あらまし 本論文は,環境の全周囲情報を取得できるカメラシステム(全方位センサ)で得られた画像を用い てセンサの位置と姿勢をロバストに推定する新しい手法を提案する.本手法は,まず環境中のいくつかの参照点 において,全方位センサで得られた画像から全周囲エッジヒストグラムをあらかじめ計算しておく.センサの位 置・姿勢を推定する際,動的計画法 (DP)を 2 パス DPに拡張して現位置と参照点の全周囲エッジヒストグラム をマッチングし,各方位角におけるエッジのシフト量を求める.これらのシフト量は sin 曲線と同じ周期性をも ち,センサの回転はエッジの全体的なシフト量に,その移動方向は sin 曲線の 0 位相に対応する.本研究では, これらのエッジシフト量から全体のシフト量とその周期の 0 位相を独立に当てはめることによって,センサの移 動方向と回転角度を効率的に推定する.最後に,最も近い...

Industrial inspection robots, which are to move around a nuclear power plant and carry out inspection tasks, must follow a given route while observing static and dynamic features of the environment. The vision system for such a robot needs to execute efficiently and mutually the tasks that are necessary for carrying out inspection reliably and flexibly while safely moving, and the following att...

A novel pan-tilt mechanism has been developed to support high-perfonnance active vision research at the AND. The mechanism is unique in that it features parallel .actuation and cabledrive transmission technology. This paper describes its design ,and reports on the experimental evaluation of its perfonnance. Results show that the design concepts are sound, and lead to a practical and cost-effect...

This paper addresses the problem of determining which 3D shape is present, and more importantly, the dimensions of the shape in a scene. This is performed in an active vision system because it reduces the complexity of the problem through the use of gaze stabilisation, choice of foveation point and selective processing by adaptively processing regions of interest. In our case only a small numbe...

The working region of a camera providing visual feedback to guide manipulation tasks can be greatly extended if the camera can move in real-time. Proper camera motion depends on several different criteria, such as object motion, maximum manipulator tracking speed, manipulator configuration, camera depth-of-field, field-of-view, spatial resolution, occlusion avoidance, etc. In this paper, the co...

We present an algorithm to solve the sensor planning problem for a trinocular, active vision system. This algorithm uses an iterative optimization method to rst solve for the translation between the three cameras and then uses this result to solve for parameters such as pan, tilt angles of the cameras and zoom set-

We present a fully integrated active vision system for interpreting dynamic scenes. We argue that even if the ego-motion of the mobile vision system is known, a single view camera calibration cannot adequately support scene model acquisition and maintenance. It is shown that stable camera/grabber chain calibration can be achieved using a multi-view calibration process. With such calibration, a ...