| 摘要 |
A vehicle environment monitoring apparatus capable of extracting an image of a monitored object in an environment around a vehicle by separating the same from the background image with a simple configuration having a single camera mounted on the vehicle is provided. The apparatus includes a first image portion extracting processing unit to extract first image portions (A1, A2) considered to be the head of a pedestrian from a currently picked up image and a previously picked up image by an infrared camera, a mask area setting processing unit to set mask areas (M1(0,0), M1(1,0), ..., M1(5,8)) around the first image portion (A1) in the currently picked up image, and an object extracting processing unit to carry out pattern matching for the previously picked up image by a comparison pattern obtained through affine transformation of each mask area at a change rate (Rate) between the first image portions (A1, A2), and to set an area (Arl) including the first image portion (A2) and a second image portion (M2(1,3), M2(2,3), ..., M2(3,6)) where a displacement amount between the position (black point) corresponding to the centroid of the mask area and the matching position is smaller than a predetermined threshold value to be an image area of the monitored object. |
