Term of Award
Fall 2019
Degree Name
Master of Science, Applied Geography
Document Type and Release Option
Thesis (open access)
Copyright Statement / License for Reuse
This work is licensed under a Creative Commons Attribution 4.0 License.
Department
Department of Geology and Geography
Committee Chair
Xiaolu Zhou
Committee Member 1
Wei Tu
Committee Member 2
Kai Wang
Abstract
Traffic sign detection and positioning have drawn considerable attention because of the recent development of autonomous driving and intelligent transportation systems. In order to detect and pinpoint traffic signs accurately, this research proposes two methods. In the first method, geo-tagged Google Street View images and road networks were utilized to locate traffic signs. In the second method, both traffic signs categories and locations were identified and extracted from the location-based GoPro video. TensorFlow is the machine learning framework used to implement these two methods. To that end, 363 stop signs were detected and mapped accurately using the first method (Google Street View image-based approach). Then 32 traffic signs were recognized and pinpointed using the second method (GoPro video-based approach) for better location accuracy, within 10 meters. The average distance from the observation points to the 32 ground truth references was 7.78 meters. The advantages of these methods were discussed. GoPro video-based approach has higher location accuracy, while Google Street View image-based approach is more accessible in most major cities around the world. The proposed traffic sign detection workflow can thus extract and locate traffic signs in other cities. For further consideration and development of this research, IMU (Inertial Measurement Unit) and SLAM (Simultaneous Localization and Mapping) methods could be integrated to incorporate more data and improve location prediction accuracy.
OCLC Number
1143316418
Recommended Citation
Wu, Zihao, "Computer Vision-Based Traffic Sign Detection and Extraction: A Hybrid Approach Using GIS And Machine Learning" (2019). Electronic Theses and Dissertations. 2039.
https://digitalcommons.georgiasouthern.edu/etd/2039
Research Data and Supplementary Material
No
Included in
Artificial Intelligence and Robotics Commons, Graphics and Human Computer Interfaces Commons, Other Earth Sciences Commons
