The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLI-B1
https://doi.org/10.5194/isprs-archives-XLI-B1-661-2016
https://doi.org/10.5194/isprs-archives-XLI-B1-661-2016
06 Jun 2016
 | 06 Jun 2016

LIDAR-INCORPORATED TRAFFIC SIGN DETECTION FROM VIDEO LOG IMAGES OF MOBILE MAPPING SYSTEM

Y. Li, J. Fan, Y. Huang, and Z. Chen

Keywords: Traffic Sign Detection, Mobile Mapping System, RANSAC, Random Forest, Camshift, Kalman Filtering

Abstract. Mobile Mapping System (MMS) simultaneously collects the Lidar points and video log images in a scenario with the laser profiler and digital camera. Besides the textural details of video log images, it also captures the 3D geometric shape of point cloud. It is widely used to survey the street view and roadside transportation infrastructure, such as traffic sign, guardrail, etc., in many transportation agencies. Although many literature on traffic sign detection are available, they only focus on either Lidar or imagery data of traffic sign. Based on the well-calibrated extrinsic parameters of MMS, 3D Lidar points are, the first time, incorporated into 2D video log images to enhance the detection of traffic sign both physically and visually. Based on the local elevation, the 3D pavement area is first located. Within a certain distance and height of the pavement, points of the overhead and roadside traffic signs can be obtained according to the setup specification of traffic signs in different transportation agencies. The 3D candidate planes of traffic signs are then fitted using the RANSAC plane-fitting of those points. By projecting the candidate planes onto the image, Regions of Interest (ROIs) of traffic signs are found physically with the geometric constraints between laser profiling and camera imaging. The Random forest learning of the visual color and shape features of traffic signs is adopted to validate the sign ROIs from the video log images. The sequential occurrence of a traffic sign among consecutive video log images are defined by the geometric constraint of the imaging geometry and GPS movement. Candidate ROIs are predicted in this temporal context to double-check the salient traffic sign among video log images. The proposed algorithm is tested on a diverse set of scenarios on the interstate highway G-4 near Beijing, China under varying lighting conditions and occlusions. Experimental results show the proposed algorithm enhances the rate of detecting traffic signs with the incorporation of the 3D planar constraint of their Lidar points. It is promising for the robust and large-scale survey of most transportation infrastructure with the application of MMS.