2022.03.25 News

NEXT-SYSTEM Utilizes Honda Technology To Create AI-FIT, a General-purpose Module That Allows Users To Generate an Avatar According to Their Body Shape

Including a Seating Simulation Application Using Pose Estimation AI Technology

Automatic 3DCG Human Body Transformation Module “AI-FIT” Banner

NEXT-SYSTEM Co., Ltd. has launched a project utilizing the technology* of Honda Motor Co., Ltd. By combining Honda’s technology, which calculates the length of limbs from skeletal estimation systems, with NEXT-SYSTEM’s AI pose estimation engine "VisionPose", which detects a person’s skeletal information without attaching markers or other equipment to the body, a general-purpose module has been developed. This module automatically measures the body size of the user through taking a picture with a smartphone, and adapts those measurements to an avatar (3DCG human body). The module will be available starting March 24, 2022.

*This module uses technology of Honda Motor Company, Co., Ltd. (patent application numbers PCT/JP2020/049064 and PCT/JP2020/049065)

What is the Automatic 3DCG Human Body Transformation Module “AI-FIT”? 

This general-purpose module combines Honda's technology and NEXT-SYSTEM’s pose estimation AI technology to automatically transform an avatar (3DCG of the human body) so that it matches the user's body shape. The user only has to take a picture of their whole body with a smartphone camera, and the module will automatically measure the size of 11 areas in their body, such as the legs, arms, and waist.

Automatic 3DCG Human Body Transformation Module “AI-FIT” Image Picture

Automatic 3DCG Human Body Transformation Module “AI-FIT” Image Picture

“AI-FIT" also includes a sample application that can visually simulate the pose of the user while seated on a chair or other object, allowing them to check the percentage of ground contact of their feet when sitting. The application is customizable and can be applied in a variety of fields and industries, including furniture manufacturing, since other than chairs, the seating object can be changed to car seats, sofas, etc.

Automatic 3DCG Human Body Transformation Module “AI-FIT” Footing Rate Measurement Demo Image Picture

Automatic 3DCG Human Body Transformation Module “AI-FIT” Footing Rate Measurement Demo Image Picture

Customizable Parts

・3DCG model of the human body
・3DCG model of the chair
・Reference point for each body part when seated

Automatic 3DCG Human Body Transformation Module “AI-FIT” Product Information

Price: 198,000YEN(tax excluded)
Package Contents:
・AI-FIT Module (Sample App included)

Website of the Automatic 3DCG Human Body Transformation Module “AI-FIT”
(in Japanese language only)

Future Outlook

This module can also be applied to the recently rapidly expanding metaverse market. By using the data acquired with this module, it will be possible to create a realistic 3D avatar closely resembling the physique of a real person by only using a single smartphone, and to integrate this avatar into the metaverse space.

A realistic 3D avatar that is modeled after a user is highly compatible to business or to fitting of clothes in virtual spaces and similar. By reflecting not only the texture of the face but also the physique, it is possible to create a more realistic version of oneself.

What is VisionPose?

VisionPose is an AI pose estimation engine that detects human skeleton information on real-time camera images, still images and videos, without the need for markers or special equipment. The AI is capable of detecting skeletal information of 30 key points in 2D and 3D in real-time and comes with two ready-to-use applications in addition to the SDK, so the user can start analyzing immediately after setting up their PC. As an all-around SDK package, it has already been applied to various fields in development and research and has been implemented by over 250 clients inside of Japan. Sale outside of Japan has started with three products, VisionPose Standard for Windows C# C++, and Linux, and the number of supported platforms will be expanded sequentially.

VisionPose Functions

・Detection of up to 30 keypoints in the human body at up to 60 FPS in real-time
・3D inference with 2 cameras and 3D inference with a single camera 
・Two ready-to-use apps:
1) “BodyAndColor” (source code included) For analyzing video streams in real-time
2) “VP Analyzer” For analyzing electronic files of videos or still images
・SDK without usage restrictions
・30-day free trial before purchase

For more information, see the VisionPose official website,
or contact us.

About NEXT-SYSTEM Co., Ltd.
NEXT-SYSTEM is a Japanese system development company founded in Fukuoka City in 2002, and since then has been focused on the research of behavior analysis through AI technology, ergonomic system development and research, development of cutting-edge systems, such as xR (AR/VR/MR), and the development and sales of their Pose Estimation AI Engine “VisionPose” and AR Signage System “Kinesys”.

Company Website 

Visit us on social media: