ABSTRACT
This study focuses on detections of cars around a person driving a car, including their states such as "going forward" or "stopping" from their brake lights. Since brake lights are visual information, we believe that they can be applied to image recognition, and the object of this study is to detect cars including their states using object detection, which is one of the image recognition methods. By using the Swin transformer as a detection method, we succeed in detecting a car including its state from an image. In addition, pre-training and network optimization were performed to achieve higher detection accuracy
- G. Mariem, E. Ridha, and Z. Mourad:“Detection of Abnormal Movements of a Crowd in a Video Scene”, International Journal of Computer Theory and Engineering vol. 8, no. 5, pp. 398-402, 2016.Google ScholarCross Ref
- Xin Xie, Huiping Li, and Fengping Hu:“The Flocs Target Detection Algorithm Based on the Three Frame Difference and Enhanced Method of the Otsu”, International Journal of Computer Theory and Engineering vol. 7, no. 3, pp. 197-200, 2015.Google ScholarCross Ref
- Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo: “Swin Transformer: Hierarchical Vision Transformer using Shifted Windows.”, IEEE International Conference on Computer Vision (ICCV), pp. 10012-10022, 2021.Google ScholarCross Ref
- Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby: “An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale.”, International Conference on Learning Representations (ICLR), pp. 1-21, 2021.Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin: “Attention Is All You Need.”, In Advances in Neural Information Processing Systems, pp. 5998-6008, 2017.Google ScholarDigital Library
- He K., Gkioxari G., Dollár P., Girshick, R. “Mask r-cnn”, IEEE International Conference on Computer Vision (CVPR), pp. 2961-2969,2017.Google ScholarCross Ref
- F. Yu, H. Chen, X. Wang, W. Xian, Y. Chen, F. Liu, V. Madhavan, and T. Darrell: “BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2636-2645, 2020.Google ScholarCross Ref
- Tsung-Yi Lin, Piotr Dollar, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie: “Feature Pyramid Networks for Object Detection”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2117-2125, 2017.Google ScholarCross Ref
- Shu Liu, Lu Qi, Haifang Qin, Jianping Shi, and Jiaya Jia: “Path Aggregation Network for Instance Segmentation”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8759-8768, 2018.Google ScholarCross Ref
- Ghiasi, Golnaz, Tsung-Yi Lin, and Quoc V. Le: “Nas-fpn: Learning Scalable Feature Pyramid Architecture for Object Detection.”, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7036-7045, 2019.Google Scholar
- Kai Chen, Yuhang Cao, Chen Change Loy, Dahua Lin and Christoph Feichtenhofer: “Feature Pyramid Grids”, arXiv Preprint arXiv:2004.03580, 2020.Google Scholar
- Xiyang Dai, Yinpeng Chen, Bin Xiao, Dongdong Chen, Mengchen Liu, Lu Yuan, Lei Zhang: “Dynamic Head: Unifying Object Detection Heads With Attentions”, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7373-7382, 2021.Google ScholarCross Ref
- J. Redmon, S. Divvala, R. Girshick, and A. Farhadi: “You Only Look Once: Unified, Real-Time Object Detection”, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779-788, 2016.Google ScholarCross Ref
- J. Redmon and A. Farhadi: “YOLOv3: An Incremental Improvement”, arXiv:1804.02767, 2018.Google Scholar
- A. Bochkovskiy, C. Y. Wang and H. Y. M. Liao: “YOLOv4: Optimal Speed and Accuracy of Object Detection”, arXiv:2004.10934, 2020.Google Scholar
Recommendations
Development the Cockpit of the Autonomous Cars
Design, User Experience, and Usability: Design Thinking and Practice in Contemporary and Emerging TechnologiesAbstractThe evolution of cars has been notorious over the years, since the first four-wheeled car, that emerged in mid-1891 up to the present day, where it’s already possible to see semi-autonomous cars.
Currently, and with the constant automotive ...
Scheme of Autonomous Vehicle Abnormal Behavior Detection Technology Based on Edge Computing
HPCCT & BDAI '20: Proceedings of the 2020 4th High Performance Computing and Cluster Technologies Conference & 2020 3rd International Conference on Big Data and Artificial IntelligenceAs the development of automatic driving technology, more and more attention has been paid to the safety and standardization of autonomous vehicles. Although high-definition map[4] navigation has been used to assist the automatic driving of vehicles, ...
Detecting Driver Fatigue based on the Driver's Response Pattern and the Front View Environment of an Automobile
ISUC '08: Proceedings of the 2008 Second International Symposium on Universal CommunicationIn the field of an automotive research, a method to monitor and to detect a drowsy or a drunken driver has been studied for many years. Previous research uses sensors such as an infrared camera for pupil detection or voice to detect fatigue. Even these ...
Comments