We present a two-step camera calibration process based on linear least squares formulations. We show how to apply this process to build an integrated modeling environment, in which a scene is modeled by having the user specify, on a given image, a set of reference points (used for camera calibration) and object points (used for positioning the objects in the scene). Once this has been done, syn...

This paper presents a method for automatically adjusting the zoom setting of an active camera undergoing pure rotation so that it maintains the ratio of projected areas in the scene and image around the fixation point. We restrict discussion to planar objects, and exploit the properties of the two different interimage transformations which are observed — the infinity homography describing corre...

This paper proposes a novel method for robustly recovering the camera geometry of an uncalibrated image sequence taken under circular motion. Under circular motion, all the camera centers lie on a circle and the mapping from the plane containing this circle to the horizon line observed in the image can be modeled as a 1D projection. A 2 2 homography is introduced in this paper to relate the pro...

Object recognition accuracy can be improved when information from multiple views is integrated, but information in each view can often be highly redundant. We consider the problem of distributed object recognition or indexing from multiple cameras, where the computational power available at each camera sensor is limited and communication between sensors is prohibitively expensive. In this scena...

It can be argued that an ideal teleconferencing system would offer a sense of presence comparable to that afforded by real face-to-face meetings. In contrast, traditional desktop videoconferencing loses essential socially important phenomena such as true perspective views, live facial expressions and tacit body language. This paper reports a prototype concept demonstrator under development at B...

It is shown that there always exists a two-way ambiguity for 2D projective reconstruction from three uncalibrated 1D views independent of the number of point correspondences. It is also shown that the two distinct projective reconstructions are exactly related by a quadratic transformation with the three camera centers as the fundamental points. The unique reconstruction exists only for the cas...

This paper describes our new multiple-camera architecture for real-time video analysis. This architecture uses an array of relatively inexpensive cameras to gather images in order to provide high resolution at low cost. The system also uses a hierarchy of cameras, including both wide-angle and telephoto views. Wide-angle cameras are responsible for camera coordination while telephoto cameras ar...

Matching pedestrians across disjoint camera views, known as person re-identification (re-id), is a challenging problem that is of importance to visual recognition and surveillance. Most existing methods exploit local regions within spatial manipulation to perform matching in local correspondence. However, they essentially extract fixed representations from pre-divided regions for each image and...

In this paper 3D motion estimation using an active stereo vision paradigm is addressed. The objective is to measure camera rotations of a stereo head to estimate the 3D motion of a single moving object in a scene. The method uses stereo camera fixation of junctions. The vertex of a junction is selected as the fixation point. Vertex position and junction orientations are recovered in the fixated...

This paper proposes human tracking and recognition method in a camera network. Human matching in a multi-camera surveillance system is a fundamental issue for increasing the accuracy of recognition in multiple views of cameras. In camera network, videos have different characteristics such as pose, scale and illumination. Therefore it is necessary to use a hybrid scheme of scale invariant featur...