This study aims at developing a practical stereo camera that is suitable for applications such as surveillance, in which detection of anomalies or measurement of moving people are required. In such surveillance cases, targets to measure usually move. In this paper, "Subtraction stereo" is proposed that focuses on motion information to increase the robustness of the stereo matching. It realizes robust measurement of range images by detecting moving regions with each camera and then applying stereo matching for the detected moving regions. Measurement of three-dimensional position, height and width of a target object using the subtraction stereo is discussed. The basic algorithm is implemented on a commercially available stereo camera, and the effectiveness of the subtraction stereo is verified by several experiments using the stereo camera.

Abstract-In this paper, detection of pedestrians using "subtraction stereo" is discussed. Subtraction stereo is a stereo vision method that focuses on the movement of objects to make a stereo camera robust and produces range images for moving regions. Features of pedestrians such as 3D position, height and width are obtained from range images obtained by subtraction stereo. Then a simple method to remove shadows is proposed. The basic algorithm of the subtraction stereo is implemented on a commercially available stereo camera, and the effectiveness of the method to detect pedestrians with removal of shadows is verified by experiments using the stereo camera.

The manner of holding a pen is distinctive among people. Therefore, pen holding style is useful for person authentication. In this paper, we propose a biometric person authentication method using features extracted from images of pen holding style. Images of the pen holding style are captured by a camera, and several features are extracted from the captured images. These features are compared with a reference dataset to calculate dissimilarity scores, and these scores are combined for verification using a three-layer perceptron. Preliminary experiments were performed by using a private database. The proposed system yielded an equal error rate (EER) of 2.6%.