Title
Obstacle localization and recognition for autonomous forklifts using omnidirectional stereovision
Abstract
In this paper we propose an approach for obstacle localization and recognition using omnidirectional stereovision applied to autonomous fork-lifts in industrial environments. We use omnidirectional stereovision with two fisheye cameras for the 3D perception of the surrounding environment. Using the reconstructed 3D points, a Digital Elevation Map (DEM) is constructed consisting of a 2.5D grid of elevation cells. Each cell is then classified as ground or obstacle. Further, we use the classified DEM to generate obstacle hypotheses. To ensure a higher detection rate we also propose a fast sliding window based approach relying on the monocular fisheye intensity image. The detections from both approaches are merged and are subjected to a tracking mechanism. Finally each obstacle is classified using boosting over Visual Codebook type features. The classification is refined using the classification history available from tracking. The presented approaches are integrated into a 3D visual perception system for AGVs and are of real time performance.
Year
DOI
Venue
2015
10.1109/IVS.2015.7225739
2015 IEEE Intelligent Vehicles Symposium (IV)
Keywords
Field
DocType
obstacle localization,obstacle recognition,autonomous forklift,omnidirectional stereovision,industrial environment,3D perception,3D points reconstruction,digital elevation map,DEM,elevation cells,obstacle hypothesis,fast sliding window based approach,monocular fisheye intensity image,tracking mechanism,obstacle classification,boosting,visual codebook type features,classification history,3D visual perception system,AGV
Obstacle,Computer vision,Omnidirectional antenna,Sliding window protocol,Computer science,Boosting (machine learning),Artificial intelligence,Monocular,Grid,Visual perception,Codebook
Conference
ISSN
Citations 
PageRank 
1931-0587
1
0.36
References 
Authors
14
3
Name
Order
Citations
PageRank
arthur daniel costea131.41
Andrei Vatavu2375.47
Sergiu Nedevschi31321126.37