Catadioptric Omnidirectional Camera Research Articles

LOCALIZATION AND MAPPING USING A NON-CENTRAL CATADIOPTRIC CAMERA SYSTEM

Abstract. This work details the development of an indoor navigation and mapping system using a non-central catadioptric omnidirectional camera and its implementation for mobile applications. Omnidirectional catadioptric cameras find their use in navigation and mapping of robotic platforms, owing to their wide field of view. Having a wider field of view, or rather a potential 360° field of view, allows the system to “see and move” more freely in the navigation space. A catadioptric camera system is a low cost system which consists of a mirror and a camera. Any perspective camera can be used. A platform was constructed in order to combine the mirror and a camera to build a catadioptric system. A calibration method was developed in order to obtain the relative position and orientation between the two components so that they can be considered as one monolithic system. The mathematical model for localizing the system was determined using conditions based on the reflective properties of the mirror. The obtained platform positions were then used to map the environment using epipolar geometry. Experiments were performed to test the mathematical models and the achieved location and mapping accuracies of the system. An iterative process of positioning and mapping was applied to determine object coordinates of an indoor environment while navigating the mobile platform. Camera localization and 3D coordinates of object points obtained decimetre level accuracies.

A direct approach for object detection with catadioptric omnidirectional cameras

In this paper, we present an omnidirectional vision-based method for object detection. We first adopt the conventional camera approach that uses sliding windows and histogram of oriented gradients (HOG) features. Then, we describe how the feature extraction step of the conventional approach should be modified for a theoretically correct and effective use in omnidirectional cameras. Main steps are modification of gradient magnitudes using Riemannian metric and conversion of gradient orientations to form an omnidirectional sliding window. In this way, we perform object detection directly on the omnidirectional images without converting them to panoramic or perspective images. Our experiments, with synthetic and real images, compare the proposed approach with regular (unmodified) HOG computation on both omnidirectional and panoramic images. Results show that the proposed approach should be preferred.

A Survey of Catadioptric Omnidirectional Camera Calibration

For dozen years, computer vision becomes more popular, in which omnidirectional camera has a larger field of view and widely been used in many fields, such as: robot navigation, visual surveillance, virtual reality, three-dimensional reconstruction, and so on. Camera calibration is an essential step to obtain three- dimensional geometric information from a two- dimensional image. Meanwhile, the omnidirectional camera image has catadioptric distortion, which need to be corrected in many applications, thus the study of such camera calibration method has important theoretical significance and practical applications. This paper firstly introduces the research status of catadioptric omnidirectional imaging system; then the image formation process of catadioptric omnidirectional imaging system has been given; finally a simple classification of omnidirectional imaging method is given, and we discussed the advantages and disadvantages of these methods.

THE SPATIAL SEMANTIC HIERARCHY IMPLEMENTED WITH AN OMNIDIRECTIONAL VISION SYSTEM

In this article, we propose a new approach to the map building task: the implementation of the Spatial Semantic Hierarchy (SSH), proposed by B. Kuipers, on a real robot fitted with an omnidirectional camera. The original Kuiper's formulation of the SSH was slightly modified, in order to manage in a more efficient way the knowledge the real robot collects while moving in the environment. The sensory data experienced by the robot are transformed by the different levels of the SSH in order to obtain a compact representation of the environment. This knowledge is stored in the form of a topological map and, eventually, of a metrical map. The aim of this article is to show that a catadioptric omnidirectional camera is a good sensor for the SSH and nicely couples with several elements of the SSH. The panoramic view and rotational invariance of our omnidirectional camera makes the identification and labelling of places a simple matter. A deeper insight is that the tracking and identification of events on an omnidirectional image such as occlusions and alignments can be used for the segmentation of continuous sensory image data into the discrete topological and metric elements of a map. The proposed combination of the SSH and omnidirectional vision provides a powerful general framework for robot maping and offers new insights into the concept of “place.” Some preliminary experiments performed with a real robot in an unmodified office environment are presented.

Tracking head positions in three-dimensional space by using a single omnidirectional camera

We propose a novel method using a single catadioptric omnidirectional camera to track 3-D head positions in nonintrusive biometric systems. Existing methods have not been able to deal with cases in which the ground plane is nonorthogonal to the optical axis of the camera. To overcome this problem, our proposed method presents the following three improvements: (i) By using 1-D tracking of the feet and head positions combined with a circular constraint in images instead of conventional 2-D tracking methods, the accuracy and computational efficiency of the tracking process is significantly improved, (ii) based on the detected 2-D head position in images with the precalibration information of the camera, the 3-D head positions can be obtained, and (iii) the 3-D head positions can be obtained without having the optical axis of the camera orthogonal to the ground plane. This makes the proposed method feasible in practical environments that use omnidirectional camera systems. Experimental results showed that the proposed method was able to track 3-D head positions at real-time speed.

Analytic image unwarping by a systematic calibration method for omni-directional cameras with hyperbolic-shaped mirrors

Unwarping an omni-directional image into a perspective-view one is easy for a single-viewpoint (SVP) designed catadioptric omni-directional camera. But misalignment between the components (such as the mirror and the lens) of this kind of camera creates multiple viewpoints and distorts the unwarped image if the SVP constraint is assumed. The SVP constraint is relaxed in this study and a systematic method is proposed to derive a set of new and general analytic equations for unwarping images taken from an omni-directional camera with a hyperbolic-shaped mirror (called a hypercatadioptric camera). The derivation is made possible by careful investigation on the system configuration and precise calibration of involved system parameters. As a verification of the correctness of the derived equations, some of the system parameters are adjusted to fit the SVP constraint, and unwarped images using the resulting simplified camera model are shown to be of no difference from those obtained by a method based on the SVP model. The generality of the proposed method so has extended the image-unwarping capability of the existing methods for the hypercatadioptric camera to tolerate lens/mirror assembly imprecision, which is difficult to overcome in most real applications. Some experimental results of image unwarping are also included to show the effectiveness of the proposed method.

Incorporating lens distortion into the design of undistorted catadioptric omnidirectional cameras

An improved approach for design of the catadioptric omnidirectional camera with horizontal scene undistorted imaging is described. In the proposed approach, the influence of the lens distortion on the imaging quality of the omnidirectional camera is taken into account. We establish a radial distortion model for an image pickup lens and retain some opposite distortion in the mirror to correct the distortion existing in the image pickup lens. A horizontal scene undistorted catadioptric omnidirectional camera is designed with an off-the-shelf TV short focus lens using our approach; the numerical simulation shows that the distortion introduced by the imaging lens is eliminated effectively.