A recognition and positioning device includes a CV video obtaining unit that generates a CV video by adding a CV value to an object video, an object designation unit that designates a recognition target object captured throughout a plurality of frames of the CV video, a consecutive frame machine learning unit that repetitively executes a recognition process through machine learning, a three-dimensional coordinate computation and object coordinate assigning unit that associates recognized objects over the frames of the CV video, identifies the objects having matched coordinates of the captured objects in corresponding frames, and assigns three-dimensional position coordinates to the objects, and a coordinate assigning and recognition output unit that assigns the three-dimensional coordinates to the objects about which a predetermined recognition certainty degree and a three-dimensional coordinate accuracy are obtained, by repeating recognition of the object and assigning of the three-dimensional position coordinates.