An image processing device according to an embodiment includes an image acquisition unit, an information acquisition unit, a generation unit, a composition unit, a determination unit, and a display control unit. The image acquisition unit acquires a captured image where an image of an environment of a vehicle is captured by an image-capturing device. The information acquisition unit acquires positional information regarding a detected position of an obstacle that exists in an environment of the vehicle. The generation unit generates a virtual viewpoint image where an environment of the vehicle is viewed from a virtual viewpoint, based on the captured image. The composition unit composites a notification image that provides notification of existence of the obstacle at the detected position with the virtual viewpoint image. The display control unit controls a display format of the notification image that is composited with the virtual viewpoint image, based on the positional information.