Proceedings. 1991 IEEE International Conference on Robotics and Automation
DOI: 10.1109/robot.1991.131922
|View full text |Cite
|
Sign up to set email alerts
|

Autonomous landmark selection for route recognition by a mobile robot

Abstract: This work introduces an approach to build a qualitative description of scenes along a route, which is used in route recognition by a mobile robot. The description consists of a series of Landmarks autonomously selected by the robot from a Generalized Panoramic View, which has been generated as a visual memory of scenes along routes. The basic idea to bridge the quantitative panoramic view to qualitative landmarks is to examine the 'distinctiveness' of patterns in the image and select landmarks from unique patt… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
3
0

Publication Types

Select...
6
2
1

Relationship

1
8

Authors

Journals

citations
Cited by 21 publications
(4 citation statements)
references
References 7 publications
0
3
0
Order By: Relevance
“…Other notable contributions related to map building are by Ayache and Faugeras [7], [6] using trinocular vision and Kalman filtering, by Zhang and Faugeras [162] using 3D reconstruction from image sequences, by Giralt et al [44] using sensor fusion techniques, and by Zheng et al [163], and Yagi et al [159] using panoramic views.…”
Section: Map-buildingmentioning
confidence: 99%
“…Other notable contributions related to map building are by Ayache and Faugeras [7], [6] using trinocular vision and Kalman filtering, by Zhang and Faugeras [162] using 3D reconstruction from image sequences, by Giralt et al [44] using sensor fusion techniques, and by Zheng et al [163], and Yagi et al [159] using panoramic views.…”
Section: Map-buildingmentioning
confidence: 99%
“…При цьому може використовуватись декілька відеокамер, інформація від яких обробляється стерео алгоритмами [3]. Якісне розпізнавання НО здійснюється на основі апріорної інформації про його зображення або в процесі панорамного опису сцен [4]. Апріорна інформація для розпізнавання об'єктів міститься в базі даних і може досягати 10 мільйонів фотографій сцен [5].…”
Section: модель кольоровості об'єктів на фоні довільної місцевостіunclassified
“…Humans memorize objects with distinctive features along the route as landmarks and move along the correct route guided by them. We have explored what are distinctive patterns over a wide range and presented a method for finding distinctive patterns in the Panoramic Representation by examining iconic properties such a s hue, saturation, area and perimeter [5]. The method, however, relies heavily on reliability in finding and/or measuring such attributes.…”
Section: Introductionmentioning
confidence: 99%