Showing papers by "Gary Bradski published in 2000"

System and method for gesture recognition in three dimensions using stereo imaging and color vision

Abstract: A system and method for recognizing gestures. The method comprises obtaining image data and determining a hand pose estimation. A frontal view of a hand is then produced. The hand is then isolated the background. The resulting image is then classified as a type of gesture. In one embodiment, determining a hand pose estimation comprises performing background subtraction and computing a hand pose estimation based on an arm orientation determination. In another embodiment, a frontal view of a hand is then produced by performing perspective unwarping and scaling. The system that implements the method may be a personal computer with a stereo camera coupled thereto.

Motion segmentation and pose recognition with motion history gradients

Abstract: This paper uses a simple method for representing motion in successively layered silhouettes that directly encode system time termed the timed Motion History Image (tMHI). This representation can be used to both (a) determine the current pose of the object and to (b) segment and measure the motions induced by the object in a video scene. These segmented regions are not "motion blobs", but instead motion regions naturally connected to the moving parts of the object of interest. This method may be used as a very general gesture recognition "toolbox". We use it to recognize waving and overhead clapping motions to control a music synthesis program.

Intel's Computer Vision Library: applications in calibration, stereo segmentation, tracking, gesture, face and object recognition

Abstract: Intel's Microcomputer Research Lab has been developing a highly optimized Computer Vision Library (CVLib) that automatically detects processor type and loads the appropriate MMX/sup TM/ technology assembly tuned module for that processor. MMX optimized functions are from 2 to 8 times faster than optimized C functions. We will be demonstrating various algorithms supported by CVLib and handing out CDs containing the library.

Method and apparatus for determining points of interest on an image of a camera calibration object

Abstract: The present invention allows for the locations of points of interest in a calibration object in a calibration image for a digital camera to be identified automatically. The image is an array of pixels corresponding to the calibration object, which has a known reference pattern. In a preferred embodiment, the invention includes receiving an array of pixels produced by a camera, classifying each pixel of the image as light or dark, extracting contours from the image by identifying lines between light and dark pixels, comparing the extracted contours to the shapes of the known reference pattern, and identifying the shapes of the known reference pattern in the image using the extracted contours. Preferably, the image is a color image, and the color information in the pixels of the image are converted into gray scale values to render the image as a gray scale image before the pixels are classified. Classifying each pixel includes applying a brightness threshold to each pixel of the image to classify those pixels having a brightness greater than the threshold as light and those below the threshold as dark.

Stereo based gesture recognition invariant to 3D pose and lighting

Abstract: This paper describes a stereo-based approach for gesture recognition that works well under extreme lighting conditions and tolerates a large range of hand poses. The approach proposes a hybrid gesture representation that models the user's arm as a 3D line and uses images to represent the hand gestures. The algorithm finds the arm orientation and the hand location from the disparity data and uses this information to initialize a color based segmentation algorithm that cleanly separates the hand from the background. Finally, our approach uses the arm orientation to compute a frontal view of the hand through perspective unwarping producing easily recognizable hand gesture templates. The classification algorithm uses statistical moments of the binarized gesture templates to find the match. We achieve 96% recognition rates under varying lighting and 3D poses for a set of 6 gestures.