Localization for Mobile Robots using Panoramic Vision, Local Features and Particle Filter

Andreasson, Henrik; Treptow, André; Duckett, Tom

doi:10.1109/robot.2005.1570627

Cited by 89 publications

(74 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This indicates that the method can cope with 3-d motions to a certain extent, and we would expect a graceful degradation in map accuracy as the roughness of the terrain increases. The representation should still be useful for self-localization using 2-d odometry and image similarity, e.g., using the global localization method in [18]. In extreme cases, of course, it is possible that the method would create inconsistent maps, and a 3-d representation should be considered.…”

Section: Discussionmentioning

confidence: 99%

Mini-SLAM: Minimalistic Visual SLAM in Large-Scale Environments Based on a New Interpretation of Image Similarity

Andreasson

Duckett

Lilienthal

2007

Proceedings 2007 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-This paper presents a vision-based approach to SLAM in large-scale environments with minimal sensing and computational requirements. The approach is based on a graphical representation of robot poses and links between the poses. Links between the robot poses are established based on odomety and image similarity, then a relaxation algorithm is used to generate a globally consistent map. To estimate the covariance matrix for links obtained from the vision sensor, a novel method is introduced based on the relative similarity of neighbouring images, without requiring distances to image features or multiple view geometry. Indoor and outdoor experiments demonstrate that the approach scales well to large-scale environments, producing topologically correct and geometrically accurate maps at minimal computational cost. Mini-SLAM was found to produce consistent maps in an unstructured, large-scale environment (the total path length was 1.4 km) containing indoor and outdoor passages. I. INTRODUCTIONThis paper presents a new approach to the problem of simultaneous localization and mapping (SLAM). The suggested method is called "Mini-SLAM" since it is minimalistic in several ways. On the hardware side, it solely relies on odometry and an omnidirectional camera. Using a camera as the external source of information for the SLAM algorithm provides a much cheaper solution compared to state-of-theart 2D and 3D laser scanners with a typically even longer range. It is further known that vision can enable solutions in highly cluttered environments where laser range scanner based SLAM algorithms fail [1]. In this paper, the readings from a laser scanner are used to demonstrate the consistency of the created maps. Please note, however, that the laser scanner is only utilised for visualisation and is not used in the visual SLAM algorithm.Apart from the frugal hardware requirements, the method is also minimalistic in its computational demands. Map estimation is performed online by a linear time SLAM algorithm that operates on an efficient graph representation. The main difference to other vision-based SLAM approaches is that there is no estimate of the positions of a set of landmarks involved, enabling the algorithm to scale up better with the size of the environment. Instead, a measure of image similarity is used to estimate the pose difference in between corresponding images and the uncertainty of this estimate. Given these "visual relations" and "odometry relations"

show abstract

Section: Discussionmentioning

confidence: 99%

Mini-SLAM: Minimalistic Visual SLAM in Large-Scale Environments Based on a New Interpretation of Image Similarity

Andreasson

Duckett

Lilienthal

2007

Proceedings 2007 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

show abstract

“…Vision-based odometry or localization algorithms are usually evaluated using either front-facing cameras [1], [11], [16], [19] or cameras pointed to the side [7], [20], [21] and using average focal length lenses. Some researchers have proposed using panoramic [3], [18] or omni-directional imagery [15], which could potentially improve localization by using a much wider field of view (FOV). However, our analysis shows that a wider FOV does not necessarily improve localization accuracy.…”

Section: Related Workmentioning

confidence: 99%

Understanding how camera configuration and environmental conditions affect appearance-based localization

Bansal

Badino

Huber

2014

2014 IEEE Intelligent Vehicles Symposium Proceedings

View full text Add to dashboard Cite

Abstract-Localization is a central problem for intelligent vehicles. Visual localization can supplement or replace GPSbased localization approaches in situations where GPS is unavailable or inaccurate. Although visual localization has been demonstrated in a variety of algorithms and systems, the problem of how to best configure such a system remains largely an open question. Design choices, such as "where should the camera be placed?" and "how should it be oriented?" can have substantial effect on the cost and robustness of a fielded intelligent vehicle. This paper analyzes how different sensor configuration parameters and environmental conditions affect visual localization performance with the goal of understanding what causes certain configurations to perform better than others and providing general principles for configuring systems for visual localization. We ground the investigation using extensive field testing of a visual localization algorithm, and the data sets used for the analysis are made available for comparative evaluation.

show abstract

“…Two broad methods can be discerned -those that model local features [2] and distinctive parts of images [26], and those that extract global representations of images and learn from them [22][10] [3]. The latter is closer to this work and includes the CENTRISTbased VPC system [33], and Spatial Pyramid Matching [15].…”

Section: Related Workmentioning

confidence: 99%

PLISS: Detecting and Labeling Places Using Online Change-Point Detection

Ranganathan¹

2010

Robotics: Science and Systems VI

View full text Add to dashboard Cite

Abstract-We present PLISS (Place Labeling through Image Sequence Segmentation), a novel technique for place recognition and categorization from visual cues. PLISS operates on video or image streams and works by segmenting it into pieces corresponding to distinct places in the environment. An online Bayesian change-point detection framework that detects changes to model parameters is used to segment the image stream. Unlike current place recognition methods, in addition to using previously learned place models for labeling, PLISS can also detect and learn a previously unknown place or place category in an online manner. Moreover, since both the inferred boundaries of places (change-points) and the place labels are fully probabilistic, they can indicate when the inference is uncertain. New places and categories are detected using a systematic statistical hypothesis testing framework. We present extensive experiments on a large and difficult image dataset. We validate our claims by comparing results obtained using different types of features and by comparing results from PLISS against the state of the art.

show abstract

Localization for Mobile Robots using Panoramic Vision, Local Features and Particle Filter

Cited by 89 publications

References 13 publications

Mini-SLAM: Minimalistic Visual SLAM in Large-Scale Environments Based on a New Interpretation of Image Similarity

Mini-SLAM: Minimalistic Visual SLAM in Large-Scale Environments Based on a New Interpretation of Image Similarity

Understanding how camera configuration and environmental conditions affect appearance-based localization

PLISS: Detecting and Labeling Places Using Online Change-Point Detection

Contact Info

Product

Resources

About