No abstract

Abstract:We aim for detection and recognition of planar objects in natural outdoor scenes under varying illumination conditions. To achieve this, we propose Relative Color Polygons (RCPs) using component colors of objects for color matching. They can be defined on many color spaces, and it is found that a 2D color space (XY space) is the optimal color space for our relative color method compared with other color spaces. To evaluate the invariance to illumination changes for object recognition, experiments have been carried out using 500 outdoor scene images. By using the proposed model, the color matching rate of the input images with the standard one was 95%. This framework is potentially applicable to image retrieval, image segmentation, image recognition, and so on.

No abstract

Abstract:We study geometrical properties between 2-D image plane and 3-D error space under affine reconstruction. The purpose of our system is to contribute to more accurate 3-D reconstruction by analyzing geometrically 2-D to 3-D relationship. In situation for no missing feature points and no noise in the 2-D observation matrix, the accurate solution is known to be provided by Singular Value Decomposition. However, several feature points of the matrix have not been observed because of occlusions and low image resolution, and so on. In this case, there is no simple solution. To obtain accurate 3-D reconstruction by recovering missing feature points, we propose the analytic approach which can handle the error orientation and distance of missing feature points by the geometrical properties.