| 摘要 |
An image processing device (100) includes an imaging device (2), a first extraction unit (5), a disparity calculation unit (4), a second extraction unit (8), and an object determination unit (9). The first extraction unit extracts a main area based on image data captured by the imaging device, the main area being an image area including a candidate for a target. The second extraction unit extracts a candidate area from the main area based on the disparity. The object determination unit determines whether an image of the candidate area is an image of the target. An extraction of the candidate area from a lower part area is restricted more strictly than that from an upper part area. The lower part area is provided below a predetermined position in the main area. The upper part area is provided above the predetermined position in the main area. |
