Denso Ten Limited

Fujitsu Ten Limited

Teruhiko Kamibayashi

Daisuke Yamamoto

Yasushi Tani

Takashi Kono

Nobunori Asayama

Nobuhisa Ikeda

Tomokazu Oki

Kohji Ohnishi

Takeo Matsumoto

Tomoyuki Fujimoto

Takayuki Ozasa

Daisuke Shiota

Naoshi Kakita

Tomohide Kasame

Junji Hashimoto

Hiroki Murasumi

Yukio Ishikawa

Shizuka Tamura

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.

Deposit detection device for detecting a partial covering location, a not-adhere location, and a diffuse reflection location

A deposit detection device according to an embodiment includes an adhesion detection module, a moving adhesion detection module, and a determination module. The adhesion detection module detects a deposit region corresponding to a deposit adhering to an imaging device, based on brightness information of an image captured by the imaging device. The moving adhesion detection module detects the deposit region detected during moving of the vehicle as a moving deposit region, from among the deposit regions detected by the adhesion detection module. When the area of the moving deposit region detected by the moving adhesion detection module is equal to or larger than a first threshold value, the determination module determines that there is a deposit.

Deposit detection device and deposit detection method

A deposit detection device according to an embodiment includes a detection module and an identification module. The detection module detects a small region as a candidate region for a deposit region corresponding to a deposit adhering to an imaging device, based on brightness information for each of small regions into which a predetermined region in an image captured by the imaging device is divided. The identification module identifies the candidate region as the deposit region when undulation change in brightness distribution of pixels included in the candidate region detected by the detection module is within a predetermined range.

An adhered substance detection apparatus of an embodiment includes a calculator and a determiner. The calculator calculates an edge feature for each cell based on edge vectors of pixels within the cell in a captured image, and further calculates a region feature for each unit region based on the calculated edge features of the cells within the unit region. The determiner determines an adherence state of an adhered substance on a lens of a camera based on the region feature. The calculator calculates, as the region feature, number of the cells having an edge strength of zero. When the number of the cells having the zero edge strength is equal to or greater than a predetermined number in a predetermined attention area in the captured image, the determiner determines not to perform a determination for detecting whether the lens of the camera is entirely covered by the adhered substance.

Adhered substance detection apparatus

A deposit detection device according to an embodiment includes an extraction module and an exclusion module. The extraction module extracts a candidate region for a deposit from a captured image captured by an imaging device. The exclusion module excludes from the candidate region a region that satisfies a predetermined exception condition. The exclusion module excludes from the candidate region a region that satisfies a first exception region when adhesion of a deposit to the imaging device is not detected, and excludes from the candidate region a region that satisfies a second exception condition different from the first exception condition when adhesion of the deposit to the imaging device is detected.

A deposit detection device according to an embodiment includes a detection module and a storage processing module. The detection module detects a deposit region corresponding to a deposit adhering to an imaging device, based on brightness information of an image captured by the imaging device. The storage processing module stores deposit information on the deposit region in a storage unit that is nonvolatile, when an ignition power of a vehicle is turned off in a state in which the deposit region is detected. For an initial detection process after the ignition power is turned on, the detection module detects the deposit region based on the deposit information stored in the storage unit.

An adhered substance detection apparatus determines whether a substance is adhered to an image-capturing apparatus. The adhered substance detection apparatus includes a controller configured to function as: an extractor that extracts candidate regions for being an adhered substance region in which the substance is adhered to the image-capturing apparatus, the candidate regions being extracted based on an edge that is detected from pixels in an image captured by the image-capturing apparatus; and a final determiner that finally determines whether the candidate regions are the adhered substance region, based on i) an area of the candidate region located in a first region of the captured image, the first region including a road surface region in the captured image and ii) an area of the candidate region located in a second region of the captured image, the second region including a region other than the road surface region in the captured image.

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.

A deposit detection device according to an embodiment includes a detection module, a determination module, and an identification module. The detection module detects a deposit region corresponding to a deposit adhering to an imaging device, based on brightness information of an image captured by the imaging device. The determination module determines whether variation in brightness information in a predetermined region of the image is within a predetermined range, in a period after a vehicle is stopped in a state in which the deposit region is detected by the detection module. The identification module identifies brightness information serving as a determination criterion of the deposit region when the determination module determines that the variation in brightness information is within a predetermined range.

A deposit detection device according to an embodiment includes a calculation module, an extraction module, and a decision module. The calculation module calculates a brightness average for each of small regions into which a predetermined region of an image captured by an imaging device is divided. The extraction module extracts, as a high-brightness region, the small region in which the brightness average calculated by the calculation module is equal to or larger than a predetermined value. The decision module decides on a brightness threshold value for detecting a deposit region corresponding to a deposit adhering to the imaging device, based on the area of the high-brightness region extracted by the extraction module.

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.

Attached object detection apparatus

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.

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.

Extraneous-matter detecting apparatus and extraneous-matter detecting method

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.

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.

Growing community of inventors

Kobe, Japan

Teruhiko Kamibayashi