摘要:
A secondary curve, the ends of which coincide with the inner corner and the outer corner of the eye, is determined successively, and the total of the edge values of the pixels overlapping the secondary curve is calculated as an evaluation value. Next, a characteristic curve is generated on the basis of data made up of the calculated evaluation value and the Y-coordinate of the intersection between the secondary curve and a straight line passing through the center of a line segment whose ends coincide with the inner corner and the outer corner of the eye. Then, the reference positions for the upper eyelid and the lower eyelid of the eye are set on the basis of the result of an attempt to detect a pixel group occurring because of the red-eye effect in a search area defined on the basis of peaks in the characteristic curve.
摘要:
A computer (30) obtains a facial image acquired by picking up an image of a person subjected to image pickup from a camera (10), and estimates a facial expression of the person subjected to image pickup based on the obtained facial image. Next, the computer obtains an eye open level of the person subjected to image pickup based on the facial image, and sets a threshold of the eye open level based on the estimated facial expression of the person subjected to image pickup. When the eye open level exceeds the threshold, the computer (30) determines that the eye of the person subjected to image pickup is opened. Moreover, when the eye open level does not exceed the threshold, the computer determines that the eye of the person subjected to image pickup is closed.
摘要:
A secondary curve, the ends of which coincide with the inner corner and the outer corner of the eye, is determined successively, and the total of the edge values of the pixels overlapping the secondary curve is calculated as an evaluation value. Next, a characteristic curve is generated on the basis of data made up of the calculated evaluation value and the Y-coordinate of the intersection between the secondary curve and a straight line passing through the center of a line segment whose ends coincide with the inner corner and the outer corner of the eye. Then, the reference positions for the upper eyelid and the lower eyelid of the eye are set on the basis of the result of an attempt to detect a pixel group occurring because of the red-eye effect in a search area defined on the basis of peaks in the characteristic curve.
摘要:
Detecting with good precision an eye inside corner position and an eye outside corner position as face feature points even when the eye inside corner and/or the eye outside corner portions are obscured by noise. First eyelid profile modeling is performed with a Bezier curve expressed by a fixed control point P3 indicating an eye inside corner first position detected in an image, a fixed control point P4 indicating an eye outside corner first position, a control point P1 corresponding to an upper eyelid position candidate (first parameter), and a control point P2 corresponding to a lower eyelid position candidate (second parameter). Then in a second eyelid profile model with fixed P1 and P2 of the first eyelid profile model having the highest fitting evaluation value λ to the eyelid profile in the image, the values of a control point P3 indicating an eye inside corner position candidate (third parameter) and a control point P4 indicating an eye outside corner candidate (fourth parameter) at a maximum of a fitting evaluation value λ when changing the values of the control point P3 and control point P4 are determined as an eye inside corner second position and an eye outside corner second position, respectively.
摘要:
A device for detecting a road traveling lane, which is capable of stably defining a position of a boundary of a traveling lane. Edge point detection means (ED) detects a plurality of edge points in a contour on an image, and segment group producing means (SD) produces a line segment on the basis of continuity of distance and direction between neighboring edge points, and groups a plurality of line segments having a predetermined relationship with each other, to produce a segment group. Further, curve detection means (CD) detects a curve fitted to the segment group. Then, when a segment group forming a curve closest to the center of the traveling lane has a predetermined length and repeated cycle, lane boundary position defining means (LD) defines the segment group as the innermost marking line, and defines a position of a neighboring curve outside of the innermost marking line as the position of the boundary of the traveling lane.
摘要:
An eyelid opening level determination device includes a face image taking unit; an upper eyelid detection unit for detecting an upper eyelid in the face image; a lower eyelid area setting unit for setting an area for searching a lower eyelid based on the upper eyelid; an edge group detecting unit for detecting an edge group where brightness changes from dark to bright as a lower eyelid candidate by scanning the area from an upper side to a lower side; a reliability value obtaining unit for obtaining a reliability value of the edge group; a lower eyelid determination unit in which the edge group having the reliability value exceeding a predetermined value in the edge group is determined to be the lower eyelid; and an eyelid opening level obtaining unit for obtaining opening level of the eyelid based on positions for the upper eyelid and the lower eyelid.
摘要:
An image around a vehicle matching the intent of a driver is automatically displayed.An infrared camera (2) picks up an image of the face of a driver (7). A visual line direction and a face direction are detected from the face image of the driver (7). Based on the visual line direction of the driver (7) and the face direction thereof, a direction in which the driver (7) gazes is detected. When the direction in which the driver (7) gazes is included in image pickup ranges of CCD cameras (1A, 1B, and 1C), an image around a vehicle (100) picked up by any one of the CCD cameras (1A, 1B, and 1C) is automatically displayed on a monitor (6).
摘要:
An eyelid opening level determination device includes a face image taking unit; an upper eyelid detection unit for detecting an upper eyelid in the face image; a lower eyelid area setting unit for setting an area for searching a lower eyelid based on the upper eyelid; an edge group detecting unit for detecting an edge group where brightness changes from dark to bright as a lower eyelid candidate by scanning the area from an upper side to a lower side; a reliability value obtaining unit for obtaining a reliability value of the edge group; a lower eyelid determination unit in which the edge group having the reliability value exceeding a predetermined value in the edge group is determined to be the lower eyelid; and an eyelid opening level obtaining unit for obtaining opening level of the eyelid based on positions for the upper eyelid and the lower eyelid.
摘要:
A parking assisting device is equipped with a imaging device (1), a gaze position determining sections (3, 11), target parking position setting sections (1, 11), and a parking assisting section (2). The imaging device (1) takes images of surrounding of a vehicle. The gaze position determining sections (3, 11) determine positions at which a driver gazes. The target parking position setting sections (1, 11) sets target parking positions based on images taken by the imaging device (1) and gaze positions determined by the gaze position determining section (11). The parking assisting section (2) assists in processing to park the vehicle at the set target parking position.
摘要:
A lower eyelid search window (W2) matching the pixels constituting the edge of a lower eyelid is transformed so that the lower eyelid search window (W2) fits the pixels constituting the edge of the lower eyelid. Then, the position of the centroid of the transformed lower eyelid search window (W2) is set as the lower eyelid reference position. Consequently, the lower eyelid reference position can be accurately set even if the lower eyelid search window (W2) is different in shape from the edge of the lower eyelid. Then, it is possible to accurately detect the degree of opening of the eyes of a driver and thus accurately determine the degree of wakefulness of the driver.