This position detection device recognizes the presence position of an object of interest in a three-dimensional space, and acquires a plurality of images captured from different imaging sites, the captured images including three-dimensional point group information about the space, and the area around the object in the space. An area detection unit uses the acquired plurality of images as input and determines whether an object of interest appears in the plurality of images. When the object of interest appears in each of the plurality of images, the area detection unit detects the area of the object in the images. An identification unit identifies a point group area corresponding to the object of interest on the basis of the point group information and the area of the object detected in the images. The position detection unit recognizes points corresponding to the object of interest from the point group information inside the area identified by the identification unit, and identifies the position of the object of interest in the space.