Abstract: An iris detection device includes a candidate detection unit, a candidate narrowing-down unit, and an iris specifying unit. The candidate detection unit detects circular regions as iris candidates from images captured by an infrared camera. The candidate narrowing-down unit narrows down the detected iris candidates into a predetermined number of iris candidates with use of data items of images of surroundings of each of the iris candidates. The iris specifying unit specifies one of the predetermined number of iris candidates obtained by the narrowing-down as an iris by matching between gradients of a contour of each of the predetermined number of iris candidates and iris templates.

Abstract: An iris detection device includes a candidate detection unit, a candidate narrowing-down unit, and an iris specifying unit. The candidate detection unit detects circular regions as iris candidates from images captured by an infrared camera. The candidate narrowing-down unit narrows down the detected iris candidates into a predetermined number of iris candidates with use of data items of images of surroundings of each of the iris candidates. The iris specifying unit specifies one of the predetermined number of iris candidates obtained by the narrowing-down as an iris by matching between gradients of a contour of each of the predetermined number of iris candidates and iris templates.

Abstract: An information provision apparatus (1) comprises an observed-object detection apparatus (11) and an information output unit (41), and outputs from the information output unit (41) information on an observed object detected by the observed-object detection apparatus (11). The observed-object detection apparatus (11) comprises: a line-of-sight detector (21) for detecting a line of sight of a driver; an object detector (22) for detecting an object which is on a line of sight of a driver, based on the direction of the line of sight detected by the line-of-sight detector (21), on a current position of a vehicle, and on map information; and an observed-object calculator (23) for determining from objects detected by the object detector (22) an observed object observed by a driver, based on time for which the object is on a line of sight. This allows an object observed by a driver to be detected even if there is no trigger from the driver.

Abstract: An information provision apparatus (1) comprises an observed-object detection apparatus (11) and an information output unit (41), and outputs from the information output unit (41) information on an observed object detected by the observed-object detection apparatus (11). The observed-object detection apparatus (11) comprises: a line-of-sight detector (21) for detecting a line of sight of a driver; an object detector (22) for detecting an object which is on a line of sight of a driver, based on the direction of the line of sight detected by the line-of-sight detector (21), on a current position of a vehicle, and on map information; and an observed-object calculator (23) for determining from objects detected by the object detector (22) an observed object observed by a driver, based on time for which the object is on a line of sight. This allows an object observed by a driver to be detected even if there is no trigger from the driver.

Abstract: An object of the present invention is to determine a kind of a passenger, e.g., adult or child, without executing a complicated image processing, thereby controlling an unfolding of an air bag. The safety apparatus for an automobile crash extracts a head ellipse from an image outputted from an area sensor. The apparatus stores beforehand reference head ellipses of every possible kind of passenger's heads. The extracted head ellipse of the present passenger is selected among the references. Then, a region including the extracted head ellipse is designated to a future processing region for searching the same passenger's head at a time to come. Thus, the passenger's head is recognized simply and rapidly, even when the passenger has moved outside the future processing region.

Abstract: An object of the present invention is to determine a kind of a passenger, e.g., adult or child, without executing a complicated image processing, thereby controlling an unfolding of an air bag. The safety apparatus against an automobile clash extracts a head ellipse from an image outputted from an area sensor. The apparatus stores beforehand reference head ellipses of every possible kinds of passenger's heads. The extracted head ellipse of the present passenger is selected among the references. Then, a region including the extracted head ellipse is designated to a future processing region for searching the same passenger's head at a time to come. Thus, the passenger's head is recognized simply and rapidly, even when the passenger once moved outside the future processing region.