Automatic Traffic Sign Detection and Recognition Using Mobile Lidar Data With Digital Images

Abstract

Abstract. 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.

Using mobile laser scanner and imagery for urban management applications

“…Finally, Guan et al [48] and Guan et al [49] relied on RIEGL VMX 450 to propose a method for detecting traffic signs directly from mobile LiDAR point clouds based on prior knowledge on aspects such as road width, pole height, material reflectance , geometrical structure, and traffic sign size. Additionally, the system uses traffic sign image segmentation by projecting the detected traffic sign points onto the digital images.…”

“…In this sense, semantic detection has simplified the traffic sign detection task. 3D information is reprojected onto 2D images, and D-ANNs are used for sign classification, as discussed in [47], [39], [61], [62], [86]- [88]. These systems use CNNs hierarchically organized based on supervised learning and contain several specialized hidden layers.…”

“…This organization allows the first layers to detect lines and curves and specialize until they reach deeper layers that recognize complex shapes, such as faces or an animal silhouettes. Guan et al [49] developed an automatic traffic sign detection and recognition method. They employed an euclidean clustering to extract pole-like objects and the retro-reflectance properties for traffic signs.…”