This paper proposes a method for the visual-based navigation of a mobile robot in indoor environments, using a single omni-directional (catadioptric) camera. The geometry of the catadioptric sensor and the method used to obtain a bird's eye (orthographic) view of the ground plane are presented. This representation significantly simplifies the so to navigation protiok by eliminating any perspective effects. The nature of each navigation task is taken into account when designing the required navigation skills and environmental representation. We propose two main navigation mo dalities: Topological Navigation and Visual Path Following. To po lok Navigatio is used fo traveling lo distances and do es no require knowledge of the exact position of the robot but rather, a qualitative position of the took map. The navigation process combines appearance based methods and visual servorv up oso environmental features. Visual Path Following is required for local, very precise navigation fo e.g.do o traversal,do cking. The robot is contro to fo w a pre-specified p...

We describe a method for visual based robot navigation with a single omni-directional (catadioptric) camera. We show how omni-directional images can be used to generate the representations needed for two main navigation modalities: Topological Navigation and Visual Path Following. Topological Navigation relies on the robot’s qualitative global position, estimated from a set of omni-directional images obtained during a training stage (compressed using PCA). To deal with illumination changes, an eigenspace approximation to the Hausdorff measure is exploited. We present a method to transform omni-directional images to Bird’s Eye Views that correspond to scaled orthographic views of the ground plane. These images are used to locally control the orientation of the robot, through visual servoing. Visual Path Following is used to accurately control the robot along a prescribed trajectory, by using bird’s eye views to track landmarks on the ground plane. Due to the simplified geometry of these images, the robot’s pose can be estimated easily and used for accurate trajectory following. Omni-directional images facilitate landmark based navigation, since landmarks remain visible in all images, as opposed to a small field-of-view standard camera. Also, omni-directional images provide the means of having adequate representations to support both accurate or qualitative navigation. Results are described in the paper. 1.

Abstract not found

Omnidirectional vision sensors, which have been proposed in 1970, are recently studied in Computer Vision and Multimedia research. This paper discusses features of previously developed omnidirectional vision sensors and their problems in the design. Further, this paper proposes designs of low-cost and compact omnidirectional vision sensors and their new applications. The author considers utilization of omnidirectional vision sensor will be a key issue in Computer Vision and Multimedia applications. Keywords: Omnidirectional vision sensor, Omnidirectional Image, Visual surveillance, Multimedia, Robot vision. 1 Introduction Physical agents living in complex environments, such as humans and animals, need two types of visual sensing abilities. One is to gaze particular objects with a precise but small retina, the other is to look around the environment with a wide but coarse retina. Both visual sensing mechanisms are required for realizing robust and flexible visual behaviors. Especiall...

{ matjaz.jogan,alesl} @ frimi-lj.si The results of recent studies on the possibility of spa-tial localization from panoramic images have shown good prospects for view-based methods. The major advantages of these methods are a wide field-of-view, capability of mod-elling cluttered environments, and flexibility in the learning phase. The redundant information captured in similar views is efficiently handled by the eigenspace approach. However, the standard approaches are sensitive to noise and occlu-sion. In this paper, we present a method of view-based lo-calization in a robust framework that solves these problems to a large degree. Experimental results on a large set of real panoramic images demonstrate the effectiveness of the approach and the level of achieved robustness. 1. Introduction and

Abstract. Appearance-based modeling of objects and scenes using PCA has been successfully applied in many recognition tasks. Robust methods which have made the recognition stage less susceptible to outliers, occlusions, and varying illumination have further enlarged the domain of applicability. However, much less research has been done in achieving robustness in the learning stage. In this paper, we propose a novel robust PCA method for obtaining a consistent subspace representation in the presence of outlying pixels in the training images. The method is based on the EM algorithm for estimation of principal subspaces in the presence of missing data. By treating the outlying points as missing pixels, we arrive at a robust PCA representation. We demonstrate experimentally that the proposed method is efficient. In addition, we apply the method to a set of panoramic images to build a representation that enables surveillance and view-based mobile robot localization. 1

Under in-plane rotations of a panoramic camera, the information content of a panoramic image is, in general, preserved. However, different representations that can be derived have important implications on further processing, e.g. for appearance-based localization. We discuss several approaches based on different representations that have been proposed and evaluate them from different points-ofview, in particular, we argue that most of them are not suitable for robust localization under partially occluded views. In this paper we propose a representation---eigenspace of spinning-images---which enables a straightforward application of the robust estimation of eigenimage coefficients which is directly related to the localization.

This paper proposes a new technique for vision-based robot navigation. The basic framework is to localise the robot by comparing images taken at its current location with reference images stored in its memory. In this work, the only sensor mounted on the robot is an omnidirectional camera. The Fourier components of the omnidirectional image provide a signature for the views acquired by the robot and can be used to simplify the solution to the robot navigation problem. The proposed system can calculate the robot position with variable accuracy ("hierarchical localisation ") saving computational time when the robot does not need a precise localisation (e.g. when it is travelling through a clear space). In addition, the system is able to self-organise its visual memory of the environment. The self-organisation of visual memory is essential to realise a fully autonomous robot that is able to navigate in an unexplored environment. Experimental evidence of the robustness of this system is given in unmodified o#ce environments.

Abstract. This paper addresses the problem of autonomous mobile robot navigation in a simple indoor environment. We present a system which combines the paradigm of visual servoing with appearance based methods. The only sensory information available to the robot comes from an omni-directional vision camera. The geometry of our system, which uses a spherical mirror is presented. Our algorithm relies on a sequence of images obtained a priori. Since this image set is relatively large, it is compressed using Principal Component Analysis (PCA), thus producing alow dimensional eigenspace. This eigenspace maps the environment in a topological sense. Hence, from this the robot can determine its global topological position along a given path. In order to control local pose, visual servoing is applied to ground plane dewarped images. The method of obtaining these images and the closed-loop control mechanism, which is reliant upon them, is detailed. Preliminary results from both simulation and real world experiments are presented, as is a method of extending the system. 1

Appearance-based visual learning and recognition techniques that are based on models derived from a training set of 2D images are being widely used in computer vision applications. In robotics, they have received most attention in visual servoing and navigation. In this paper we discuss a framework for visual self-localization of mobile robots using a parametric model built from panoramic snapshots of the environment. In particular, we propose solutions to the problems related to robustness against occlusions and invariance to the rotation of the sensor. Our principal contribution is an “eigenspace of spinning-images”, i.e., a model of the environment which successfully exploits some of the specific properties of panoramic images in order to efficiently calculate the optimal subspace in terms of principal components analysis (PCA) of a set of training snapshots without actually decomposing the covariance matrix. By integrating a robust recover-and-select algorithm for the computation of image parameters we achieve reliable localization even in the case when the input images are partly occluded or noisy. In this way, the robot is capable of localizing itself in realistic environments.