Equirectangular Image Data Detection, Segmentation and Classification of Varying Sized Traffic Signs: A Comparison of Deep Learning Methods
Author:
Li Heyang (Thomas)1ORCID, Todd Zachary1ORCID, Bielski Nikolas1ORCID
Affiliation:
1. School of Mathematics and Statistics, College of Engineering, University of Canterbury, Christchurch 8041, New Zealand
Abstract
There are known limitations in mobile omnidirectional camera systems with an equirectangular projection in the wild, such as momentum-caused object distortion within images, partial occlusion and the effects of environmental settings. The localization, instance segmentation and classification of traffic signs from image data is of significant importance to applications such as Traffic Sign Detection and Recognition (TSDR) and Advanced Driver Assistance Systems (ADAS). Works show the efficacy of using state-of-the-art deep pixel-wise methods for this task yet rely on the input of classical landscape image data, automatic camera focus and collection in ideal weather settings, which does not accurately represent the application of technologies in the wild. We present a new processing pipeline for extracting objects within omnidirectional images in the wild, with included demonstration in a Traffic Sign Detection and Recognition (TDSR) system. We compare Mask RCNN, Cascade RCNN, and Hybrid Task Cascade (HTC) methods, while testing RsNeXt 101, Swin-S and HRNetV2p backbones, with transfer learning for localization and instance segmentation. The results from our multinomial classification experiment show that using our proposed pipeline, given that a traffic sign is detected, there is above a 95% chance that it is classified correctly between 12 classes despite the limitations mentioned. Our results on the projected images should provide a path to use omnidirectional images with image processing to enable the full surrounding awareness from one image source.
Funder
Ministry of Business Innovation and Economics New Zealand Transport Agency Christchurch City Council
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference61 articles.
1. Wali, S.B., Abdullah, M.A., Hannan, M.A., Hussain, A., Samad, S.A., Ker, P.J., and Mansor, M.B. (2019). Vision-based traffic sign detection and recognition systems: Current trends and challenges. Sensors, 19. 2. Guo, J., Lu, J., Qu, Y., and Li, C. (2018, January 26–30). Traffic-Sign Spotting in the Wild via Deep Features. Proceedings of the 2018 IEEE Intelligent Vehicles Symposium (IV), Suzhou, China. 3. Zhu, Z., Liang, D., Zhang, S., Huang, X., Li, B., and Hu, S. (2016–1, January 26). Traffic-sign detection and classification in the wild. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA. 4. Li, Y., Tong, G., Gao, H., Wang, Y., Zhang, L., and Chen, H. (2019). Pano-RSOD: A Dataset and Benchmark for Panoramic Road Scene Object Detection. Electronics, 8. 5. Chandan, K., Albertson, J., Zhang, X., Zhang, X., Liu, Y., and Zhang, S. (2021). Learning to Guide Human Attention on Mobile Telepresence Robots with 360 degree Vision. arXiv.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|