Abstract: An image size changing section obtains a size changed image by changing the size of one of two original images captured by a pair of cameras. If an edge of an object has many oblique components, the edge is difficult to detect as a vertical edge but, when the image is horizontally reduced, an oblique edge becomes close to a vertical edge. For this reason, feature end points are extracted with reliability by a feature extracting section and, thereby, an object is recognized and the distance to the object is determined reliably.

Abstract: The present invention relates to a pattern-matching processing method based on left and right images of an object photographed in stereo. A left area and a right area are generated, each having a fixed pattern containing plural pixels extracted from the left and right images, respectively, and in the left area, a reference image is generated by calculating an interpolation pixel value to be used between two transversely adjacent pixels based on the average of the two pixel values, and by calculating an interpolation pixel value to be used between two vertically adjacent pixels based on the average of the plural pixel values surrounding the relating position. Similarly, in the right area, interpolation pixel values are calculated and a comparison image is generated. Then pattern matching is performed between the reference image and the comparison images generated sequentially by shifting the right original image pixel by pixel.

Abstract: An image size changing section obtains a size changed image by changing the size of one of two original images captured by a pair of cameras. If an edge of an object has many oblique components, the edge is difficult to detect as a vertical edge but, when the image is horizontally reduced, an oblique edge becomes close to a vertical edge. For this reason, feature end points are extracted with reliability by a feature extracting section and, thereby, an object is recognized and the distance to the object is determined reliably.

Abstract: An image size changing section obtains a size-changed image by changing the size of one of two original images captured by a pair of cameras. If an edge of an object has many oblique components, the edge is difficult to detect as a vertical edge but, when the image is horizontally reduced, an oblique edge becomes close to a vertical edge. For this reason, a feature end points are extracted with reliability by a feature extracting section and, thereby, an object is recognized and the distance to the object is determined reliably.

Abstract: The present invention relates to a pattern-matching processing method based on left and right images of an object photographed in stereo. A left area and a right area are generated, each having a fixed pattern containing plural pixels extracted from the left and right images, respectively, and in the left area, a reference image is generated by calculating an interpolation pixel value to be used between two transversely adjacent pixels based on the average of the two pixel values, and by calculating an interpolation pixel value to be used between two vertically adjacent pixels based on the average of the plural pixel values surrounding the relating position. Similarly, in the right area, interpolation pixel values are calculated and a comparison image is generated. Then pattern matching is performed between the reference image and the comparison images generated sequentially by shifting the right original image pixel by pixel.

Abstract: An image size changing section obtains a size-changed image by changing the size of one of two original images captured by a pair of cameras. If an edge of an object has many oblique components, the edge is difficult to detect as a vertical edge but, when the image is horizontally reduced, an oblique edge becomes close to a vertical edge. For this reason, a feature end points are extracted with reliability by a feature extracting section and, thereby, an object is recognized and the distance to the object is determined reliably.