An image processing device has a first image input unit that inputs a visible light image of a target area imaged by a first camera, a second image input unit that inputs a temperature distribution image of the target area imaged by a second camera, a first image processing section that processes the visible light image input to the first image input unit, and detects an object imaged in the visible light image, a second image processing section that processes the temperature distribution image input to the second image input unit and detects an object imaged in the temperature distribution image, and an image region extracting unit that extracts an image region not suited for the detection of the object in the first image processing section for the visible light image of the target area input to the first image input unit.