Abstract: An information collection system includes an on-vehicle device and a server, wherein the on-vehicle device includes a first transmission signal transmitting part configured to transmit a first transmission signal to the server when the vehicle event is detected, and an upload executing part configured to transmit the vehicle event data to the server when the upload demand is received. The server includes a determining part configured to determine, based on the determination purposes information, when the first transmission is received, whether the information acquisition condition is met, an upload demanding part configured to transmit the upload demand to the on-vehicle device when it is determined that the information acquisition condition is met, and a vehicle event data receiving part configured to receive the vehicle event data transmitted from the on-vehicle device.

Abstract: An information collection system includes an on-vehicle device and a server, wherein the on-vehicle device includes a first transmission signal transmitting part configured to transmit a first transmission signal to the server when the vehicle event is detected, and an upload executing part configured to transmit the vehicle event data to the server when the upload demand is received. The server includes a determining part configured to determine, based on the determination purposes information, when the first transmission is received, whether the information acquisition condition is met, an upload demanding part configured to transmit the upload demand to the on-vehicle device when it is determined that the information acquisition condition is met, and a vehicle event data receiving part configured to receive the vehicle event data transmitted from the on-vehicle device.

Abstract: An eye part detecting device has an image input section (21) for acquiring a face image, an eyelid edge labeling section (24) for detecting upper eyelid candidates and lower eyelid candidates which satisfy predetermined conditions for upper eyelids or lower eyelids in the face image, and an eyelid determination section (27) for comparing combinations of the upper and lower eyelid candidates to determine the combination of the upper and lower eyelid candidates whose relation best satisfies a predetermined condition as the upper and lower eyelids. The eyelid edge labeling section (24) classifies the horizontal edges and vertical edges calculated by an edge calculating section (23) into the upper eyelid candidates and the lower eyelid candidates according to a degree of how well the predetermined conditions are satisfied.

Abstract: An eye opening detection system that includes an imaging mechanism that captures an image of the face of a detected subject, an edge extraction mechanism that extracts the edge of the image captured, and an upper and lower eyelid detection mechanism that detects the upper and lower eyelids of the detected subject according to the edge extracted, and that detects the eye opening of the detected subject with reference to a detected distance between the upper and lower eyelids. The upper and lower eyelid detection detects the upper eyelid and detects the lower eyelid with reference to the upper eyelid detected.

Abstract: An eyelid detection apparatus includes a face image storing means storing a plurality of face images of a subject captured at different timings, a change detecting means detecting changes in each face image caused by blinking after processing the plurality of face images stored by the face image storing means, and an eyelid detecting means detecting a position of an eyelid of the subject based on the changes detected by the change detecting means.

Abstract: While a view angle is switched between wide and narrow view angles, images with the wide view angle and images with the narrow view angle are alternately taken. Based on images taken with the narrow view angle, movements of corresponding points in images in correspondence between the narrow-angle images are detected. Based on the images taken with the wide view angle, a translational vector and a rotation matrix that represent changes in the position and posture between the wide-angle images are calculated. By linearly interpolating the translational vector and the rotation matrix between the wide-angle images, a translational vector and a rotation matrix that represent changes in the position and posture between the narrow-angle images are estimated. Based on movements of corresponding points in the images and the translational vector and the rotational matrix between the narrow-angle images, three-dimensional coordinates of the corresponding points on the measurement object are highly accurately measured.

Abstract: A facial image photographic device for vehicle mounting includes a facial image photographic camera which photographs the face of a driver of a vehicle while the vehicle is running, and a changeover device. The changeover device changes over a utilization environment of the facial image photographic camera between a position in which, when performing photography, the facial image photographic camera can be exposed to direct insolation by sunlight, and a position in which, when not performing photography, at least a part of the facial image photographic camera is not to be exposed to direct insolation by sunlight than when performing photography.

Abstract: An eye detecting device includes an image generating device for generating a face image, a nostril detecting portion for detecting a nostril in the face image, an eye searching area setting portion for setting an eye searching area in the face image based on a position of the nostril detected by the nostril detecting portion, and an eye searching portion for searching an eye within the eye searching area set by the eye searching area setting portion.

Abstract: An on-board warning apparatus of the invention includes an inattentive time measuring device that measures a duration of an inattentive state of a driver; a dozing time measuring device that measures a duration of a dozing state of the driver; a first warning output device that warns the driver when the measured inattentive time exceeds a first predetermined period of time Ta; and a second warning output device that warns the driver when the measured dozing time exceeds a second predetermined period of time Tb. The first predetermined time Ta is shorter than the second predetermined period of time Tb.

Abstract: An eyelid detection apparatus includes a face-image storing apparatus for storing an image of a face of a subject, an eyelid-candidate extracting apparatus for processing the image stored in the face-image storing apparatus to extract a pair of lines, which becomes a candidate of a combination of a line corresponding to an upper eyelid and a line corresponding to a lower eyelid, a parameter calculating apparatus for calculating a parameter, which indicates a possibility that a pan of the image stored in the face-image storing apparatus, the part corresponding to the pair of lines extracted by the eyelid-candidate extracting apparatus, includes at least one of outer and inner corners of an eye, and an eyelid detecting apparatus for detecting a position of an eyelid of the subject on the basis of the parameter calculated by the parameter calculating apparatus.

Abstract: A face feature point detection apparatus includes an image capturing device, an edge calculating unit calculating edge values indicating a luminance change in a direction, and a detection target determining unit scanning an edge image, which is created by arranging the edge values for corresponding pixels based on pixel arrangement of the face images, with an image window being an aggregation of selected pixels formed in a predetermined shape, the detection target determining unit determining a position of the image window having a largest weighted sum of weighted sums to be a detection position where a detection target is present, providing that the weighted sum is calculated by multiplying the edge value which corresponds to each pixel in the image window by a predetermined value defined on a per-pixel basis and adding up all products of the edge value and the predetermined value.

Abstract: An image capturing section captures a face of an observed person. A position detecting section detects, from a face image expressing the face captured by the image capturing section, one of a position expressing a characteristic of a nose and a position expressing a characteristic of a region between eyebrows. A computing section computes a past relative position of a predetermined region of the face that is based on the position detected in the past by the position detecting section. A region position detecting section detects a position of the predetermined region on the basis of the past relative position computed by the computing section and the current position detected by the position detecting section.

Abstract: An eyelid detection apparatus includes edge image generating means for generating an edge image representing a magnitude of pixel value change per pixel in a predetermined direction in a region including an eye, based upon an image of the region; local peak value point searching means for searching a local peak value point, where the magnitude of pixel value change reaches a local peak value in the predetermined direction, in the edge image; and boundary point detecting means for detecting at least one of a first boundary point indicating a boundary between an upper eyelid and an eyeball and a second boundary point indicating a boundary between a lower eyelid and the eyeball, based upon a point which is shifted from the local peak value point in a direction towards the eyeball.

Abstract: It is possible to accurately detect a face center position based on an image of a person when the person is wearing glasses even when the person is facing sideways. Face images obtained as a result of photographing a face of a driver using a camera (10) are stored in an image memory (22). The CPU 24 determines positions of the sides and top and bottom positions of the face based on the face images stored in the image memory (22). Further, the CPU 24 determines whether or not the driver is wearing glasses or is facing sideways. When the wearing glasses and facing sideways is determined, a face center position is detected using face images for a lower region of the face. As a result, it is possible to detect a face center position in a reliable manner even when a driver wearing glasses is facing sideways.

Abstract: An eyelid detecting apparatus includes an image capturing portion for capturing a face image, a red-eye effect detecting portion for detecting a red-eye effect in which a light appears red at the pupil in the face image, the light entering through the pupil, reflecting on a choroidea of the eye, and exiting from the pupil, an eyelid detecting portion for detecting an upper eyelid and a lower eyelid in the face image on the basis of an edge appearing on a boundary between a bright portion and a dark portion and the eyelid detecting portion ignoring the edge of a red-eye effect occurring pupil so as not to be considered as the upper eyelid and the lower eyelid when the red-eye effect detecting portion detects the red-eye effect.

Abstract: While a view angle is switched between wide and narrow view angles, images with the wide view angle and images with the narrow view angle are alternately taken. Based on images taken with the narrow view angle, movements of corresponding points in images in correspondence between the narrow-angle images are detected. Based on the images taken with the wide view angle, a translational vector and a rotation matrix that represent changes in the position/posture between the wide-angle images are calculated. By linearly interpolating the translational vector and the rotation matrix between the wide-angle images, a translational vector and a rotation matrix that represent changes in the position/posture between the narrow-angle images are estimated. Based on movements of corresponding points in the images and the translational vector and the rotational matrix between the narrow-angle images, three-dimensional coordinates of the corresponding points on the measurement object are highly accurately measured.

Abstract: An eye opening detection system that includes an imaging mechanism that captures an image of the face of a detected subject, an edge extraction mechanism that extracts the edge of the image captured, and an upper and lower eyelid detection mechanism that detects the upper and lower eyelids of the detected subject according to the edge extracted, and that detects the eye opening of the detected subject with reference to a detected distance between the upper and lower eyelids. The upper and lower eyelid detection detects the upper eyelid and detects the lower eyelid with reference to the upper eyelid detected.

Abstract: An eye part detecting device has an image input section (21) for acquiring a face image, an eyelid edge labeling section (24) for detecting upper eyelid candidates and lower eyelid candidates which satisfy predetermined conditions for upper eyelids or lower eyelids in the face image, and an eyelid determination section (27) for comparing combinations of the upper and lower eyelid candidates to determine the combination of the upper and lower eyelid candidates whose relation best satisfies a predetermined condition as the upper and lower eyelids. The eyelid edge labeling section (24) classifies the horizontal edges and vertical edges calculated by an edge calculating section (23) into the upper eyelid candidates and the lower eyelid candidates according to a degree of how well the predetermined conditions are satisfied.

Abstract: An on-board warning apparatus of the invention includes an inattentive time measuring device that measures a duration of an inattentive state of a driver; a dozing time measuring device that measures a duration of a dozing state of the driver; a first warning output device that warns the driver when the measured inattentive time exceeds a first predetermined period of time Ta; and a second warning output device that warns the driver when the measured dozing time exceeds a second predetermined period of time Tb. The first predetermined time Ta is shorter than the second predetermined period of time Tb.

Abstract: It is possible to accurately detect a face center position based on an image of a person when the person is wearing glasses even when the person is facing sideways. Face images obtained as a result of photographing a face of a driver using a camera (10) are stored in an image memory (22). The CPU 24 determines positions of the sides and top and bottom positions of the face based on the face images stored in the image memory (22). Further, the CPU 24 determines whether or not the driver is wearing glasses or is facing sideways. When the wearing glasses and facing sideways is determined, a face center position is detected using face images for a lower region of the face. As a result, it is possible to detect a face center position in a reliable manner even when a driver wearing glasses is facing sideways.