An operation determination method in a motion operation device that receives a non-contact operation performed by a user on a display image, comprising:
- acquiring a photographed image obtained by photographing the user, the photographed image including both a fingertip of the user and eyes of the user;
- detecting positions of eyes and a fingertip of the user in the photographed image by hardware configured to execute prescribed detection processes;
- calculating, by software executed by a processor, positions of a line-of-sight and the fingertip of the user with respect to a display surface where the display image is displayed;
- and
- determining, by software executed by the processor, a motion of the fingertip of the user with respect to the display image;
- wherein
- the acquiring includes acquiring first image data obtained by a left image sensor placed in a front left direction with respect to the user, and second image data obtained by a right image sensor placed in a front right direction with respect to the user, and
- the detecting the positions of the eyes and the fingertip of the user includes
- executing operations using a plurality of logic circuits and memory units of the hardware, each of the plurality of logic circuits being configured to supply an operation result to a corresponding memory unit, and the corresponding memory unit being configured to supply the operation result to a next logic circuit in a sequence of the plurality of logic circuits,
- using first hardware configured to, based on the first image data, generate first coordinate position information indicating the positions of the eyes and the fingertip of the user on a two-dimensional image, and
- using second hardware configured to, based on the second image data, generate second coordinate position information indicating the positions of the eyes and the fingertip of the user on the two-dimensional image,
- wherein the using the first hardware comprises including in the first hardware
- first face recognition hardware configured to perform a face recognition process based on the first image data,
- first eye recognition hardware configured to perform an eye recognition process based on an output of the first face recognition hardware,
- first 2D coordinate conversion hardware configured to generate coordinate position information indicating the position of the eyes on the two-dimensional image, based on an output of the first eye recognition hardware,
- first hand recognition hardware configured to perform a hand recognition process based on the first image data,
- first fingertip recognition hardware configured to perform a fingertip recognition process based on an output of the first hand recognition hardware, and
- second 2D coordinate conversion hardware configured to generate coordinate position information indicating the position of the fingertip on the two-dimensional image, based on an output of the first fingertip recognition hardware, and
- wherein the using the second hardware comprises including in the second hardware
- second face recognition hardware configured to perform a face recognition process based on the second image data,
- second eye recognition hardware configured to perform an eye recognition process based on an output of the second face recognition hardware,
- third 2D coordinate conversion hardware configured to generate coordinate position information indicating the position of the eyes on the two-dimensional image, based on an output of the second eye recognition hardware,
- second hand recognition hardware configured to perform a hand recognition process based on the second image data,
- second fingertip recognition hardware configured to perform a fingertip recognition process based on an output of the second hand recognition hardware, and
- fourth 2D coordinate conversion hardware configured to generate coordinate position information indicating the position of the fingertip on the two-dimensional image, based on an output of the second fingertip recognition hardware.