According to an embodiment, an image processing apparatus creates a depth map representing distribution of depths of pixels in an image. The apparatus includes an area detecting unit configured to detect an area of a vertical object included in an image; a base depth adding unit configured to add a base depth to the image, the base depth being a basic distribution of depths of pixels in the image; and, a depth map creating unit configured to acquire at least one depth of a vicinity of a ground contact position of the vertical object from the base depth added to the image, and create the depth map by setting the acquired depth onto the base depth as a depth of the area of the vertical object.