SoftBank Corp. and Aizip, Inc.’s
Real-Time Fish Counting Application with
On-Device AI Wins Innovation Award at CES® 2025

Softbank Corp. (“SoftBank”) and Aizip, Inc. (California, USA, “Aizip”) have collaborated on the development of an on-device machine learning application for counting fish, for edge devices such as smartphones, and this application was selected for an Innovation Award in the Food & AgTech category at CES® 2025.

For the past few years, SoftBank has been conducting research to develop a real-time fish counting solution to enhance the operational efficiency of aquaculture operators. For this research, using an AI model created with SoftBank’s computer graphics (CG) simulation technology and Aizip’s compact AI technology, SoftBank and Aizip developed an AI application to count fish on smartphones. This miniature and low-power AI model utilizes Tiny Machine Learning (TinyML), but is still capable of counting fish underwater with 95% accuracy. In addition, SoftBank and Aizip also used TinyML technology to develop an SLM (Small Language Model) that can use RAG (Retrieval-Augmented Generation) for a smartphone QA (Questions and Answers) application.

SoftBank and Aizip will be presenting the applications at CES® 2025 on January 7, 2025, in Las Vegas.

Real-time data capture and analysis on smartphones and other edge devices is becoming increasingly important for DX (digital transformation) and operational efficiency in primary industries. Through this joint research program, the possibilities of using AI applications in a marine environment and for improvements in efficiency for the aquaculture industry are clear. By making use of TinyML, the opportunities for using smartphones in environments without networks, such as the open ocean, mountaintops or in airplanes can be expanded.

By making it possible to run AI applications on edge devices, SoftBank and Aizip seek to revolutionize industry.

The details of the joint research are below.

On-device Fish Counting AI Application

SoftBank had been developing a cloud-based AI system designed for fish counting to enhance the operational efficiency of aquaculture operators. However, the system’s reliance on a server-based architecture presented challenges, particularly in securing power and communication for real-time underwater analysis. To overcome these limitations, a power-efficient, low-memory machine learning model capable of running on edge devices, such as smartphones, was needed.

To solve these problems, an AI model that can do real-time analysis on edge devices was developed, using SoftBank’s CG fish schooling simulation to automatically create a training dataset for Aizip’s compact TinyML technology. TinyML is known for being low power and small scale, able to run on edge devices, and yet it has similar accuracy to large, server level neural networks. For this research, a TinyAI model was optimized for counting fish, and successfully counted fish underwater, in real-time, with a standard smartphone camera, with 95% accuracy. Using this technology, the possibilities of using AI applications in a marine environment and for improvements in efficiency for the aquaculture industry are clear.

QA Application with a Built-In SLM

To investigate the possibilities of TinyML, SoftBank collaborated with Aizip to develop an employee QA system. While Large Language Models (LLMs) have made it possible to answer general questions, they typically require powerful servers to operate. However, for internal systems that only need to address specialized domains, edge device operation is preferred for lower power consumption and enhanced information security when handling sensitive internal data. Shrinking language models to fit resource-constrained edge devices while maintaining cloud-level generation quality presents a significant challenge. Aizip has addressed this by developing SLMs that not only run efficiently on mobile devices but also deliver generation quality comparable to cloud-based models through fine-tuning on task-specific datasets. Furthermore, the SLM is integrated into a RAG system that includes a database of employee service documents. This setup enables rapid adaptation to evolving data without requiring the SLM to be retrained. The newly developed QA system can clarify user questions by allowing the model to interact with ambiguous queries, achieving an impressive 96% accuracy rate in our in-house QA system. Future research is expected to deliver further accuracy improvements.

Tiny Machine Learning (TinyML) overview diagram

SoftBank and Aizip succeeded in reducing power consumption and size, allowing real-time execution on a smartphone, without reducing accuracy.

Results of the Demonstration Experiment