Localization of 3D lines from single images using off-axis catadioptric cameras
نویسندگان
چکیده
The reconstruction of 3D scenes constituted by straight lines can find many applications both in Computer vision and in Mobile robotics. Most approaches to 3D reconstruction analyze several images, which need the determination of the correspondences between the used images. This paper studies the localization of straight lines in 3D space from single 2D images, acquired by a noncentral catadioptric camera. In general, using a noncentral camera, the viewing rays starting from the points of a straight line constitute a nonplanar surface: if this non-planar surface only contains a finite number of straight line, other than the viewing rays, then the straight line can be localized (up to a finite number of solutions). In a previous work we dealt with line localization using an axial-symmetric catadioptric camera. In this paper the axial-symmetry constraint is relaxed, since the camera is placed at a generic position relative to an axial-symmetric mirror. The geometrical conditions for line localization are derived for off-axis catadioptric cameras based on a conic mirror, and some preliminary experimental results are presented.
منابع مشابه
Omnidirectional Multiview Systems: calibration, features and 3D information
Omnidirectional cameras wide field of view (FOV) is a great advantage over the conventional systems. Their usage have increased among the computer vision and robotics communities in recent years. This type of cameras allow to include the whole scene in a single view. They have been used in such different areas as surveillance, tracking, visual navigation, localization and SLAM, structure from m...
متن کاملLine Localization From Single catadioptric Image
Indoor environments often contain several line segments. The 3D reconstruction of such environments can thus be reduced to the localization of lines in the 3D space. Multi-view reconstruction requires the solution of the correspondence problem. The use of a single image to localize space lines is attractive, since the correspondence problem can be avoided. However, using a central camera the li...
متن کاملRotation Estimation of a Complete Omnidirectional Camera using Line Features
Rotation estimation with cameras is important for flying robot navigation. Usually, it is performed using a single camera by keeping track of some strong features such as corners or lines within the environment and observing their motion. However, with a normal camera, the field of view is quite limited and this can lead to an error because information is obtained from a small section of the sc...
متن کاملDepth From Distortions
Traditionally, images distortions have been regarded as a flaw that needed to be corrected. Much effort has been focused on “undistortion” methods to remedy this shortcoming. However, we see distortions as encoding crucial information about scene structure. In this paper we describe how scene depth is encoded in the distortions of images acquired with non-single viewpoint cameras or by mosaic c...
متن کاملMotion Estimation for Hybrid Cameras Using Point and Line Feature Fusion
We present in this paper a structure-from-motion approach for single viewpoint cameras using point and line features. From the image sequence captured by any central projection cameras, the motion can be recovered by decoupling of orientation and displacement: rotation is estimated from vanishing points of parallel lines and translation is calculated from known rotation and point/line correspon...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2005