First, the data processing apparatus 1 determines the moving image data to be analyzed (S10). For example, the user specifies a plurality of moving image files captured at a plurality of places different from each other as data to be analyzed. Then, the data processing apparatus 1 sets all the moving image files as data to be analyzed. In this case, each of the moving image files is handled as child data.

As another example, the user may specify a plurality of moving image files, and specify the start position and the end position of the data to be analyzed for each moving image file. Then, the data processing apparatus 1 may set a range from the specified start position to the specified end position of each moving image file as data to be analyzed. In this case, the data from the specified start position to the specified end position of each moving image file is handled as child data.

Then, the person extraction unit 10 analyzes the moving image data to be analyzed, and extracts a person whose appearance frequency in the moving image data to be analyzed satisfies a predetermined condition among persons detected in the moving image data to be analyzed (S11).

That is, the person extraction unit 10 determines whether or not each person detected in the moving image data to be analyzed appears in each of the plurality of pieces of child data. Then, based on the determination result, the person extraction unit 10 calculates an appearance frequency for each person detected in the moving image data to be analyzed. Then, the person extraction unit 10 extracts a person whose appearance frequency satisfies a predetermined condition among persons detected in the moving image data to be analyzed.