Abstract: A deposit detection device according to an embodiment includes a calculation module, a detection module, an interpolation module, and a state management module. The calculation module calculates a region feature amount based on an edge vector of each pixel, for each unit region composed of a predetermined number of pixels included in a captured image. The detection module detects the unit region corresponding to a partial covering location and the unit region corresponding to a diffuse reflection location based on a detection condition and a second detection condition, respectively, the first detection condition and the second detection condition being based on the region feature amount. The interpolation module interpolates the area ratio of the partial covering location reduced due to the diffuse reflection location. The state management module controls state transitions of states related to interpolation of the area ratio, based on increase and decrease of the diffuse reflection location.

Abstract: A deposit detection device according to an embodiment includes a detection module and a determination module. The detection module detects a deposit region including a deposit adhering to a lens of an imaging device from a captured image captured by the imaging device. The determination module performs maintenance determination as to whether to maintain a detection history of detection by the detection module, based on brightness information of the captured image.

Abstract: An attached substance detection device according to an embodiment includes a calculation unit and a determination unit. The calculation unit calculates a score of a divided region that is provided by dividing a predetermined target region, based on an edge intensity in each pixel region of a captured image that is captured by an image-capturing device. The determination unit determines whether or not the target region is an attached substance region where an attached substance is attached to a lens of the image-capturing device, based on the score that is calculated by the calculation unit.

Abstract: A decision part decides a representative edge direction using a predetermined angle range as a unit for each pixel area of a plurality of pixel areas of a photographic image photographed by a camera based on an edge angle of each pixel contained in the pixel area. An extractor extracts two of the pixel areas that are adjacent to each other as a pair area among the pixel areas of the photographic image, when the two pixel areas that are adjacent to each other have opposite representative edge directions. A determination part determines whether or not there is an attachable matter on a lens of the camera based on at least one of (1) a number of the pair areas extracted by the extractor and (2) a total sum of edge intensities of the pixel areas contained in the pair areas.

Abstract: An attached object detection apparatus includes a setting part, a calculator, and a detector. A setting part sets a plurality of divided regions within a captured image captured by an image capturing apparatus. A calculator calculates, for each of the plurality of divided regions and based on luminance of pixels in the divided region, a representative luminance value and an amount of luminance dispersion. A detector detects, as an attached region that has an attached object, a divided region among the plurality of divided regions that satisfies the following conditions: i) a first difference is equal to or smaller than a first predetermined difference, ii) a second difference is equal to or smaller than a second predetermined difference, and iii) the representative luminance value of the current divided region is equal to or smaller than a first predetermined value.

Abstract: An adhered substance detection apparatus includes a controller configured to function as a determination part, an extractor, and a detector. The determination part determines a representative edge direction using a predetermined angle range as a unit for each pixel area of a plurality of pixel areas of a photographic image photographed by a photographing device, the representative edge direction being determined for each of the pixel areas based on an edge angle of each pixel included in the pixel area. The extractor extracts an array pattern in which a plurality of the pixel areas having a same representative edge direction are continuously arranged along a predetermined scanning direction based on the representative edge directions of the pixel areas determined by the determination part. The detector detects whether an adhered substance area exists on a lens of the photographing device based on the array pattern extracted by the extractor.

Abstract: An extraneous-matter detecting apparatus includes a region setting unit, a computing unit, a change-value setting unit, an updating unit, and a detection unit. The region setting unit sets divided regions for a captured image captured by an image capturing device. The computing unit computes, for a corresponding divided region, a first difference between a past representative value of luminance and a present representative value of luminance and a second difference between a past dispersion amount of luminance and a present dispersion amount of luminance. The change-value setting unit sets, based on the first and the second differences, a change value of a counter value that indicates an adhesion state of an extraneous matter in the divided region. The updating unit updates the counter value based on the change value. The detection unit detects, based on the counter value, an adhesion state of an extraneous matter in the divided region.

Abstract: An adhering substance detection apparatus includes calculating, first and second detecting, and generating units. The calculating unit calculates a variation in a feature value related to luminance in past and current captured images captured by an image capturing device, based on the luminance of pixels included in the captured images. The first detecting unit detects a first region in which the variation calculated by the calculating unit falls within a threshold range, and the feature value in the current captured image falls within a threshold range. The second detecting unit detects a second region in which an irregularity in a distribution of the luminance of the pixels included in the captured image satisfies a predetermined irregularity condition. The generating unit generates a sum region being a sum of the first and second regions, as an adhering substance region corresponding to an adhering substance adhering to the image capturing device.

Abstract: An extraneous-matter detecting apparatus according to an embodiment includes a region setting unit, a computing unit, and a state setting unit. The region setting unit sets, for a captured image captured by an image capturing device provided in a vehicle, a plurality of divided regions. The computing unit computes a representative value of luminance in a target region for detecting an adhesion of an extraneous matter. The target region includes the plurality of divided regions. The state setting unit sets, based on a vehicle speed and the representative value of luminance in the target region, a transition state of information that indicates an adhesion state of an extraneous matter in the divided region.

Abstract: An attached object detection apparatus includes: an extractor that extracts, based on edges detected from pixels of a captured image captured by an image capturing apparatus, a candidate region for an attached object region corresponding to an attached object on the image capturing apparatus; and a determiner that determines, based on a fluctuation of luminance distribution of pixels within the candidate region extracted by the extractor, whether or not the candidate region is the attached object region.

Abstract: An attached object detection apparatus includes a memory and a controller coupled to the memory. The controller is configured to: extract one or more candidate regions from a captured image captured by an image capturing apparatus, each of the one or more candidate regions being a candidate for being an attached object region corresponding to a portion of the image in which an attached object is attached to the image capturing apparatus, the one or more candidate regions being extracted based on edges detected from pixels of the image; select, as one or more selection regions, one or more of the candidate regions satisfying predetermined selection conditions, from amongst the extracted one or more candidate regions; and determine, based on fluctuation of luminance distribution of pixels in the selected one or more selection regions, whether or not each of the one or more selection regions is the attached object region.

Abstract: An attachable matter detection apparatus includes a controller configured to function as an extractor and a detector. The extractor extracts edge information of each pixel contained in a photographic image photographed by an imaging device. The detector detects a candidate area estimated to have a water droplet out of the photographic image based on a matching result between (i) each of the pixels converted into a predetermined data format based on the edge information extracted by the extractor and (ii) a template representing a water droplet and having the data format. The detector calculates a matching frequency with the template for a predetermined area along a contour of the candidate area, and excludes the candidate area when the candidate area satisfies a predetermined exclusion condition based on the matching frequency.

Abstract: An adhering substance detection apparatus according to an embodiment includes a calculating unit and a determining unit. The calculating unit calculates, for each cell composed of a predetermined number of pixels in a captured image, an edge feature value that is based on edge vectors in the pixels, and that classifies an edge orientation that is included in the edge feature value, into two types of angle classes. The determining unit determines a condition of adhering substance adhering to an image capturing apparatus that captured the captured image, based on a transition count representing number of transitions the angle class goes through within a unit region that is a predetermined region composed of a predetermined number of the cells.