An information processing apparatus includes an input unit configured to input a plurality of images captured from a plurality of viewpoints, an extraction unit configured to extract a region of an object from each of the plurality of images, an acquisition unit configured to obtain a contour from the region of the object, a smoothing unit configured to perform smoothing of the contour based on a point group on the obtained contour, a correlation unit configured to correlate regions of the object extracted from respective ones of the plurality of images, and a calculation unit configured to calculate a position of the object based on information of regions correlated by the correlation unit and the point group obtained by the smoothing unit.