Abstract: An angle detecting device has a processor configured to detect a first point and a second point indicating parts of rear of the towing vehicle within a first plane, a third point and a fourth point indicating parts of front of the towed vehicle within a second plane from within an image that includes the rear of the towing vehicle and the front of the towed vehicle, project the first to fourth points onto a projection plane parallel to ground and calculate fifth to eighth points, and calculate an angle formed between a first straight line connecting the fifth point and sixth point and a second straight line connecting the seventh point and eighth point in the projection plane as the relative angle of the towed vehicle with respect to the towing vehicle.

Abstract: A travel control device includes an image recognition unit which performs image recognition of a pattern drawn on a road surface by light irradiated from a surrounding vehicle, a prediction unit which predicts behavior of the surrounding vehicle based on a result of the image recognition of the pattern, and a travel control unit which controls travel of a host vehicle based on the behavior of the surrounding vehicle.

Abstract: A motor controller includes a first control circuit, a second control circuit, a determination circuit, and a command circuit. The first control circuit outputs a first control value based on a rule base from a command value of an angular velocity and a measured value of an angular velocity. The second control circuit outputs a second control value based on a learned model from the command value of the angular velocity and the measured value of the angular velocity. The determination circuit determines a state based on at least the second control value. The command circuit acquires and outputs a control command value from the first control value and the second control value based on a result determined by the determination circuit.

Abstract: An apparatus for detecting a lane boundary includes one or more processors configured to: input an image representing a region around a vehicle into a classifier to identify the types of objects represented in respective pixels of the image, and detect a boundary of the travel lane by determining, for each of pixel lines in a direction crossing the travel lane in the image, whether the position corresponding to a pixel group including a predetermined number of contiguous pixels is inside the travel lane in order along a scanning direction from one end to the other end of the pixel line, depending on the order of the types of objects represented in the pixel group and the result of determination whether the position corresponding to the immediately preceding pixel group with respect to the scanning direction is inside the travel lane.

Abstract: An information processing device has a processor configured to detect a vanishing point where two lane marking lines in a front image representing environment ahead of a vehicle intersect, to detect a moving direction of the vehicle from a predetermined reference location to the vanishing point in the front image, to determine whether or not each of two moving directions has a different orientation in excess of a predetermined reference range with respect to the previously detected moving direction when the two moving directions have been detected, and to determine that a branching road that branches from a road in which the vehicle is traveling has appeared in the front image, when it has been determined that either of the two moving directions has a different orientation.

Abstract: An angle detecting device has a processor configured to detect a first point and a second point indicating parts of rear of the towing vehicle within a first plane, a third point and a fourth point indicating parts of front of the towed vehicle within a second plane from within an image that includes the rear of the towing vehicle and the front of the towed vehicle, project the first to fourth points onto a projection plane parallel to ground and calculate fifth to eighth points, and calculate an angle formed between a first straight line connecting the fifth point and sixth point and a second straight line connecting the seventh point and eighth point in the projection plane as the relative angle of the towed vehicle with respect to the towing vehicle.

Abstract: A motor controller includes a first control circuit, a second control circuit, a determination circuit, and a command circuit. The first control circuit outputs a first control value based on a rule base from a command value of an angular velocity and a measured value of an angular velocity. The second control circuit outputs a second control value based on a learned model from the command value of the angular velocity and the measured value of the angular velocity. The determination circuit determines a state based on at least the second control value. The command circuit acquires and outputs a control command value from the first control value and the second control value based on a result determined by the determination circuit.

Abstract: An apparatus for detecting a lane boundary includes one or more processors configured to: input an image representing a region around a vehicle into a classifier to identify the types of objects represented in respective pixels of the image, and detect a boundary of the travel lane by determining, for each of pixel lines in a direction crossing the travel lane in the image, whether the position corresponding to a pixel group including a predetermined number of contiguous pixels is inside the travel lane in order along a scanning direction from one end to the other end of the pixel line, depending on the order of the types of objects represented in the pixel group and the result of determination whether the position corresponding to the immediately preceding pixel group with respect to the scanning direction is inside the travel lane.

Abstract: A road surface detecting apparatus comprises a camera sensor 11 for taking images of a region in front of a vehicle, and an electronic control unit (ECU) configured to: calculate, based on a taken image, parallax information including a parallax of each pixel composing the taken image; extract a pixel corresponding to a road surface from the taken image; acquire, based on information of the extracted pixel, information-indicating-a-road-surface; calculate, based on the information-indicating-a-road-surface, a road surface gradient formula by approximating a gradient of the road surface by a quadratic function; determine whether or not an absolute value of a coefficient of a quadratic term of this formula is greater than a coefficient threshold; and invalidate the information-indicating-a-road-surface when the absolute value is determined to be greater than the threshold.

Abstract: A target object estimating apparatus comprises parallax information calculating means for calculating parallax information including a parallax between corresponding pixels of taken images taken at a same computation timing, road surface region detecting means for detecting a road surface region in the taken image based on the parallax information, road surface region determining means for determining whether or not each pixel in the taken image corresponds to the road surface region, transition information calculating means for calculating transition information including a change amount of a position of each pixel, using temporally sequential taken images, and estimated value calculating means for estimating a position and a speed of a target object by calculating, based on the parallax/transition information, estimated values of the position and the speed of each pixel.

Abstract: In a monitoring apparatus, an optical flow calculator calculates an optical flow for each of selected pixel regions included in at least one pixel region group of an image. The optical flow for each of the selected pixel regions includes information about a direction and amount of movement of a corresponding part of the at least one target object. An adjuster calculates the sum of areas of all the pixel regions included in the at least one pixel region group of the image, and adjusts a selected number of the optical flows to be matched with the at least one pixel region group as a function of the calculated sum of the areas of all the pixel regions included in the at least one pixel region group.

Abstract: An apparatus comprises three-dimensional object detecting means for detecting a three-dimensional object in a taken image, temporarily determining means for calculating, based on parallax information, a lower end height from a road surface to a lower end of the object, for temporarily determining that the object is a ground-contacting object when the lower end height is less than or equal to a threshold, and for temporarily determining that the object is a floating object when the lower end height exceeds the threshold, and finally determining means for finally determining whether the object is a ground-contacting object or a floating object. The finally determining means finally determines that the object is a ground-contacting object at the current computation timing when the object is determined to be a ground-contacting object in at least one of the temporary determination at the current computation timing and the final determination at the previous computation timing.

Abstract: In a monitoring apparatus, a disparity calculator obtains, for each point of a target object, a pair of matched pixel regions in respective base image and reference image corresponding to the point of the target object. The disparity calculator calculates a disparity of each of the matched pixel regions of the base image relative to the corresponding matched pixel region of the reference image. A distance calculator corrects the calculated disparity of each of the matched pixel regions of the base image in accordance with a tolerable disparity range for the disparity to thereby increase the calculated disparity of the corresponding one of the matched pixel regions of the base image. The distance calculator calculates the depth distance of each point of the target object relative to the vehicle as a function of the corrected disparity of the corresponding one of the matched pixel regions.

Abstract: A parallax calculating apparatus comprises first parallax calculating means for calculating a first parallax on a basis of a reference image for all pixels in the reference image using SGM method, second parallax calculating means for calculating a second parallax on a basis of the reference image for at least a part of pixels among pixels in the reference image using BM method, and final parallax calculating means for calculating a final parallax of each of pixels in the reference image based on the first and second parallaxes. The final parallax calculating means calculates the first parallax as the final parallax for a pixel for which only the first parallax has been calculated and calculates a parallax where a decimal part of the first parallax is replaced with that of the second parallax as the final parallax for a pixel for which the first and second parallaxes have been calculated.

Abstract: A light source estimating apparatus of embodiments has a sensitivity ratio spatial distribution calculating unit configured to extract a first color pixel and a second color pixel which have close spectral sensitivity and which have different sensor responses from a first picked up image picked up with an image sensor under an arbitrary light source, and calculate a ratio between a signal value of the first color pixel and a signal value of the second color pixel to acquire a first sensitivity ratio spatial distribution, and a similarity determining unit configured to estimate a type of the arbitrary light source based on similarity between a second sensitivity ratio spatial distribution group calculated using a second picked up image picked up with the image sensor under a known light source and the first sensitivity ratio spatial distribution.

Abstract: In a monitoring apparatus, a disparity calculator obtains, for each point of a target object, a pair of matched pixel regions in respective base image and reference image corresponding to the point of the target object. The disparity calculator calculates a disparity of each of the matched pixel regions of the base image relative to the corresponding matched pixel region of the reference image. A distance calculator corrects the calculated disparity of each of the matched pixel regions of the base image in accordance with a tolerable disparity range for the disparity to thereby increase the calculated disparity of the corresponding one of the matched pixel regions of the base image. The distance calculator calculates the depth distance of each point of the target object relative to the vehicle as a function of the corrected disparity of the corresponding one of the matched pixel regions.

Abstract: In a monitoring apparatus, an optical flow calculator calculates an optical flow for each of selected pixel regions included in at least one pixel region group of an image. The optical flow for each of the selected pixel regions includes information about a direction and amount of movement of a corresponding part of the at least one target object. An adjuster calculates the sum of areas of all the pixel regions included in the at least one pixel region group of the image, and adjusts a selected number of the optical flows to be matched with the at least one pixel region group as a function of the calculated sum of the areas of all the pixel regions included in the at least one pixel region group.

Abstract: An apparatus comprises three-dimensional object detecting means for detecting a three-dimensional object in a taken image, temporarily determining means for calculating, based on parallax information, a lower end height from a road surface to a lower end of the object, for temporarily determining that the object is a ground-contacting object when the lower end height is less than or equal to a threshold, and for temporarily determining that the object is a floating object when the lower end height exceeds the threshold, and finally determining means for finally determining whether the object is a ground-contacting object or a floating object. The finally determining means finally determines that the object is a ground-contacting object at the current computation timing when the object is determined to be a ground-contacting object in at least one of the temporary determination at the current computation timing and the final determination at the previous computation timing.

Abstract: A road surface detecting apparatus comprises imaging means 11 for taking an image of a region in front of a vehicle, parallax information calculating means for calculating, based on a taken image, parallax information including a parallax of each pixel composing the taken image, road surface information acquiring means for extracting a pixel corresponding to a road surface from the taken image, and acquiring, based on information of extracted pixel, information-indicating-a-road-surface, road surface gradient formula calculating means for calculating, based on the information-indicating-a-road-surface, a road surface gradient formula by approximating a gradient of the road surface by a quadratic function, gradient change determining means for determining whether or not an absolute value of a coefficient of a quadratic term of this formula is greater than a coefficient threshold, and invalidating means for invalidating the information-indicating-a-road-surface when the absolute value is determined to be greate

Abstract: A parallax calculating apparatus comprises first parallax calculating means for calculating a first parallax on a basis of a reference image for all pixels in the reference image using SGM method, second parallax calculating means for calculating a second parallax on a basis of the reference image for at least a part of pixels among pixels in the reference image using BM method, and final parallax calculating means for calculating a final parallax of each of pixels in the reference image based on the first and second parallaxes, The final parallax calculating means calculates the first parallax as the final parallax for a pixel for which only the first parallax has been calculated and calculates a parallax where a decimal part of the first parallax is replaced with that of the second parallax as the final parallax for a pixel for which the first and second parallaxes have been calculated,