This study is intended to quantitatively clarify the relationship between the motion characteristics behind the human motion in complicated motions like dancing and the subjective impressions of the observer. It examines the impression structures related to the motion of a determined body part of dancing and considers the motion characteristics giving a specific impression. To compare and consider the impression structures related to the motion of a body part, the authors made a principal component analysis, one of the multi-variable analytic methods, to check the arm and leg motions for any differences in the impression structure. Similarly, they considered any differences in the impression structures due to the experience knowledge of dance. Next, to consider any differences in the physical features that have effect on the impressions, they quantified the motion characteristics and used a heavy regression analysis to estimate the common motion characteristics that give the same impressions. In addition, they used the characteristics of the legs that are parts of the motion presumed to have the relationship with the impressions to reproduce the motion with CG for the consideration of these impressions. As a result, when the impressions of the arm and leg motions were compared, four impression evaluation axes of "like-dislike," "dynamic-static," "individual-monotonous," and "collected-wide" were extracted as the axes that evaluated the same impressions, but the impressions of "hard-soft" and "heavy-light" were extracted only from those of each arm or leg motion. When the evaluation axes of the impressions were compared between groups with differences in the knowledge of dance, five similar evaluation axes were extracted for each of them and there was no big difference in the impression structures themselves, but significant differences were found for the evaluation of impressions between the words used for the sensitivity evaluation in difference in knowledge. Attention was paid to the characteristics of the motion generating each impression to show the relationship between motion characteristics and subjective impressions.

The friendly communication can be more promoted between the human and computer if the function of gesture recognition is implemented to the computer system as the input interface along with the keyboards and mice. We propose a mouse-like function for estimating hand shape from input images with a monocular camera, with which a computer user feels no restraint or awkwardness. Our system involves conversion of sequential images from Cartesian coordinates to log-polar coordinates. Temporal and spatial subtractions and color information are used to extract the hand region. The origin of log-polar coordinates is chosen as the center of the acquired image, but once the hand has been extracted, the estimated centroid position of the hand region in the next frame, obtained from the current hand position and speed, is used as the origin to convert. Recognition of the hand shape is carried out by multiple regression analysis using higher order local autocorrelation features of log-polar coordinate space. Mouse-like functions are realized according to the hand shape and motion trajectory. Compared to conventional Cartesian coordinates, conversion to log-polar coordinates enables us to reduce image date and computation time, remove the variability by the scaling, and improve antinoise characteristics.

Pointing devices are essential components of graphical user interfaces, and the mouse in particular is widely used because of its intuitive and easy operation. Since it must be directly touched by the user, however, the mouse is restricted in the locations where it can be used. A pointing device consists of a pointing mechanism and a switching mechanism, so the use of a noncontact device to carry out these actions should remove the restriction concerning location. In this study, we investigate the construction of a pointing device that does not impart a feeling of restraint or awkwardness, which estimates the user’s hand shape and position from images captured by a monocular camera, a noncontact device. In this system, the captured image is transformed from a Cartesian coordinate system to a log-polar system to reduce image data and computational cost, and achieve real-time operation without using special hardware other than a regular camera. Higher order local autocorrelation features of the log-polar coordinate space were used to achieve robustness against background change and hand rotation. In addition to direct pointing, the ability to recognize gestures from the hand’s motion trajectory was incorporated to achieve more comfortable user-computer interaction. In experiments using a system consisting of a regular computer and digital video camera, tracking of the hand and estimation of symbolic signs from extracted frames was stable at a practical average speed of 30 ms per frame.

No abstract

No abstract