Abstract: A stereoscopic object detection device including a first detection unit configured to detect a road surface and a stereoscopic object; a second detection unit configured to detect the stereoscopic object by a millimeter-wave radar; and a detection control unit configured to detect the stereoscopic object based on the detection result of at least one of the first detection unit and the second detection unit. The detection control unit is configured to detect the stereoscopic object based on the detection result of the first detection unit when the stereoscopic object is within a range where the road surface is detectable by the first detection unit. The detection control unit is configured to detect the stereoscopic object based on the detection results of the first detection unit and the second detection unit when the stereoscopic object is outside of the range where the road surface is detectable by the first detection unit.

Abstract: A second classification unit classifies each set of classified parallax points is classified into any one of a stereoscopic object category, a road surface category, and an unknown category based on the distribution of the longitudinal positions of the parallax points belonging to the set in the parallax image. A road surface estimation unit estimates a road surface based on the parallax points of the set classified into the road surface category, and a third classification unit classifies a set corresponding to a stereoscopic object among the sets classified into the unknown category based on the estimated road surface.

Abstract: A road surface detection device that detects a road surface region based on disparity information obtained from a captured image of an area around a vehicle that is captured by an onboard camera, includes a path estimating portion that estimates a travel path where the vehicle will travel, based on driving information of the vehicle; and a detecting portion that weights the disparity information, and detects a road surface region in the captured image based on the weighted disparity information, wherein when the detecting portion weights the disparity information, the detecting portion gives less weight to the disparity information positioned on a side away from the travel path in the captured image than to the disparity information positioned on a side near the travel path in the captured image.

Abstract: An apparatus that detects a road surface on the basis of a parallax image around a vehicle, the road surface detection apparatus includes an ECU configured to determine on the basis of parallax information of the parallax image whether a unit area is a road surface area for each unit area of the parallax image associates each unit area with a grid in a map on the basis of parallax information and coordinate position of the unit area, an eye point of the map being set so as to be higher than an eye point of the parallax image, the map being obtained by partitioning an area around the vehicle in a grid, and detect road surface grids and each grid located between the road surface grids as the road surface, the road surface grids being the grids corresponding to the unit areas determined as the road surface areas.

Abstract: An object detection device including: an imaging unit (11) carried on a movable body; a first calculation unit (21; 22; 23) that calculate an observed value of an image displacement among a plurality of images captured by the imaging unit (11) at respective different timings; a first object detection unit (10, 21; 10, 22; 10, 23) that detects an object candidate and acquires information of the object candidate; a second calculation unit (21, 22, 23) that calculates a theoretic value of the image displacement on the basis of the information of the object candidate; and a second object detection unit (21; 22; 23) that compares the observed value of the image displacement and the theoretic value of the image displacement and determines whether the object candidate is an object on the basis of the comparison result.

Abstract: An object detecting device includes a camera ECU that detects an object from image data for a predetermined area has been captured by a monocular camera, a fusion processing portion that calculates the pre-correction horizontal width of the detected object, a numerical value calculating portion that estimates the length in the image depth direction of the calculated pre-correction horizontal width, and a collision determining portion that corrects the pre-correction horizontal width calculated by the fusion processing portion, based on the estimated length in the image depth direction.

Abstract: An object detection device, including: an imaging unit that is mounted on a movable body; an object detection unit that calculates an image displacement of a partial image between two images captured by the imaging unit at different times, and performs detection processing to detect an object in an image based on at least the image displacement; and a control unit that changes a manner of performing the detection processing based on a position in the image in a lateral direction of the movable body.

Abstract: An image display device that includes an extraction component, a calculation component, an image processing component and a display component is provided. The extraction component extracts from photographic images a photographic image in which a face has been photographed. The calculation component calculates a position of an eye in the photographic image extracted by the extraction component. The image processing component performs image processing on the photographic image such that the position of the eye calculated by the calculation component will be at a predetermined position. The display component displays the photographic image which has been processed by the image processing component.

Abstract: An object detecting device includes a camera ECU that detects an object from image data for a predetermined area has been captured by a monocular camera, a fusion processing portion that calculates the pre-correction horizontal width of the detected object, a numerical value calculating portion that estimates the length in the image depth direction of the calculated pre-correction horizontal width, and a collision determining portion that corrects the pre-correction horizontal width calculated by the fusion processing portion, based on the estimated length in the image depth direction.

Abstract: An image capturing apparatus includes: an image capturing device which receives an optical image of an object subjected to light via an image capturing lens and converts the optical image into an image signal; a face detecting device which detects a plurality of human faces from the image signal; a face distance calculating device which calculates a distance between the detected human faces; a notice device which gives a notice corresponding to the calculated distance between the human faces; a timer shot device which performs a real shooting after an elapse of a first predetermined time since a shooting instruction; and a control device which gives the shooting instruction to the timer shot device when the calculated distance between the human faces is less than a predetermined value. Accordingly, even when the shooting object includes persons, a well composed shooting can be easily realized.

Abstract: An object detection device including: an imaging unit (11) carried on a movable body; a first calculation unit (21; 22; 23) that calculate an observed value of an image displacement among a plurality of images captured by the imaging unit (11) at respective different timings; a first object detection unit (10, 21; 10, 22; 10, 23) that detects an object candidate and acquires information of the object candidate; a second calculation unit (21, 22, 23) that calculates a theoretic value of the image displacement on the basis of the information of the object candidate; and a second object detection unit (21; 22; 23) that compares the observed value of the image displacement and the theoretic value of the image displacement and determines whether the object candidate is an object on the basis of the comparison result.

Abstract: An object detection device, including: an imaging unit (400) that is mounted on a movable body; an object detection unit (201) that calculates an image displacement of a partial image between two images captured by the imaging unit (400) at different times, and performs detection processing to detect an object in an image based on at least the image displacement; and a control unit (201) that changes a manner of performing the detection processing based on a position in the image in a lateral direction of the movable body.

Abstract: An image processing method, comprises: an input step of inputting a color digital image; a white balance correction step of correcting white balance of the inputted digital image; an exposure correction step of correcting exposure of the digital image having the corrected white balance; a determination step of determining a pixel in which an output pixel value is saturated without being corrected to be underexposed by the exposure correction, among respective pixels in the digital image having the corrected white balance; and a pixel value correction step of setting only the determined pixel to be saturated as a correction target pixel and correcting the pixel value of the correction target pixel to be more than or equal to the pixel value. Thereby, the color attachment with respect to the blown-out highlight portion can be prevented at the time of the desensitization process.

Abstract: When a transition is made from display of one image of a subject to display of another image of a subject in a slideshow, the transition is made in a natural manner. A first enlarged image is obtained by cropping and enlarging a portion of a subject image so as to include a face-image portion. A plurality of first enlarged images are obtained in such a manner that a cropping zone gradually decreases and the enlarging rate of the cropped image gradually increases. A first enlarged image in which the face-image portion is displayed in close-up is obtained. When a plurality of enlarged images are displayed one after another and a first enlarged image prevailing at the time of image transition is displayed, a second enlarged image in which a face image contained in a second subject image is shown in close-up is displayed. Second enlarged images that gradually zoom out from the face-image portion are displayed one after another to thereby make a transition to display of the second subject image.

Abstract: The sizes of icons for moving images (the size of a rectangle on the front side of each icon, the length of each icon in the depth direction thereof, etc.) that specify moving-image files are changed depending upon file information (moving image playback times, image sizes of the frames that make up the moving images, sizes of the moving-image files, etc.) concerning the moving-image files specified by the icons for the moving images. The content of each moving-image file can be ascertained by observing the icon for its moving image.

Abstract: An image capturing apparatus includes: an image capturing device which receives an optical image of an object subjected to light via an image capturing lens and converts the optical image into an image signal; a face detecting device which detects a plurality of human faces from the image signal; a face distance calculating device which calculates a distance between the detected human faces; a notice device which gives a notice corresponding to the calculated distance between the human faces; a timer shot device which performs a real shooting after an elapse of a first predetermined time since a shooting instruction; and a control device which gives the shooting instruction to the timer shot device when the calculated distance between the human faces is less than a predetermined value. Accordingly, even when the shooting object includes persons, a well composed shooting can be easily realized.

Abstract: An image display device that includes an extraction component, a calculation component, an image processing component and a display component is provided. The extraction component extracts from photographic images a photographic image in which a face has been photographed. The calculation component calculates a position of an eye in the photographic image extracted by the extraction component. The image processing component performs image processing on the photographic image such that the position of the eye calculated by the calculation component will be at a predetermined position. The display component displays the photographic image which has been processed by the image processing component.

Abstract: An image processing method, comprises: an input step of inputting a color digital image; a white balance correction step of correcting white balance of the inputted digital image; an exposure correction step of correcting exposure of the digital image having the corrected white balance; a determination step of determining a pixel in which an output pixel value is saturated without being corrected to be underexposed by the exposure correction, among respective pixels in the digital image having the corrected white balance; and a pixel value correction step of setting only the determined pixel to be saturated as a correction target pixel and correcting the pixel value of the correction target pixel to be more than or equal to the pixel value. Thereby, the color attachment with respect to the blown-out highlight portion can be prevented at the time of the desensitization process.

Abstract: When a transition is made from display of one image of a subject to display of another image of a subject in a slideshow, the transition is made in a natural manner. A first enlarged image is obtained by cropping and enlarging a portion of a subject image so as to include a face-image portion. A plurality of first enlarged images are obtained in such a manner that a cropping zone gradually decreases and the enlarging rate of the cropped image gradually increases. A first enlarged image in which the face-image portion is displayed in close-up is obtained. When a plurality of enlarged images are displayed one after another and a first enlarged image prevailing at the time of image transition is displayed, a second enlarged image in which a face image contained in a second subject image is shown in close-up is displayed. Second enlarged images that gradually zoom out from the face-image portion are displayed one after another to thereby make a transition to display of the second subject image.

Abstract: An image comparative display method having displaying two images; that is, a first image and a second image, on a monitor screen in a side-by-side arrangement, wherein the first image is selected by a first set of images, and the second image is selected by a second set of images, wherein the monitor screen is split into a first region that displays the first image; a second region that displays the second image; a third region adjacent to the first region, the third region displaying at least one first thumbnail image corresponding to at least one image from the first set of images; and a fourth region adjacent to the second region, the fourth region displaying at least one second thumbnail image corresponding to at least one image from the second set of images.