Learn More
We consider the problem of metrically reconstructing a scene viewed by a m o ving stereo head. The head comprises two cameras with coplanar optical axes arranged on a lateral rig, each camera being free to vary its angle of vergence. Under various constraints, we derive n o vel explicit forms for the epipolar equation, and show that a static stereo head(More)
If suuciently many pairs of corresponding points in a stereo image pair are available to construct the associated fundamental matrix, then it has been shown that 5 relative orientation parameters and 2 focal lengths can be recovered from this fundamental matrix. This paper presents a new and essentially linear algorithm for recovering focal lengths.(More)
—In this paper we propose a novel appearance descriptor for 3D human pose estimation from monocular images using a learning-based technique. Our image-descriptor is based on the intermediate local appearance descriptors that we design to encapsulate local appearance context and to be resilient to noise. We encode the image by the histogram of such local(More)
Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from depth images which are viewpoint dependent. In contrast, we directly process pointclouds for cross-view action recognition from unknown and unseen views. We propose the histogram of oriented principal components (HOPC) descriptor that is(More)
3D rotations arise in many computer vision, computer graphics, and robotics problems and evaluation of the distance between two 3D rotations is often an essential task. This paper presents a detailed analysis of six functions for measuring distance between 3D rotations that have been proposed in the literature. Based on the well-developed theory behind 3D(More)
—This paper presents an evaluation of the SIFT (Scale Invariant Feature Transform), Colour SIFT, and SURF (Speeded Up Robust Feature) descriptors on very low resolution images. The performance of the three descriptors are compared against each other on the precision and recall measures using ground truth correct matching data. Our experimental results show(More)
We propose an algorithm which combines the discrimi-native information from depth images as well as from 3D joint positions to achieve high action recognition accuracy. To avoid the suppression of subtle discriminative information and also to handle local occlusions, we compute a vector of many independent local features. Each feature encodes spatiotemporal(More)