As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
An object recognizing and tracking method based on depth images of 3D Lidar is presented for perceiving dynamic surroundings in this paper. Based on the design principle of 3D Lidar sensor, the Lidar data is projected into 2D depth images and height images. The algorithm divides the depth image into different clusters by edge detection, and then extracts the spatial features. Then the obstacles can be associated to their history by feature comparing. At last, a Kalman filter is used to calculate the obstacles’ velocity and predict the future location of obstacles, which can make a more accurate result for next loop. The proposed algorithm is tested on the self-developed mobile robot platform, “Qilin-II”. As results, multiple obstacles within 20 meters have been recognized, tracked and rematched successfully at the rate of 95 milliseconds per frame.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.