Abstract: A visibility support apparatus includes a light receiving unit receiving reflected light from an object to generate a signal for an image for each of wavelength bands, a wavelength selecting unit to set, in the image for at least one wavelength band, a set of those of pixels with comparable signal intensities which define the largest occupied area to be a reference area and to compare, for each of identification target pixels not included in the reference area, a value of the pixel in the image for each wavelength band with a pixel value of the reference area to select at least two wavelength bands which are effective for detecting the object, and a display unit to group the identification target pixels based on a wavelength band combination selected for each identification target pixel and display an image in which the object is distinguishably shown based on the grouping.

Abstract: A sound source detection system for detecting a sound source (e.g., running sound of a vehicle) based on sound collected by microphones extracts characteristic amounts from the sound collected by the microphones, sets a plurality of classes according to the position of the sound source by a multi-class pattern recognition method (e.g., multi-class SVM) using the characteristic amounts, extracts characteristic amounts from sound collected by the microphones for detection of a sound source, determines a class to which the extracted characteristic amounts belong, from the preset plurality of classes, and estimates the sound source based on the class.

Abstract: A sound source detecting system that detects a predetermined sound source on the basis of sounds collected by sound collectors includes: a noise extracting unit that extracts a noise from signals of the collected sounds; and a noise suppressing unit that suppresses a signal component of the noise extracted by the noise extracting unit from the signals of the collected sounds. The sound source detecting unit detects a location of the predetermined sound source, such as an approaching vehicle, using information about the sounds having the signals of which the noise is suppressed.

Abstract: According to the present invention, a pedestrian is detected from an imaged image and a partial image including the pedestrian is extracted, shape information of the pedestrian acquired from the extracted partial image is accumulated and the shape information of a predetermined time before and the current shape information are compared using the accumulated shape information to detect change in the movement of the pedestrian, discontinuous movement estimating information indicating a discontinuous movement of the pedestrian that occurs following the change in the movement of the pedestrian is acquired from a storage means at the time the change in the movement of the pedestrian is detected, and a behavior of the pedestrian is predicted using the acquired discontinuous movement estimating information.

Abstract: Disclosed is a sound source detection device 1 which compares information of sound collected by sound collectors 13, 14, 15, and 16 to detect a predetermined sound source. The sound source detection device 1 includes a target determination unit 22 which arranges sound collectors at the same distance from a noise source inside a mobile object to determine a detection-target region of a sound source, and a sound source detection unit 25 which detects the direction of the predetermined sound source using information of sound of the detection-target region determined by the target determination unit 22. Accordingly, the sound source detection unit 25 does not determine sound input to the sound collectors 13, 14, 15, and 16 at the same timing as a detection target, making it possible to eliminate the influence of a noise source other than a sound source inside the mobile object in advance.

Abstract: A movable body spectrum measuring apparatus including a dictionary data storing unit for storing spectrum data containing wavelength information and light intensity information of an object being measured, and a limitation information storing unit for storing limitation information to regulate the wavelength information into partial wavelength information. The movable body spectrum measuring apparatus further including a discrimination level setting unit for setting selectively the limitation information corresponding to the discrimination level required of the object being measured, a restricting unit for restricting the spectrum data regarding the observation light to the spectrum data composed exclusively of the wavelength information limited by the limitation information, and a discrimination unit for discriminating the object being measured based on the comparison between the restricted spectrum data and the spectrum data regarding the dictionary data storing unit.

Abstract: A learning unit 4 generates a function table indicating the relationship between the class number and position information of an object and the probability of appearance of the object for each small area image pattern of a code book, calculates a sharing matrix indicating the commonality of a feature amount between the classes, makes a tree diagram in which the classes with a similar feature amount are clustered, and calculates the weight of each node in the tree diagram for each small area image pattern. The recognition processing unit 7 compares image data captured by a camera 2 with the code book, selects the closest small area image pattern among a plurality of small area image patterns, extracts the class related to the node with the smallest weight among the nodes with a weight equal to or greater than a threshold value for the selected small area image pattern, and votes the position information of the small area image pattern for the class, thereby recognizing the object.

Abstract: An approaching vehicle detecting system that detects an approaching vehicle on the basis of sounds collected by a plurality of sound collectors mounted on a host vehicle determines whether a transverse moving direction of a sound source detected by the plurality of sound collectors is a direction approaching the host vehicle, determines whether a vertical position of the sound source detected using the plurality of sound collectors is in the same plane as that of the host vehicle, and detects that sound source as the approaching vehicle when it is determined that the transverse moving direction of the sound source is the direction approaching the host vehicle and the vertical position of the sound source is in the same plane as that of the host vehicle.

Abstract: Provided is a movable body spectrum measuring apparatus, which can discriminate a measuring object with high precision by photographic data from a spectrum sensor mounted on a movable body such as a vehicle and can process the photographic data in real time. A movable body spectrum measuring apparatus discriminates the measuring object around a vehicle on the basis of the spectrum data from an observation light. A spectrum sensor can measure wavelength information and light intensity information. The movable body spectrum measuring apparatus comprises a dictionary data storing unit storing, as dictionary data, the spectrum data containing the wavelength information and the light intensity information regarding a plurality of predetermined measuring objects, and an arithmetic device for discriminating the measuring object on the basis of comparison computation to compare the spectrum data of the observation light and the spectrum data stored in the dictionary data storing unit.

Abstract: A subject is to provide a pedestrian motion predicting device capable of accurately predicting a possibility of a rush out before a pedestrian actually begins to rush out. According to the embodiments, the pedestrian is detected from input image data, a portion in which the detected pedestrian is imaged is cut out from the image data, a shape of the pedestrian imaged in the cut-out partial image data is classified by collating the shape with a learning-finished identifier group or a pedestrian recognition template group, and the rush out of the pedestrian is predicted based on a result of the acquired classification.

Abstract: A method for operating on images is described for interest point detection and/or description working under different scales and with different rotations, e.g. for scale-invariant and rotation-invariant interest point detection and/or description.

Abstract: An approaching vehicle detection device includes an approaching vehicle detection unit 22 that detects an approaching vehicle based on a running noise, an acquisition unit (an illumination sensor 10 and a weather information acquisition device 11) that acquires visibility information which indicates a visibility around the vehicle, and a determination unit (operation determination unit 21A) that determines whether or not to cause the approaching vehicle detection unit 22 to operate based on the visibility information acquired by the acquisition unit.

Abstract: There is provided an approaching vehicle detection device that detects an approaching vehicle on the basis of sounds collected by a plurality of sound collectors 13A, 14A, 15A, and 16A, in which a sound source (in particular, traveling sound of the vehicle) is detected using pairs of the sound collectors 11A (13A, 14A) and 12A (15A, 16A) with narrow spacings, and approach of the sound source is detected using a pair of the sound collectors 13A and 16A which are disposed to be more widely spaced than the pairs of the sound collectors 11A and 12A.

Abstract: A distance measuring apparatus (11) optically detects a measuring target, thereby measuring an object distance, which is the distance to the measuring target. The orientation of an optical axis of a lens is set to be different from an advancing direction of light incident from the measuring target. The lens is configured to form an image from the incident light, thereby obtaining an image of the measuring target.

Abstract: Provided is a device for detecting sound outside vehicle capable of detecting sounds outside the vehicle with high accuracy in various surrounding environments. A sound source direction detecting ECU 1 acquires sound collection information about sounds outside a vehicle which are collected by microphones 2A to 2G. The sound source direction detecting ECU 1 acquires traveling road information about the vicinity of a host vehicle on the basis of the acquired sound collection information. When the traveling road information is acquired, the sound source direction detecting ECU 1 adjusts the sound collection characteristics of the microphones 2A to 2G on the basis of the traveling road information.

Abstract: A light with a known spectrum is emitted from a light source toward a road surface, a first reflected light that is a reflected light of the known light reflected from the road surface is received by a first light receiver, and a reflectance spectrum of the light of the road surface is calculated from a spectrum of the first reflected light received by the first light receiver and the spectrum of the known light stored in the storage unit. A second reflected light that is reflected light of an environmental light reflected from the road surface is received by a second light receiver, and a spectrum of the environmental light is calculated from a spectrum of the second reflected light received by the second light receiver and the calculated reflectance spectrum of the light of the road surface.

Abstract: We describe methods of characterizing a set of images to determine their respective illumination, for example for recovering the 3D shape of an illuminated object. The method comprises: inputting a first set of images of the object captured from different positions; determining frontier point data from the images, this defining a plurality of frontier points on the object and for each said frontier point a direction of a normal to the surface of the object at the frontier point, and determining data defining the image capture positions; inputting a second set of images of said object, having substantially the same viewpoint and different illumination conditions; and characterizing the second set of images said frontier point data to determine data comprising object reflectance parameter data (?) and, for each image of said second set, illumination data (L) comprising data defining an illumination direction and illumination intensity for the image.

Abstract: A spectrum measurement device that recognizes objects to be measured on the basis of spectral data of observed light that is detected by a spectrum sensor capable of measuring wavelength information and light intensity information. The spectrum measurement device comprises a lighting device capable of projecting light that includes a wavelength region with a high atmospheric absorption index and recognizes the distance from a vehicle to an object to be measured through a computation that uses spectral data of observed light that is obtained from the object to be measured whereupon light of at least the wavelength region with the high atmospheric absorption index is projected.

Abstract: A spectrometer recognizes a measurement target on the basis of the spectral data set of observed light detected by a spectral sensor capable of measuring wavelength information and light intensity information. The spectrometer is provided with a spectral data processor. Spectral data sets are detected at two different positions by the spectral sensor, and the processor subtracts a first spectral data set from a second spectral data set, or divides the first spectral data set by the second spectral data set to calculate one phase correlation spectral data set, which is correlated to the spectral data sets at the two different positions. The processor simultaneously identifies the measurement target corresponding to the two different positions on the basis of the correlation spectral data set.

Abstract: A distance measurement device measures target distances to a measurement target by optically detecting the measurement target using a lens. The image formation relative quantity calculating part of the distance measurement device creates an image of the measurement target by causing light having a plurality of wavelengths from the measurement target to form an image by part of the lens. By further determining the image formation distances from the lens to the image for each wavelength, image formation relative quantities, which are quantities indicating the relative relationship between the image formation distances, are calculated. A recording part records correlation information, which is information defined by the chromatic aberration characteristics of the lens, in a manner so as to indicate the correlation between image formation relative quantities and target distances.