This paper suggests a new portable posture input system which consists of a stereo vision system, a color marked puppet, and a laptop computer. Using the puppet, we can intuitively input any posture which we want to represent. The puppet posture is recognized by the stereo vision. First, the color mark of each puppet joint is obtained and segmented. In this case, the normalized color technique is employed for robust color mark extraction. Then, the 3D positions of the segmented color marks are calculated by the epipolar geometry method. Using the obtained 3D positions, all joint angles of the puppet are represented as a quaternion. Therefore, the obtained joint quaternions determine the resultant posture of the human being model. Finally, the experimental results show the effectiveness and feasibility of the suggested posture input system.

This paper introduces a navigation method for a teleoperated mobile agent (or robot) moving in an unstructured environment that includes unknown obstacles and uneven terrain, based on a guided-navigation algorithm (GNA) and a rollover-prevention algorithm (RPA). Although the mobile agent is primarily driven by an operator at a remote site, it reacts autonomously for avoiding collision with obstacles and for preventing rollover when it suspects/detects possible collision or rollover. The autonomous reactive motion is normally unexpected, thus there exists the inconsistency between the intended motion and the controlled motion of the agent from the operator. A force-reflection technique utilizing a force-feedback joystick is developed to manipulate this inconsistency. To verify the feasibility and effectiveness of the proposed navigation method, experiments with the Robot for Hazardous Application-Double Tracks (ROBHAZ-DT) (actual mobile agent) are successfully carried out.

This paper presents an efficient person tracking algorithm for a vision-based mobile robot using two independently moving cameras each of which is mounted on its own pan/tilt unit. Without calibrating these cameras, the goal of our proposed method is to estimate the distance to a target appearing in the image sequences captured by the cameras. The main contributions of our approach include: 1) establishing the correspondence between the control inputs to the pan/tilt units and the pixel displacement in the image plane without using the intrinsic parameters of the cameras; and 2) derivation of the distance information from the correspondence between the centers of masses of the segmented color-blobs from the left and the right images without stereo camera calibration. Our proposed approach has been successfully tested on a mobile robot for the task of person following in real environments.

This paper presents a robust model-based visual tracking algorithm that can give accurate 3D pose of a rigid object. Our tracking algorithm uses an incremental pose update scheme in a prediction-verification framework. Extended Kalman filter is used to update the pose of a target incrementally to minimize the error between the expected map of the target model and the corresponding gradient edge in the image space. The main contributions of this paper include: 1) A novel approach to how we use the two extremities of straight-lines as features. By taking into account the measurement uncertainties associated with the locations of the extracted extremities of the straight-line, our approach can compare correctly two straight-lines of different lengths. 2) Our use of a test of mean criterion for initiating backtracking and our use of a variable threshold on the output of this criterion that makes nil-matching more effective. We have tested our tracking algorithm with image sequences containing highly cluttered backgrounds. The system successfully tracks objects even when they are highly occluded.

This paper describes a control method of mobile robots for avoiding slip and turnover in sloped terrain. An inexpensive vision/gyro sensor module that consists of a laser line generator, a USB camera and a gyro sensor, is suggested for obtaining terrain information nearby the robot system. Using information of the terrain and the robot state, the maximum limit of the forward velocity of the robot is defined for avoiding slip and turnover. Simultaneously the maximum value of the robot velocity is reflected to an operator in the form of a reflective force. Consequently the operator can recognize the maximum velocity of the robot determined by terrain information and the robot state. In this point of view, the inconsistency between the robot state and the user's command can be compensated by the reflective force. The experimental results show the effectiveness of the suggested method.

One of the most difficult aspects of dealing with illumination effects in computer vision is accounting for specularity in the images of real objects. The specular regions in an image are often saturated - which creates problem for all image processing algorithms that use decision thresholds. Such algorithms include those for edge detection, region segmentation, etc. Detecting specularity and whenever possible compensating for it are obviously advantageous. Along these lines, this paper represents a new specularity detection and compensation method which is based on the notion of truncated least-squares approximation to the function that maps the color distribution between two images of an object under different illumination conditions. We also present a protocol for the evaluation of the current method for specularity detection. Our protocol as currently formulated uses human subjects to grade the specularity detection method.