INFORMATION PROCESSING DEVICE

• US 20180082178A1
• Filed: 12/27/2016
• Published: 03/22/2018
• Est. Priority Date: 03/28/2016
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: NAKAMURA, Akira, NARIHIRA, Takuya, FUJITA, Takuya
• Granted Patent: US 10,430,707 B2
• Time in Patent Office: Days
• CPC Class Codes: G01V 20/00 Geomodelling in general
• CPC Class Codes: G06F 2111/10 Numerical modelling
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G06N 3/006 based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06T 17/05 Geographic models
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 3/4046 using neural networks
• CPC Class Codes: G06T 7/55 from multiple images

Abstract

There is provided an information processing device to improve generalization performance of the neural network, the information processing device including: a control unit configured to control display related to a setting of a parameter related to physical simulation; a communication unit configured to transmit the parameter to a physical simulator and receive image information obtained in the physical simulation from the physical simulator; and a machine learning unit configured to perform machine learning on the basis of the image information. The control unit causes a display unit to display a learning result obtained by the machine learning unit and the parameter in association with each other.

Claims

1. An information processing device comprising:

a control unit configured to control display related to a setting of a parameter related to physical simulation; and

a communication unit configured to transmit image information associated with the parameter obtained in the physical simulation to a machine learning unit and receive a determination result based on the image information from the machine learning unit,

wherein the control unit causes a display unit to display the determination result and the parameter in association with each other.

2. The information processing device according to claim 1,

wherein the setting of the parameter includes a parameter range indicating a range of a value of the parameter, and

the control unit causes the display unit to display the determination result and the parameter range in association with each other.

3. The information processing device according to claim 2,

wherein the setting of the parameter further includes division information related to the parameter range,

the control unit further causes the display unit to display the determination result and the division information in association with each other, and

the image information is acquired on the basis of the parameter range and the division information.

4. The information processing device according to claim 2,

wherein the control unit sets a new parameter on the basis of the determination result, and causes the display unit to display the determination result and the new parameter in association with each other.

5. The information processing device according to claim 4,

wherein the determination result is true-false information of determination on the image information,

the control unit sets a new parameter range on the basis of a determination result indicating an erroneous determination, and

the new parameter range includes a value of the parameter associated with the determination result indicating the erroneous determination and is narrower than the parameter range associated with the determination result.

6. The information processing device according to claim 5,

wherein the control unit controls display such that the determination result indicating the erroneous determination is enlarged.

7. The information processing device according to claim 4,

wherein the control unit sets a new parameter range that does not include the parameter range associated with the determination result.

8. The information processing device according to claim 1,

wherein the control unit causes the display unit to display the determination result together with an indicator related to a value of the parameter.

9. The information processing device according to claim 1,

wherein the parameter is set or changed by a user.

10. The information processing device according to claim 1,

wherein the control unit further causes the determination result and an image generated on the basis of the image information to be displayed in association with each other.

11. The information processing device according to claim 1, further comprising

a simulator unit configured to perform the physical simulation.

12. The information processing device according to claim 11, further comprising:

a model acquiring unit configured to acquire a three-dimensional model generated from a two-dimensional image,

wherein the simulator unit performs the physical simulation using the three-dimensional model generated from the two-dimensional image.

13. The information processing device according to claim 12,

wherein the model acquiring unit acquires a three-dimensional model generated by SLAM.

14. The information processing device according to claim 13,

wherein the parameter related to the physical simulation further includes a three-dimensional model parameter,

the model acquiring unit acquires the three-dimensional model on the basis of the three-dimensional model parameter, and

the three-dimensional model parameter includes at least one of the number of feature points to be extracted, a matching threshold value of a feature point, and a range of a feature point used for a camera parameter calculation.

15. The information processing device according to claim 12,

wherein the control unit causes the display unit to display at least one of the two-dimensional image, an image generated on the basis of the image information, and an execution image of the physical simulation.

16. The information processing device according to claim 1,

wherein the communication unit transmits a compensation related to the image information to the machine learning unit.

17. The information processing device according to claim 1,

wherein the communication unit receives a plurality of the determination results determined by a plurality of neural networks having different network structures.

18. An information processing device comprising:

a control unit configured to control display related to a setting of a parameter related to physical simulation;

a communication unit configured to transmit the parameter to a physical simulator and receive image information obtained in the physical simulation from the physical simulator; and

a machine learning unit configured to perform machine learning on the basis of the image information,

wherein the control unit causes a display unit to display a learning result obtained by the machine learning unit and the parameter in association with each other.