In a motion analysis apparatus 101, a data input unit 205 acquires a first imaging result and a second imaging result. In the motion analysis apparatus 101, a skeleton recognition unit 206 recognizes skeleton positions of a subject using the first imaging result acquired by the data input unit 205, and recognizes skeleton positions of the subject using the second imaging result acquired by the data input unit 205. A motion period extraction unit 403 extracts a period from a start of a motion to an end of the motion as a range of data for comparing skeleton feature points recognized by the skeleton recognition unit 206. The similarity calculation unit 401 compares skeleton feature points recognized for an input from a depth camera with skeleton feature points recognized for an input from an RGB camera to calculate similarities, and outputs a determination result based on the similarities.