Information processing device, information processing method, and control program
The information processing device uses adversarial imitation learning to generate fish farm images automatically, addressing the limitations of manual parameter specification and improving reproducibility by employing a generator and classifier to adjust fish behavior and spacing.
JP2026084433AActive Publication Date: 2026-05-21SOFTBANK CORPORATION +1
View PDF 10 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- SOFTBANK CORPORATION
- Filing Date
- 2024-11-11
- Publication Date
- 2026-05-21
AI Technical Summary
Technical Problem
Conventional methods for generating simulated images of fish farms require users to manually specify parameters like swimming behavior and spacing between fish, limiting image reproducibility and increasing user workload.
Method used
An information processing device employs adversarial imitation learning using a generator and classifier to generate images, involving an acquisition, generation, extraction, calculation, and learning process to improve reproducibility without manual parameter specification.
Benefits of technology
Reduces user burden while enhancing the reproducibility of simulation images by automatically adjusting fish behavior and spacing based on biological rules and reward functions.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure 2026084433000001_ABST
Abstract
To reduce user load while improving the reproducibility of simulation images. [Solution] An information processing device (100) that performs adversarial imitation learning using a generator and a classifier, comprising: an acquisition unit (11) that acquires a reference image of a region including an object; a generation unit (12) that performs processing as a generator, and generates a generated image according to a policy model that is updated according to a reward function; an extraction unit (14) that inputs the reference image to an autoencoder to extract latent variables corresponding to the reference image and also inputs the generated image to an autoencoder to extract latent variables corresponding to the generated image; a calculation unit (15) that inputs each extracted latent variable to a classifier that identifies whether it corresponds to a latent variable in the reference image or the generated image, and updates the reward function according to the output result of the classifier; and a learning unit (17) that updates the policy model according to the updated reward function.
Need to check novelty before this filing date? Find Prior Art