System, information processing method, and information processing program
A system includes a first image sensor that generates a first image signal by synchronously scanning all pixels at a prescribed timing, a second image sensor including an event-driven type vision sensor that, upon detecting a change in an intensity of incident light on each pixel, generates a second image signal asynchronously, an inertial sensor that acquires attitude information on the first image sensor and the second image sensor, a first computation processing device that recognizes a user on the basis of at least the second image signal and calculates coordinate information regarding the user on the basis of at least the second image signal, a second computation processing device that performs coordinate conversion on the coordinate information on the basis of the attitude information, and an image generation device that generates a display image which indicates a condition of the user, on the basis of the converted coordinate information.
1 . A system comprising:
a first image sensor that generates a first image signal by synchronously scanning all pixels at a prescribed timing;
a second image sensor including an event-driven type vision sensor that, upon detecting a change in an intensity of incident light on each of the pixels, generates a second image signal asynchronously;
an inertial sensor that acquires attitude information on the first image sensor and the second image sensor;
a first computation processing device that recognizes a user on a basis of at least the second image signal and calculates coordinate information regarding the user on the basis of at least the second image signal;
a second computation processing device that performs coordinate conversion on the coordinate information on a basis of the attitude information; and
an image generation device that generates a display image which indicates a condition of the user, on a basis of the converted coordinate information.
2 . The system according to claim 1 , further comprising:
a positional information acquisition section that acquires positional information on the first image sensor and the second image sensor; and
an inference section that infers a relative positional relation between a display apparatus displaying the display image and the first and second image sensors on a basis of the positional information and the attitude information, wherein
the second computation processing device performs the coordinate conversion based on the positional relation.
3 . The system according to claim 1 , wherein the coordinate information includes at least one of coordinate information regarding a posture of the user, coordinate information regarding a shape of a user's arm, coordinate information regarding a shape of a user's hand/finger, and coordinate information regarding an attitude of an external apparatus being mounted on or being held by the user.
4 . The system according to claim 1 , wherein the first computation processing device calculates coordinate information regarding at least one joint of the user according to a learned model that is constructed by learning of a relation between an image of a person having multiple joints and coordinate information indicating positions of the multiple joints.
5 . The system according to claim 1 , further comprising: a warning section that performs a warning action when a change in the attitude information exceeds a prescribed threshold value.
6 . The system according to claim 1 , further comprising:
a sensor apparatus that includes the first image sensor, the second image sensor, the inertial sensor, and the first computation processing device; and
an information processing apparatus that includes the second computation processing device and the image generation device, wherein
the sensor apparatus outputs the attitude information and the coordinate information to the information processing apparatus.
7 . An information processing method for generating a display image to be displayed on a display apparatus, the method comprising:
acquiring a first image signal generated by a first image sensor that synchronously scans all pixels at a prescribed timing, and a second image signal generated by a second image sensor including an event-driven type vision sensor that, upon detecting a change in an intensity of incident light on each of the pixels, generates the second image signal asynchronously;
recognizing a user on a basis of at least the second image signal and calculating coordinate information regarding the user on the basis of at least the second image signal;
performing coordinate conversion on the coordinate information on a basis of attitude information on the first image sensor and the second image sensor; and
generating the display image so as to indicate a condition of the user, on a basis of the converted coordinate information.
8 . A non-transitory, computer readable storage medium containing a computer program, which when executed by a computer, causes the computer to perfrom an information processing method for generating a display image to be displayed on a display apparatus, by carrying out actions, comprising:
a function of acquiring a first image signal generated by a first image sensor that synchronously scans all pixels at a prescribed timing, and a second image signal generated by a second image sensor including an event-driven type vision sensor that, upon detecting a change in an intensity of incident light on each of the pixels, generates the second image signal asynchronously;
recognizing a user on a basis of at least the second image signal and calculating coordinate information regarding the user on the basis of at least the second image signal;
performing coordinate conversion on the coordinate information on a basis of attitude information on the first image sensor and the second image sensor; and
generating the display image which indicates a condition of the user, on a basis of the converted coordinate information.