Paper Info
Title
Experimental tests of vision-based artificial landmark detection using random forests and particle filter
Abstract
This paper proposes a novel artificial landmark detection technique for underwater robots in structured underwater environment. The novel landmark detection technique is composed of a salient object segmentation using random forest combined with particle filter and an object recognition using weighted template matching. The random image patch-based random forest is employed for detection of the regions of salient objects and its accuracy is enhanced by combining with particle filter. Each detected candidate region is refined through the active contour technique and recognized as one of the artificial landmarks or background by the weighted template matching technique. The performance of the proposed method is evaluated by experiments with an autonomous underwater robot platform, yShark, developed by KRISO and the results are discussed by comparing with the result of the previous research.
Year
DOI
Venue
2014
10.1109/URAI.2014.7057483
URAI
Keywords
Field
DocType
template matching,particle filtering (numerical methods),random forest,object detection,yshark,image matching,image segmentation,autonomous underwater robot platform,mobile robots,object segmentation,particle filter,autonomous underwater vehicles,feature extraction,image classification,random image patch,object recognition,vision-based artificial landmark detection,robot vision,underwater vision,vegetation
Active contour model,Template matching,Computer vision,Scale-space segmentation,Pattern recognition,Computer science,Particle filter,Segmentation-based object categorization,Image segmentation,Artificial intelligence,Landmark,Random forest
Conference
ISSN
Citations 
PageRank 
2325-033X
0
0.34
References 
Authors
7
4
Name
Order
Citations
PageRank
Donghoon Kim1518.42
Donghwa Lee2265.20
Hyun Myung329062.59
Hyun-Taek Choi4147.98