A Clustering-Based Obstacle Segmentation Approach for Urban Environments

Submitted by grigby1 on Wed, 03/08/2017 - 2:04pm

Title	A Clustering-Based Obstacle Segmentation Approach for Urban Environments
Publication Type	Conference Paper
Year of Publication	2015
Authors	Ridel, D. A., Shinzato, P. Y., Wolf, D. F.
Conference Name	2015 12th Latin American Robotic Symposium and 2015 3rd Brazilian Symposium on Robotics (LARS-SBR)
Date Published	oct
Keywords	autonomous navigation, Benchmark testing, Cameras, clustering, Clustering algorithms, clustering-based obstacle segmentation approach, collision avoidance, collision prevention, disparity map, hand-labeled image evaluation, Image edge detection, image segmentation, KITTI object detection benchmark, object detection, obstacle detection, precision metric, pubcrawl170111, recall metric, robots, Sensors, stereo image processing, stereo vision, urban environment
Abstract	The detection of obstacles is a fundamental issue in autonomous navigation, as it is the main key for collision prevention. This paper presents a method for the segmentation of general obstacles by stereo vision with no need of dense disparity maps or assumptions about the scenario. A sparse set of points is selected according to a local spatial condition and then clustered in function of its neighborhood, disparity values and a cost associated with the possibility of each point being part of an obstacle. The method was evaluated in hand-labeled images from KITTI object detection benchmark and the precision and recall metrics were calculated. The quantitative and qualitative results showed satisfactory in scenarios with different types of objects.
DOI	10.1109/LARS-SBR.2015.58
Citation Key	ridel_clustering-based_2015

Groups:

Science of Security VO