu , Z. , Shaoqing , R. , and Jian , S. Deep Residual Learning for Image Recognition The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Boston, USA 2015
- Szegedy , C. , Liu , W. , Jia , Y. et al. Going Deeper with Convolutions The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Boston, USA 2015
- Saining , X. , Ross , G. , Piotr , D. , Zhuowen , T. et al. Aggregated Residual Transformations for Deep Neural Networks The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Honolulu, USA 2017
- Lin , T.Y. , Dollár , P. , Girshick , R. et al. Feature Pyramid Networks for Object Detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2117 2125 2017
- Shu , L. , Lu , Q. , Haifang , Q. , Jianping , S. et al. Path Aggregation Network for Instance Segmentation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 8759 8768 2018
- Rezatofighi , H. , Tsoi , N. , Gwak , J.Y. et al. Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019