Abstract: In an obstacle detection apparatus, the captured image of a vicinity of a vehicle from an imaging apparatus is acquired. A three-dimensional estimation image showing a three-dimensional position of a feature point in the captured image is generated, and a three-dimensional position of an object is estimated. An attribute image in which an object in the captured image is classified into one or more classes that include at least a road-surface class is generated. The three-dimensional estimation image and the attribute image are fused, the feature points and the classes are associated, and road-surface points associated with the road-surface class are extracted. Based on the road-surface points, a road-surface height in the vicinity of the vehicle is estimated. Based on the estimated road-surface height, the three-dimensional position of the object is corrected. Based on the three-dimensional position of the object, an obstacle in the vicinity of the vehicle is detected.

Abstract: A parking space detection apparatus detects a parking space of an own vehicle and includes: a vehicle determination section that determines whether an other vehicle is present on at least one of two sides of a parking space, based on search information acquired from an in-vehicle search section that searches for the parking space; a width calculation section that, it is determined that the other vehicle is present on at least one of the two sides of the parking space, calculate a width of the parking space on an entrance side and a width of the parking space on an inner side based on the search information; and a parking determination section that determines whether the own vehicle is able to park in the parking space based on the widths of the parking space on the entrance side and on the inner side and size of the own vehicle.

Abstract: An image processing unit generates a corrected bird's-eye-view image that is a captured bird's-eye-view image and that is a bird's-eye-view image from which irradiation light present in the captured image has been removed. The corrected bird's-eye-view image is generated as a bird's-eye-view image representing a difference between the captured bird's-eye-view image and a difference image that is an image representing a change in a pixel value of the captured bird's-eye-view image. The image processing unit generates a corrected history image that is a bird's-eye-view image obtained by combining the corrected bird's-eye-view images while shifting positions of the corrected bird's-eye-view images on the basis of a movement amount of the own vehicle. The image processing unit generates a corrected display image that is a bird's-eye-view image obtained by combining the corrected history image and the latest captured bird's-eye-view image, and makes a display unit display the corrected display image.

Abstract: A mounting angle detection device converts, into a bird's-eye view image, an image captured of the ground on which a target marking having two straight line parts parallel to each other and equal in width is marked, and searches for a mounting angle at which the two straight line parts in the bird's-eye view image are parallel to each other and equal in width. Even with a vehicle including an in-vehicle camera on the front or back, the mounting angle detection device detects an actual mounting angle of the camera and calibrates the mounting angle of the camera. The mounting angle detection device detects the mounting angle using, as the target marking, even a parking space that lacks a transverse line crossing the two straight line parts parallel to each other and equal in width, and calibrates the mounting angle to a correct mounting angle of the camera.

Abstract: In a display processing device, an acquisition section acquires a captured image of surroundings of the vehicle from at least one imaging device installed in a vehicle. A first generation section generates a first converted image that is an image as seen from a first viewpoint in the vehicle, based on the captured image at a latest imaging time point. A calculation section calculates displacement of the vehicle. A second generation section generates a second converted image that is an image as seen from the first viewpoint at the latest imaging time point and is an image of an area including under the vehicle, based on the captured image captured earlier than the latest imaging time point and the displacement. The display processing section causes a display device visible to an occupant of the vehicle to display a display image obtained by compositing the first and second converted images.

Abstract: A parking space detection apparatus detects a parking space of an own vehicle and includes: a vehicle determination section that determines whether an other vehicle is present on at least one of two sides of a parking space, based on search information acquired from an in-vehicle search section that searches for the parking space; a width calculation section that, it is determined that the other vehicle is present on at least one of the two sides of the parking space, calculate a width of the parking space on an entrance side and a width of the parking space on an inner side based on the search information; and a parking determination section that determines whether the own vehicle is able to park in the parking space based on the widths of the parking space on the entrance side and on the inner side and size of the own vehicle.

Abstract: A pedestrian detection device on a vehicle having a vehicular camera and a sonar or a radar includes: an identification dictionary storage unit that stores multiple identification dictionaries of shape features of a pedestrian; a detection result accumulation unit that searches the captured image for one feature to detect the pedestrian, and accumulates a detection result for each identification dictionary; a pedestrian position accumulation unit that detects the pedestrian using the sonar or the radar, and accumulates a pedestrian position; an identification dictionary selection unit that selects a detection identification dictionary having the detection result consistent with the pedestrian position; and a pedestrian detection unit that searches the captured image for one feature described in the detection identification dictionary, and detects the pedestrian.

Abstract: An image processing apparatus includes an image acquisition unit and a determination unit. The image acquisition unit uses a camera to acquire a first image representing an area in a first relative position and a second image representing an area in a second relative position closer to the moving direction of the vehicle than the first relative position. The determination unit compares the first image with the second image acquired earlier than the first image and representing an area overlapping the first image for luminance and/or the intensity of a predetermined color component to determine whether there exists a specific area higher in luminance than the surroundings or lower in luminance than the surroundings in the first image.

Abstract: A mounting angle detection device converts, into a bird's-eye view image, an image captured of the ground on which a target marking having two straight line parts parallel to each other and equal in width is marked, and searches for a mounting angle at which the two straight line parts in the bird's-eye view image are parallel to each other and equal in width. Even with a vehicle including an in-vehicle camera on the front or back, the mounting angle detection device detects an actual mounting angle of the camera and calibrates the mounting angle of the camera. The mounting angle detection device detects the mounting angle using, as the target marking, even a parking space that lacks a transverse line crossing the two straight line parts parallel to each other and equal in width, and calibrates the mounting angle to a correct mounting angle of the camera.

Abstract: An image analysis apparatus is applied to an on-vehicle camera that captures an image of a predetermined monitoring region oriented in a predetermined direction referenced to a vehicle, to analyze an image captured by the on-vehicle camera. The image analysis apparatus includes (i) a storage section that stores a feature quantity of a monitoring region image obtained when an image of the monitoring region is captured by the on-vehicle camera, (ii) an extraction section that acquires an image captured by the on-vehicle camera and extracts a feature quantity of the image captured by the on-vehicle camera, and (iii) a notification section that compares the feature quantity of the image captured by the on-vehicle camera against the feature quantity of the monitoring region image to perform determination whether the on-vehicle camera is mounted in an abnormal position, and notifies a result of the determination.

Abstract: A moving object detection apparatus that analyzes a photographic image captured by an onboard camera and detects a moving object is provided. The moving object detection apparatus includes an imaging portion that captures the photographic image at a predetermined time interval; a peripheral region detection portion that detects a first moving object of a size smaller than a predetermined size and a second moving object of a size larger than the predetermined size as the moving object in a peripheral region; and a central region detection portion that detects the first moving object as the moving object in a central region. The central region detection portion detects the first moving object and the second moving object as the moving object when the second moving object has been detected in the peripheral region at a previous time.

Abstract: An image processing unit generates a corrected bird's-eye-view image that is a captured bird's-eye-view image and that is a bird's-eye-view image from which irradiation light present in the captured image has been removed. The corrected bird's-eye-view image is generated as a bird's-eye-view image representing a difference between the captured bird's-eye-view image and a difference image that is an image representing a change in a pixel value of the captured bird's-eye-view image. The image processing unit generates a corrected history image that is a bird's-eye-view image obtained by combining the corrected bird's-eye-view images while shifting positions of the corrected bird's-eye-view images on the basis of a movement amount of the own vehicle. The image processing unit generates a corrected display image that is a bird's-eye-view image obtained by combining the corrected history image and the latest captured bird's-eye-view image, and makes a display unit display the corrected display image.

Abstract: A pedestrian detection device on a vehicle having a vehicular camera and a sonar or a radar includes: an identification dictionary storage unit that stores multiple identification dictionaries of shape features of a pedestrian; a detection result accumulation unit that searches the captured image for one feature to detect the pedestrian, and accumulates a detection result for each identification dictionary; a pedestrian position accumulation unit that detects the pedestrian using the sonar or the radar, and accumulates a pedestrian position; an identification dictionary selection unit that selects a detection identification dictionary having the detection result consistent with the pedestrian position; and a pedestrian detection unit that searches the captured image for one feature described in the detection identification dictionary, and detects the pedestrian.

Abstract: A vehicular surrounding-monitoring control apparatus is mounted in a vehicle having an imaging unit capturing an image of surrounding and a display. The vehicular surrounding-monitoring control apparatus includes: an extraction section extracting, as an object region, an image region corresponding to each object from a captured image obtained by the imaging unit; a determining section determining whether a plurality of objects are coordinated into a group on the basis of positional relations of the object regions and types of the objects; and a display control unit displaying, when the objects are determined to be coordinated into a group, displaying a symbol image, which is specific to the group and expresses the presence of the group, so as to be superimposed on the captured image in the display.

Abstract: An image generating device that generates a composite image based on partial images cut out from captured images having photographic subject regions partially overlapping with each other, includes: a correction device that corrects each target partial image by setting one of first and second adjacent partial images as a reference partial image; a generation device that generates first and second conversion tables for approximating a concentration characteristic of each target partial image in overlapping first and second common regions to the first and second adjacent partial images, respectively; and a mixture conversion device that converts a concentration of each target partial image to make an influence of the first conversion table larger as a position of a pixel is closer to the first adjacent partial image, and to make the influence of the second conversion table larger as the position of the pixel is closer to the second adjacent partial image.

Abstract: An image display device for displaying an image showing surrounding of a vehicle in a bird's eye view style is provided. The image display device includes a bird's eye view image generation section that generates, based on an image captured by an on-vehicle camera, a bird's eye view image showing the surrounding of the vehicle in the bird's eye view style, a vehicle image combination section that combines a vehicle image showing the vehicle with the bird's eye view image by placing the vehicle image at a position of the vehicle in the bird's eye view image, and an image output section that, from the bird's eye view image with which the vehicle image is combined, cuts out a predetermined scope in accordance with the shift position of the vehicle, and outputs the cut-out image to the display screen.

Abstract: An image analysis apparatus is applied to an on-vehicle camera that captures an image of a predetermined monitoring region oriented in a predetermined direction referenced to a vehicle, to analyze an image captured by the on-vehicle camera. The image analysis apparatus includes (i) a storage section that stores a feature quantity of a monitoring region image obtained when an image of the monitoring region is captured by the on-vehicle camera, (ii) an extraction section that acquires an image captured by the on-vehicle camera and extracts a feature quantity of the image captured by the on-vehicle camera, and (iii) a notification section that compares the feature quantity of the image captured by the on-vehicle camera against the feature quantity of the monitoring region image to perform determination whether the on-vehicle camera is mounted in an abnormal position, and notifies a result of the determination.

Abstract: A moving object detection apparatus and a moving object detection method that detect a moving object appeared in the photographic image by analyzing the photographic image obtained by an onboard camera (10, 10R, 10L) are provided. The moving object detection apparatus is equipped with: an imaging portion (101) that captures the photographic image at a predetermined time interval; a peripheral region detection portion (102) that detects, as the moving object, a first moving object and a second moving object in peripheral regions (RP); and a central region detection portion (103) that detects, as the moving object, the first moving objects in a central region (RC). The moving object detection apparatus is equipped with the peripheral region detection portion (102) and the central region detection portion (103).

Abstract: An alertness level detection apparatus, which is equipped to a vehicle and detecting alertness level of a driver, includes a stimulus information acquirer detecting stimulus applied to driver's visual sensation within driver's visual field under a state in which the driver watches in travel direction of the vehicle and acquiring stimulus information related to occurrence time and occurrence position of the stimulus within the driver's visual field, a face image generator generating a face image of the driver, a line-of-sight position detector detecting line-of-sight position of the driver by analyzing the face image, a moving time duration detector detecting moving time duration taken for the driver to move the line of sight to the occurrence position of the stimulus immediately after the occurrence time of the stimulus, and an alertness level determiner determining the alertness level of the driver based on the moving time duration.

Abstract: An image generating device that generates a composite image based on partial images cut out from captured images having photographic subject regions partially overlapping with each other, includes: a correction device that corrects each target partial image by setting one of first and second adjacent partial images as a reference partial image; a generation device that generates first and second conversion tables for approximating a concentration characteristic of each target partial image in overlapping first and second common regions to the first and second adjacent partial images, respectively; and a mixture conversion device that converts a concentration of each target partial image to make an influence of the first conversion table larger as a position of a pixel is closer to the first adjacent partial image, and to make the influence of the second conversion table larger as the position of the pixel is closer to the second adjacent partial image.