Vision-based localization algorithm based on landmark matching, triangulation, reconstruction, and comparison

Yuen, David C. K.; MacDonald, Bruce A.

doi:10.1109/tro.2004.835452

Cited by 68 publications

(34 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 is fed into RANSAC along with the set of generated putatives C t , where a set of promising inlier putatives are selected to produce an optimal camera pose θ t . The RANSAC-based framework described above is very popular and has been used successfully by many authors [14], [15]. As the map M becomes larger and denser, we need to pay special attention in step (c) in order to maintain high-quality putative matches, since the high ratio of outlier putative matches will cause the RANSAC procedure in step (d) to slow down substantially or even fail to compute a correct estimate [16], which will result in under-performing system.…”

Section: Vision-based Camera Localizationmentioning

confidence: 99%

Learning visibility of landmarks for vision-based localization

Alcantarilla

Mariottini

et al. 2010

2010 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-We aim to perform robust and fast vision-based localization using a pre-existing large map of the scene. A key step in localization is associating the features extracted from the image with the map elements at the current location. Although the problem of data association has greatly benefited from recent advances in appearance-based matching methods, less attention has been paid to the effective use of the geometric relations between the 3D map and the camera in the matching process.In this paper we propose to exploit the geometric relationship between the 3D map and the camera pose to determine the visibility of the features. In our approach, we model the visibility of every map feature with respect to the camera pose using a nonparametric distribution model. We learn these nonparametric distributions during the 3D reconstruction process, and develop efficient algorithms to predict the visibility of features during localization. With this approach, the matching process only uses those map features with the highest visibility score, yielding a much faster algorithm and superior localization results. We demonstrate an integrated system based on the proposed idea and highlight its potential benefits for the localization in large and cluttered environments.

show abstract

Section: Vision-based Camera Localizationmentioning

confidence: 99%

Learning visibility of landmarks for vision-based localization

Alcantarilla

Mariottini

et al. 2010

2010 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

show abstract

“…To achieve this goal, vision based approaches have been tried, which help a robot to acquire meaningful information from visual images [6,7]. However, they require high computing cost and built-in sensors in robot.…”

Section: Related Workmentioning

confidence: 99%

Rfid Based Collision-Free Robot Docking in Cluttered Environment

Kim

Kim²,

Chong³

2010

PIER

View full text Add to dashboard Cite

Abstract-This paper proposes a radio frequency identification (RFID) based collision-free robot docking in cluttered environment. Physical distance estimation sensors are fused to the developed degree of arrival (DOA) guided robot docking system, and collision-avoidance function is implemented based on the vector field histogram technique. Additionally, new simple but efficient DOA filtering algorithm is developed based on the gain control according to the improved robot control algorithm, which enables the robot to move continuously. The experimental results show that the robot can move to target transponder even though the estimated DOA is blocked by obstacles. The success rate does not reach satisfactory level due to the limitation of the employed sensors and collision-avoidance algorithm, but it is proved that the collision-free docking becomes available without any priori map and reference stations.

show abstract

“…The RANSAC algorithm [19] is a useful method to estimate parameters of such models, however for efficiency, an agglomerative hierarchical tree T is used to identify the clusters. To construct the tree, Ψ (k) is heat mapped, represented as a symmetric matrix M , with respect to Manhattan distance between each individual helix,…”

Section: Helix Bearing Algorithmmentioning

confidence: 99%

Monocular vision SLAM for indoor aerial vehicles

Çelik

Chung

Clausman

et al. 2009

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-This paper presents a novel indoor navigation and ranging strategy by using a monocular camera. The proposed algorithms are integrated with simultaneous localization and mapping (SLAM) with a focus on indoor aerial vehicle applications. We experimentally validate the proposed algorithms by using a fully self-contained micro aerial vehicle (MAV) with on-board image processing and SLAM capabilities. The range measurement strategy is inspired by the key adaptive mechanisms for depth perception and pattern recognition found in humans and intelligent animals. The navigation strategy assumes an unknown, GPS-denied environment, which is representable via corner-like feature points and straight architectural lines. Experimental results show that the system is only limited by the capabilities of the camera and the availability of good corners.

show abstract

Vision-based localization algorithm based on landmark matching, triangulation, reconstruction, and comparison

Cited by 68 publications

References 18 publications

Learning visibility of landmarks for vision-based localization

Learning visibility of landmarks for vision-based localization

Rfid Based Collision-Free Robot Docking in Cluttered Environment

Monocular vision SLAM for indoor aerial vehicles

Contact Info

Product

Resources

About