Robust vision-based localization for mobile robots using an image retrieval system based on invariant features

Wolf, Jürgen; Burgard, Wolfram; Burkhardt, Hans

doi:10.1109/robot.2002.1013387

Cited by 74 publications

(60 citation statements)

References 15 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The idea of adapting text categorization methods to visual categorization is not new. For example, an object class recognition method is proposed [12] for the unsupervised learning of invariant descriptors of image windows. However, in the training step of their method, distinct views of the same object class must be segregated into different categories.…”

Section: Outlines Of Our Approachmentioning

confidence: 99%

Learning Representative Features for Robot Topological Localization

Zhao

Feng

Fang

et al. 2013

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

This paper proposes a new method for mobile robots to recognize places with the use of a single camera and natural landmarks. In the learning stage, the robot is manually guided along a path. Video sequences are captured with a front-facing camera. To reduce the perceptual alias of visual features, which are easily confused, we propose a modified visual feature descriptor which combines the dominant hue colour information with the local texture. A Location Features Vocabulary Model (LVFM) is established for each individual location using an unsupervised learning algorithm. During the course of travelling, the robot employs each detected interest point to vote for the most likely place. The spatial relationships between the locations, modelled by the Hidden Markov Model (HMM), are exploited to increase the robustness of location recognition in cases of dynamic change or visual similarity. The proposed descriptors are compared with several state-of-the-art descriptors including SIFT, colour SIFT, GLOH and SURF. Experiments show that both the LVFM based on the dominant Hue-SIFT feature and the spatial relationships between the locations contribute considerably to the high recognition rate.

show abstract

Section: Outlines Of Our Approachmentioning

confidence: 99%

Learning Representative Features for Robot Topological Localization

Zhao

Feng

Fang

et al. 2013

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

show abstract

“…The field of mobile robot localization is currently dominated by global localization algorithm (Davison, 1998;Se et al, 2002;Sim & Dudek, 1998;Thrun et al, 2001;Wolf et al, 2002), due to the global pose being the desired goal. However, a robust and accurate local localization algorithm has many benefits, such as faster processing time, less reliability on the landmarks, and they often form the basis for global localization algorithms.…”

Section: Related Workmentioning

confidence: 99%

Floor Texture Visual Servo Using Multiple Cameras for Mobile Robot Localization

Matsumoto¹,

Powers²,

Asgari³

2010

Robot Localization and Map Building

View full text Add to dashboard Cite

“…Only in a few approaches, vision is used for self-localization [2,11]. Self-localization in RoboCup is different, because the area the robots can be located at is relatively small, i. e. the field, but in that area the position of the robots has to be determined quite precisely to allow different robots of the same team to communicate about objects on the field, and to follow some location-based rules of the game.…”

Section: Self-localization Based On Edge Pointsmentioning

confidence: 99%

Fast and Robust Edge-Based Localization in the Sony Four-Legged Robot League

Röfer

Jüngel

2004

RoboCup 2003: Robot Soccer World Cup VII

View full text Add to dashboard Cite

Abstract. This paper presents a fast approach for edge-based selflocalization in RoboCup. The vision system extracts edges between the field and field lines, borders, and goals following a grid-based approach without processing whole images. These edges are employed for the selflocalization of the robot. Both image processing and self-localization work in real-time on a Sony Aibo, i. e. at the frame rate of the camera. The localization method was evaluated using a laser range sensor at the field border as a reference system.

show abstract

Robust vision-based localization for mobile robots using an image retrieval system based on invariant features

Abstract: In this paper we present a vision-based approach to mobile

Cited by 74 publications

References 15 publications

Learning Representative Features for Robot Topological Localization

Learning Representative Features for Robot Topological Localization

Floor Texture Visual Servo Using Multiple Cameras for Mobile Robot Localization

Fast and Robust Edge-Based Localization in the Sony Four-Legged Robot League

Contact Info

Product

Resources

About