Stereo vision has numerous applications in robotics, graphics, inspection and other areas. A prime application, one which has driven work on stereo in our laboratory, is teleconferencing in which the use of a stereo webcam already makes possible various transformations of the video stream. These include digital camera control, insertion of virtual objects, background substitution, and eye-gaze ...

We present a stereo algorithm to recursively compute a boundary-level structural description of a static scene, from a sequence of dynamic stereo images. This algorithm is based on connected line segments as the basic match primitive, which yields a description composed primarily of boundaries of objects in the scene. The algorithm is integrated into a dynamic stereo vision system to compute an...

Stereo Vision is a key technology for modern Driver Assistance Systems aiming at increased traffic safety and driving comfort. The opportunity to directly measure the depth of pixels and objects is crucial for understanding the current traffic situation and to detect risky situations. Inspired by results obtained in photogrammetry, we developed a stereo vision system that has recently been intr...

A real-time object tracking and collision avoidance method for mobile robot navigation is presented using stereo vision and a laser sensor. Stereo vision is used to identify the target while laser based range measurements are utilized to avoid collision with surrounding objects. The target is tracked by its predetermined or dynamically defined color. Experimental results in indoor environments ...

We describe a novel quadrotor micro air vehicle (MAV) system that is designed to use computer vision algorithms within the flight control loop. One main contribution is the integration of a powerful onboard computer which is a necessity for running state-of-the-art computer vision algorithms with real-time constraints. The system also features IMU-Vision synchronization by hardware time stampin...

In extracting three-dimensional positional information from images, both static stereo processing and monocular structure-from-motion processing possess shortcomings for a general purpose vision system. A solution to these problems is to use stereo structurefrom-motion processing. This paper addresses the problems of integrating stereo and structure-frommotion data to determine the camera ego-m...

The 3D reconstruction of image and video scenes by stereo analysis is an important topic in computer vision research. In this talk, we first present some principles of stereo algorithms and recent developments. We then demonstrate two applications of stereo reconstruction for the analysis and visualization of human movement: (a) We employ depth maps derived from sport scenes for novel view synt...

Effective object motion estimation is significant to improve the performance of soccer robots in RoboCup Middle Size League. In this paper, a hybrid vision system is constructed by combining omnidirectional vision and stereo vision for ball recognition and motion estimation in three-dimensional (3D) space. When the ball is located on the ground field, a novel algorithm based on RANSAC and Kalma...

Camera calibration is an important step in the initialisation of many stereo vision systems. The accuracy of camera parameters has a marked effect on the data obtained from a stereo vision system. In this paper, we describe some difficulties met in an attempt to build a calibration system based on Tsai’s Algorithm [Tsai, 1987]. We also offer some methods to overcome these problems. An overview ...