Kabushiki Kaisha Toshiba

Mitsubishi Denki Kabushiki Kaisha

Hoechst Japan Limited

Hiroshi Hattori

Kazunori Onoguchi

Nobuyuki Takeda

Hiroaki Nakai

Kenichi Ono

Kaoru Suzuki

Takashi Wada

Minoru Yagi

Mutsumi Watanabe

Tatsuro Nakamura

Kouichi Matsukawa

Hideki Ishihara

A pattern discriminating apparatus includes a setting unit configured to set at least one area in a three-dimensional space in a three-dimensional image data, a feature value calculating unit configured to calculate a pixel feature value from one pixel to another of the three-dimensional image data, a matrix calculating unit configured to (1) obtain at least one point on a three-dimensional coordinate in the area which is displaced in position from a focused point on the three-dimensional coordinate in the area by a specific mapping, and (2) calculate a co-occurrence matrix which expresses the frequency of occurrence of a combination of the pixel feature value of the focused point in the area and the pixel feature values of the mapped respective points, and a discriminating unit configured to discriminate whether or not an object to be detected is imaged in the area on the basis of the combination of the specific mapping and the co-occurrence matrix and a learning sample of the object to be detected which is learned in advance.

Pattern discriminating apparatus

A computer readable storage medium storing instructions of a computer program which when executed by a computer results in performance of steps including inputting a first image and a second image from two cameras of three or more cameras, respectively, transforming the first image to a transformed image, obtaining a degree of similarity D indicating a similarity between an image in a processing region established in the second image and an image in a corresponding processing region established in the first image, obtaining a degree of similarity P indicating a similarity between an image in the processing region established in the second image and an image in a corresponding processing region established in the transformed image, detecting the obstacle based on the degree of similarity D and the degree of similarity P on a reference plane region, and selecting and outputting either a result of detection of a plurality of the obstacles or a position of an obstacle detected as being the closest to the three or more cameras.

System and method for detecting obstacle

Apparatus includes unit configured to compute parallax search range in (x-y-d) three-dimensional space formed of three variables (x and y providing first point (x, y) on first image and parallax candidate d), similarity unit configured to compute degree-of-similarity C (x, y, d) between point (x, y) and second point (x', y&#x2032;) corresponding to point (x, y), using sum of products of brightness levels of corresponding pixel pairs between first window on first image and second window on second image, first window including first point (x, y) second window including second point (x&#x2032;, y&#x2032;) and unit configured to compute parallax D between first point (x, y) and second point (x&#x2032;, y&#x2032;), based on C (x, y, d), where similarity unit includes unit configured to store sum, which is used for computing C (x, y, d) between new first point on first image and new second point on second image.

Three-dimensional-information reconstructing apparatus, method and program

An obstacle detection system using stereo cameras mounted on a vehicle, to detect an obstacle existing on a ground plane at a high speed and in a high precision even with the stereo cameras being uncalibrated and with a vibration during a traveling and a change in the inclination of the ground plane. The obstacle detection system comprises: a plurality of uncalibrated TV cameras for inputting stereo images; an image storage unitfor storing a plurality of images inputted from the TV cameras; a feature extraction unitfor extracting a plurality of mutually parallel lines existing on the ground plane; a parameter computation unitfor determining a relation to hold between the projected positions of an arbitrary point of the ground plane upon the individual images, from the plurality of lines extracted by the feature extraction unitand a detection unitfor detecting an object having a height from the ground plane, by using the relation determined by the parameter computation unit

Obstacle detection system and method therefor

A computer readable storage medium storing instructions of a computer program which when executed by a computer results in performance of steps including inputting a first image and a second image from two cameras, respectively, transforming the first image to a transformed image, obtaining a degree of similarity D indicating similarity between an image in a processing region established in the second image and an image in a corresponding processing region established in the first image, obtaining a degree of similarity P indicating a similarity between an image in the processing region established in the second image and an image in a corresponding processing region established in the transformed image, detecting the obstacle based on of the degree of similarity D and the degree of similarity P on a reference plane region, detecting the obstacle on a basis of the degree of similarity D and the degree of similarity P on a reference plane region, obtaining a difference K between the degree of similarity D and the degree of similarity P both obtained as being on the reference plane region, judging that the obstacle is at a position where the difference K is large, and determining a width and a height of the processing region on the basis of a position in the vertical direction on the second image.

A plurality of cameras respectively input an image from different camera positions. The plurality of cameras is on a moving object. An image memory stores a plurality of images input by the plurality of cameras. An image transformation unit transforms one image input by a first camera using each of a plurality of transformation parameters each representing a geometrical relationship among a predetermined plane, the first camera, and a second camera, and generates a plurality of transformed images from a view position of the second camera. A matching processing unit compares each of the plurality of transformed images with another image input by the second camera for each area consisting of pixels, and calculates a coincidence degree of each area between each transformed image and another image. An obstacle detection unit detects an obstacle area consisting of areas each having a coincidence degree below a threshold from another image.

Obstacle detection apparatus and method

A computer readable storage medium storing instructions of a computer program which when executed by a computer results in performance of steps including inputting a first image and a second image from two cameras, respectively, transforming the first image to a transformed image, obtaining a degree of similarity D indicating similarity between an image in a processing region established in the second image and an image in a corresponding processing region established in the first image, obtaining a degree of similarity P indicating a similarity between an image in the processing region established in the second image and an image in a corresponding processing region established in the transformed image, detecting the obstacle based on of the degree of similarity D and the degree of similarity P on a reference plane region, detecting the obstacle on a basis of the degree of similarity D and the degree of similarity P on a reference plane region, obtaining a difference K between the degree of similarity D and the degree of similarity P both obtained as being on the reference plane region, and judging that the obstacle is at a position where the difference K is large.

A computer readable storage medium storing instructions of a computer program which when executed by a computer results in performance of steps including inputting a first image and a second image from two cameras, respectively, transforming the first image to a transformed image, obtaining a degree of similarity D indicating similarity between an image in a processing region established in the second image and an image in a corresponding processing region established in the first image, obtaining a degree of similarity P indicating a similarity between an image in the processing region established in the second image and an image in a corresponding processing region established in the transformed image, detecting the obstacle based on of the degree of similarity D and the degree of similarity P on a reference plane region, and determining a width and a height of the processing region on the basis of a position in the vertical direction on the second image.

A method for detecting an obstacle by using two cameras of three or more cameras, the obstacle being on a reference plane in a field of view common to the two cameras, the method inputting a first image and a second image from the two cameras, respectively, transforming the first image to a transformed image, obtaining a degree of similarity D indicating a similarity between an image in a processing region established in the second image and an image in a corresponding processing region established in the first image, obtaining a degree of similarity P indicating a similarity between an image in the processing region established in the second image and an image in a corresponding processing region established in the transformed image, detecting the obstacle based on the degree of similarity D and the degree of similarity P on a reference plane region, and selecting and outputting either a result of detection of a plurality of the obstacles or a position of an obstacle detected as being the closest to the three or more cameras.

A method for detecting an obstacle by using two cameras, the obstacle being on a reference plane in a field of view common to the two cameras, the method inputting a first image and a second image from the two cameras, respectively, transforming the first image to a transformed image, obtaining a degree of similarity D indicating a similarity between an image in a processing region established in the second image and an image in a corresponding processing region established in the first image, obtaining a degree of similarity P indicating a similarity between an image in the processing region established in the second image and an image in a corresponding processing region established in the transformed image, detecting the obstacle based on of the degree of similarity D and the degree of similarity P on a reference plane region, obtaining a difference K between the degree of similarity D and the degree of similarity P both obtained as being on the reference plane region, judging that the obstacle is at a position where the difference K is large, and determining a width and a height of the processing region on the basis of a position in the vertical direction on the second image.

A method for detecting an obstacle by using two cameras, the obstacle being on a reference plane in a field of view common to the two cameras, the method inputting a first image and a second image from the two cameras, respectively, transforming the first image to a transformed image, obtaining a degree of similarity D indicating a similarity between an image in a processing region established in the second image and an image in a corresponding processing region established in the first image, obtaining a degree of similarity P indicating a similarity between an image in the processing region established in the second image and an image in a corresponding processing region established in the transformed image, detecting the obstacle based on the degree of similarity D and the degree of similarity P on a reference plane region, detecting the obstacle on a basis of the degree of similarity D and the degree of similarity P on a reference plane region, obtaining a difference K between the degree of similarity D and the degree of similarity P both obtained as being on the reference plane region, and judging that the obstacle is at a position where the difference K is large.

A method for detecting an obstacle by using two cameras, the obstacle being on a reference plane in a field of view common to the two cameras, the method inputting a first image and a second image from the two cameras, respectively, transforming the first image to a transformed image, obtaining a degree of similarity D indicating a similarity between an image in a processing region established in the second image and an image in a corresponding processing region established in the first image, obtaining a degree of similarity P indicating a similarity between an image in the processing region established in the second image and an image in a corresponding processing region established in the transformed image, detecting the obstacle based on the degree of similarity D and the degree of similarity P on a reference plane region, and determining a width and a height of the processing region on the basis of a position in the vertical direction on the second image.

An obstacle detection system using stereo cameras mounted on a vehicle, to detect an obstacle existing on a ground plane at a high speed and in a high precision even with the stereo cameras being uncalibrated and with a vibration during a traveling and a change in the inclination of the ground plane. The obstacle detection system comprises: a plurality of uncalibrated TV cameras for inputting stereo images; an image storage unitfor storing a plurality of images inputted from the TV cameras; a feature extraction unitfor extracting a plurality of mutually parallel lines existing on the ground plane; a parameter computation unitfor determining a relation to hold between the projected positions of an arbitrary point of the ground plane upon the individual images, from the plurality of lines extracted by the feature extraction unit; and a detection unitfor detecting an object having a height from the ground plane, by using the relation determined by the parameter computation unit

A computer readable storage medium storing instructions of a computer program which when executed by a computer results in performance of steps including inputting a first image and a second image from two cameras, respectively, transforming the first image to a transformed image, obtaining a degree of similarity D indicating similarity between an image in a processing region established in the second image and an image in a corresponding processing region established in the first image, obtaining a degree of similarity P indicating a similarity between an image in the processing region established in the second image and an image in a corresponding processing region established in the transformed image, detecting the obstacle based on of the degree of similarity D and the degree of similarity P on a reference plane region, obtaining a difference K between the degree of similarity D and the degree of similarity P both obtained as being on the reference plane region, judging that the obstacle is at a position where the difference K is large, judging that there is no obstacle when there is no difference K of degree of similarity equal to or greater than a threshold value set beforehand about the vertical directions of all of the images, and detecting that there is the obstacle when there is the difference K of degree of similarity equal to or more than the threshold value in the vertical direction of the image.

A method for detecting an obstacle by using two cameras, the obstacle being on a reference plane in a field of view common to the two cameras, the method inputting a first image and a second image from the two cameras, respectively, transforming the first image to a transformed image, obtaining a degree of similarity D indicating a similarity between an image in a processing region established in the second image and an image in a corresponding processing region established in the first image, obtaining a degree of similarity P indicating a similarity between an image in the processing region established in the second image and an image in a corresponding processing region established in the transformed image, detecting the obstacle based on the degree of similarity D and the degree of similarity P on a reference plane region, obtaining a difference K between the degree of similarity D and the degree of similarity P both obtained as being on the reference plane region, judging that the obstacle is at a position where the difference K is large, judging that there is no obstacle when there is no difference K of degree of similarity equal to or greater than a threshold value set beforehand about the vertical directions of all of the images, and detecting that there is the obstacle when there is the difference K of degree of similarity equal to or more than the threshold value in the vertical direction of the image.

Growing community of inventors

Tokyo, Japan

Hiroshi Hattori