In this paper, the visual tracking algorithm for a moving target is proposed for the biped robot of which camera movement is irregular. hexagonal matching algorithm is used to measure the changes of size, location, an...
详细信息
ISBN:
(纸本)9783037850046
In this paper, the visual tracking algorithm for a moving target is proposed for the biped robot of which camera movement is irregular. hexagonal matching algorithm is used to measure the changes of size, location, and rotation angle for a moving object from its image frame. For enhancing the efficiency of the tracking, we can adaptively adjust the starting point and the size of search area from the image information obtained. Finally, by using Affine Transform and Kalman Filter, the position estimation of the moving target is refined against the swing of the camera. Experiments with 20-DOF biped robot using mono vision sensor are implemented to prove the reliability of the proposed method.
A novel image synthesis method of an object at arbitrary viewpoint by using the 3-D geometric model and several camera images is proposed. Although the image-based rendering synthesizes the relatively accurate diffuse...
详细信息
ISBN:
(纸本)9781424418343
A novel image synthesis method of an object at arbitrary viewpoint by using the 3-D geometric model and several camera images is proposed. Although the image-based rendering synthesizes the relatively accurate diffuse reflection component from the camera images from different viewpoints, it can not synthesize the specular reflection component with sufficient accuracy as the movement of the specular reflection component as the changes in viewpoints are not taken into consideration. In order to overcome this problem, we propose a method for synthesizing the arbitrary viewpoint images with the use of the displacement vectors of the specular reflection components. The displacement vectors are estimated by a hexagonal matching algorithm based on the triangle mesh model which was modified for arbitrary shaped images. In the hexagonalmatching, the images synthesized from 3-D geometric model of a real object and camera images are used as reference image. The experiments show that the proposed method reconstructs the specular reflection components more accurately and also improves the coding performance compared to the conventional methods.
暂无评论