Orientation (computer vision)

About: Orientation (computer vision) is a research topic. Over the lifetime, 17196 publications have been published within this topic receiving 358181 citations.

Method of stereoscopic 3d image capture using a mobile device, cradle or dongle

Abstract: A system, apparatus, method, and computer-readable media are provided for the capture of stereoscopic three dimensional (3D) images using multiple cameras or a single camera manipulated to deduce stereoscopic data. According to one method, a dongle or cradle is added to a mobile phone or other device to capture stereoscopic images. According to another method, the images are captured from cameras with oblique orientation such that the images may need to be rotated, cropped, or both to determine the appropriate stereoscopic 3D regions of interest. According to another method, a single camera is manipulated such that stereoscopic 3D information is deduced.

Consensus photometric stereo

Abstract: This paper describes a photometric stereo method that works with a wide range of surface reflectances. Unlike previous approaches that assume simple parametric models such as Lambertian reflectance, the only assumption that we make is that the reflectance has three properties; monotonicity, visibility, and isotropy with respect to the cosine of light direction and surface orientation. In fact, these properties are observed in many non-Lambertian diffuse reflectances. We also show that the monotonicity and isotropy properties hold specular lobes with respect to the cosine of the surface orientation and the bisector between the light direction and view direction. Each of these three properties independently gives a possible solution space of the surface orientation. By taking the intersection of the solution spaces, our method determines the surface orientation in a consensus manner. Our method naturally avoids the need for radiometrically calibrating cameras because the radiometric response function preserves these three properties. The effectiveness of the proposed method is demonstrated using various simulated and real-world scenes that contain a variety of diffuse and specular surfaces.

Learning 3-D object orientation from images

Abstract: We propose a learning algorithm for estimating the 3-D orientation of objects. Orientation learning is a difficult problem because the space of orientations is non-Euclidean, and in some cases (such as quaternions) the representation is ambiguous, in that multiple representations exist for the same physical orientation. Learning is further complicated by the fact that most man-made objects exhibit symmetry, so that there are multiple “correct” orientations. In this paper, we propose a new representation for orientations—and a class of learning and inference algorithms using this representation—that allows us to learn orientations for symmetric or asymmetric objects as a function of a single image. We extensively evaluate our algorithm for learning orientations of objects from six categories.

Image rotation correction for video or photographic equipment

Abstract: Image recording apparatus such as a camera (2) stores data (8) representing still or moving image data on a data carrier (12). A rotation sensor (14) measures the angle of orientation of the camera. The stored data is based both on the image data and the output angle data to allow the captured image to be rotated for display to have the true horizontal displayed as horizontal.