21 Aug 2020
21 Aug 2020
AUTOMATIC TRAFFIC SIGN DETECTION AND RECOGNITION USING MOBILE LIDAR DATA WITH DIGITAL IMAGES
H. Guan1, Y. Yu2, D. Li3, and J. Li4
H. Guan et al.
H. Guan1, Y. Yu2, D. Li3, and J. Li4
- 1School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science & Technology, Nanjing, Jiangsu 210044, China
- 2College of Computer Engineering, Huaiyin Institute of Technology, Huaian, JS 223003, China
- 3State Key laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan, China
- 4Department of Geography and Environmental Management, University of Waterloo, Waterloo, ON N2L 3G1, Canada
- 1School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science & Technology, Nanjing, Jiangsu 210044, China
- 2College of Computer Engineering, Huaiyin Institute of Technology, Huaian, JS 223003, China
- 3State Key laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan, China
- 4Department of Geography and Environmental Management, University of Waterloo, Waterloo, ON N2L 3G1, Canada
Hide author details
Keywords: mobile LiDAR, images, traffic sign, capsule convolutional networks, high-order capsule features
This paper presents a traffic sign detection and recognition method from mobile LiDAR data and digital images for intelligent transportation-related applications. The traffic sign detection and recognition method includes two steps: traffic sign interest regions are first extracted from mobile LiDRA data. Next, traffic signs are identified from digital images simultaneously collected from the multi-sensor mobile LiDAR systems via a convolutional capsule network model. The experimental results demonstrate that the proposed method obtains a promising, reliable, and high performance in both detecting traffic signs in 3-D point clouds and recognizing traffic signs on 2-D images.