Abstract: Disclosed is a stereo matching method and apparatus based on a stereo vision, the method including acquiring a left image and a right image, identifying image data by applying a window to each of the acquired left image and right image, storing the image data in a line buffer, extracting a disparity from the image data stored in the line buffer, and generating a depth map based on the extracted disparity.

Abstract: Disclosed is a stereo matching method and apparatus based on a stereo vision, the method including acquiring a left image and a right image, identifying image data by applying a window to each of the acquired left image and right image, storing the image data in a line buffer, extracting a disparity from the image data stored in the line buffer, and generating a depth map based on the extracted disparity.

Abstract: Provided is a method of computing precise disparity using a stereo matching method based on developed census transform with an adaptive support weight method in area based stereo matching. The method includes a step of setting an adaptive support weight window centered on a specific point of a left image and setting adaptive support weight windows with the same size with respect to one point positioned within a maximum disparity prediction value about a specific point of the left image in a right image.

Abstract: Provided is a disparity correcting device which rapidly corrects disparity information generated on the basis of a left image and disparity information generated on the basis of a right image through a simple configuration, and a method thereof, in stereo vision which generates a 3-dimensional image using a left image and a right image captured from left and right cameras.

Abstract: Provided is a method of computing precise disparity using a stereo matching method based on developed census transform with an adaptive support weight method in area based stereo matching. The method includes a step of setting an adaptive support weight window centered on a specific point of a left image and setting adaptive support weight windows with the same size with respect to one point positioned within a maximum disparity prediction value about a specific point of the left image in a right image.

Abstract: Provided is a disparity correcting device which rapidly corrects disparity information generated on the basis of a left image and disparity information generated on the basis of a right image through a simple configuration, and a method thereof, in stereo vision which generates a 3-dimensional image using a left image and a right image captured from left and right cameras.

Abstract: A system for real-time stereo matching is provided, which provides improved stereo matching speed and rate by gradually optimizing a disparity range used in the stereo matching based on the stereo matching result of the previous frame image and thus reducing unnecessary matching computations.

Abstract: A method and apparatus for performing parallel box filtering in region based image processing is provided. The method of performing parallel box filtering in region based image processing includes selecting parallel pixel blocks having a size of M×N to be operated in parallel, selecting pixels included in a mask region having a size of K×L that is a parallel pixel operation region and a first region having a size of (M+K?1)×(N+L?1) that corresponds to overlapping masks of M*N, selecting pixels of a second region commonly included in the mask regions of M*N and storing the results of operation with respect to the pixels of the second region as repeated operation values, and operating block operation values with respect to the parallel pixel blocks using the repeated operation values.

Abstract: A method and apparatus for performing parallel box filtering in region based image processing is provided. The method of performing parallel box filtering in region based image processing includes selecting parallel pixel blocks having a size of M×N to be operated in parallel, selecting pixels included in a mask region having a size of K×L that is a parallel pixel operation region and a first region having a size of (M+K?1)×(N+L?1) that corresponds to overlapping masks of M*N, selecting pixels of a second region commonly included in the mask regions of M*N and storing the results of operation with respect to the pixels of the second region as repeated operation values, and operating block operation values with respect to the parallel pixel blocks using the repeated operation values.