Naslov
Algorithms for the detection of moving objects utilizing lidar sensors and stereo camera

Autori
Ćesić, Josip ; Lenac, Kruno ; Cvišić, Igor ; Kitanov, Andrej ; Seder, Marija ; Marković, Ivan ; Petrović, Ivan

Izvornik
CloudSLAM deliverable D1.1

Vrsta, podvrsta
Ostale vrste radova, izvještaj

Godina
2016

Ključne riječi
detection and tracking of moving objects ; laser range scanner ; stereo camera

Sažetak
Detection and tracking of moving objects is an essential problem in situational awareness context and hence crucial for many robotic applications. Here we propose a method for the detection of moving objects with a 3D laser range sensor and a stereo cameras. First, the lidar detection procedure starts with the ground extraction using random sample consensus approach for model parameter estimation. The resulting point cloud is then downsampled using voxel grid approach and filtered using a radius outlier rejection method. Within the approach, we have utilized a procedure for building short–term maps of the environment by using the octree data structure. This data structure enables an efficient comparison of the current scan and the short–term local map, thus detecting dynamic parts of scene. The ego-motion of the mobile agent is compensated using the available odometry information (still independent of the type of the agent), which is rather imperfect, and hence is refined using the iterative closest point registration technique. Furthermore, due to sensor characteristics, the iterative closest point is carried out in 2D between the short– term map and the current, where the non-ground filtered scans are projected onto 2D. The experiments performed using Velodyne HDL-32E laser sensor mounted on top of a mobile platform demonstrate the suitability and efficiency of the proposed method. Second, the stereo detection procedure aims at detecting a moving object and extracting it from the rest of the surrounding. To estimate the interim vehicle displacement, we use our visual stereo odometry algorithm (named SOFT) presented in [7]. Features not conforming to the computed displacement are considered as moving objects and are grouped together to yield measurements. In that respect our approach would fall within the motion-based detection approaches.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo, Temeljne tehničke znanosti

POVEZANOST RADA