Find in Library
Search millions of books, articles, and more
Indexed Open Access Databases
Vertical Corner Feature Based Precise Vehicle Localization Using 3D LIDAR in Urban Area
oleh: Jun-Hyuck Im, Sung-Hyuck Im, Gyu-In Jee
Format: | Article |
---|---|
Diterbitkan: | MDPI AG 2016-08-01 |
Deskripsi
Tall buildings are concentrated in urban areas. The outer walls of buildings are vertically erected to the ground and almost flat. Therefore, the vertical corners that meet the vertical planes are present everywhere in urban areas. These corners act as convenient landmarks, which can be extracted by using the light detection and ranging (LIDAR) sensor. A vertical corner feature based precise vehicle localization method is proposed in this paper and implemented using 3D LIDAR (Velodyne HDL-32E). The vehicle motion is predicted by accumulating the pose increment output from the iterative closest point (ICP) algorithm based on the geometric relations between the scan data of the 3D LIDAR. The vertical corner is extracted using the proposed corner extraction method. The vehicle position is then corrected by matching the prebuilt corner map with the extracted corner. The experiment was carried out in the Gangnam area of Seoul, South Korea. In the experimental results, the maximum horizontal position error is about 0.46 m and the 2D Root Mean Square (RMS) horizontal error is about 0.138 m.