Abstract: The pixels located at equal intervals in a shot image are converted into intensity components and applied with a differential filter. The number of the obtained variations that have values larger than or equal to a certain value among the obtained variations is counted. Then discrimination of a vehicle shot in the target image is executed on the basis of the counted value. The counted value varies depending on a size of a shot object in a shot image. The counted value is large when an occupied area of the object is large, and the counted value is small when the occupied area of the object is small. By so doing, it is advantageously possible to properly discriminate a vehicle.

Abstract: A vehicle-type determination apparatus includes a vehicle-portion extracting unit, a hood recognizing unit, and a vehicle-type determining unit. The vehicle-portion extracting unit extracts a vehicle portion from an image of a recognition object. The hood recognizing unit recognizes an area corresponding to a hood in the vehicle portion extracted by the vehicle-portion extracting unit. The vehicle-type determining unit determines the vehicle type based on the degree of inclination of a side of the hood area recognized by the hood recognizing unit.

Abstract: A color classification method including: determining a plurality of predetermined process target regions from a plurality of pickup images taken by an imaging device; calculating a plurality of color distributions of pixels contained in the respective determined process target regions; and forming a plurality of clusters by executing a clustering process based on the calculated color distributions for the pickup images, the method being for classifying a plurality of colors with respect to the respective formed clusters, the forming step including: extracting predetermined number of the classified colors, whose calculated rates are highest in the calculated plurality of the rates, from among the predetermined classified colors; defining a plurality of color spaces, dimensions of each of which are selected from the predetermined number of the extracted classified colors.

Abstract: A color classification method including: determining a plurality of predetermined process target regions from a plurality of pickup images taken by an imaging device; calculating a plurality of color distributions of pixels contained in the respective determined process target regions; and forming a plurality of clusters by executing a clustering process based on the calculated color distributions for the pickup images, the method being for classifying a plurality of colors with respect to the respective formed clusters, the forming step including: extracting predetermined number of the classified colors, whose calculated rates are highest in the calculated plurality of the rates, from among the predetermined classified colors; defining a plurality of color spaces, dimensions of each of which are selected from the predetermined number of the extracted classified colors.

Abstract: A vehicle-type determination apparatus includes a vehicle-portion extracting unit, a hood recognizing unit, and a vehicle-type determining unit. The vehicle-portion extracting unit extracts a vehicle portion from an image of a recognition object. The hood recognizing unit recognizes an area corresponding to a hood in the vehicle portion extracted by the vehicle-portion extracting unit. The vehicle-type determining unit determines the vehicle type based on the degree of inclination of a side of the hood area recognized by the hood recognizing unit.

Abstract: The pixels located at equal intervals in a shot image are converted into intensity components and applied with a differential filter. The number of the obtained variations that have values larger than or equal to a certain value among the obtained variations is counted. Then discrimination of a vehicle shot in the target image is executed on the basis of the counted value. The counted value varies depending on a size of a shot object in a shot image. The counted value is large when an occupied area of the object is large, and the counted value is small when the occupied area of the object is small. By so doing, it is advantageously possible to properly discriminate a vehicle.