VisionPose

More than 250 companies

High-precision AI posture analysis engine that analyzes behaviors and actions from human posture information

About VisionPose

A Pose Estimation AI engine, enabling high-precision analysis for human skeletal and pose information, provided by NEXT-SYSTEM Co., Ltd. This can analyze not only camera images but also still images and videos without markers.Also, it supports 2D/3D analysis.

Features

  • Supports camera images, still images, and videos

    Support for camera images, still images, and videos

  • 2D and 3D coordinate analysis is possible

    2D and 3D coordinate analysis is possible

  • Broad platform support

    Broad platform support

  • Commercial use is possible without usage restrictions

    Commercial use is possible with no usage restrictions

  • Improved accuracy by additional learning

    Accuracy improvement by additional learning

  • Detects up to 30 body keypoints

    Detects up to 30 body keypoints

  • Multi-person detection is possible

    Multi-person detection is possible

  • Includes ready-to-use skeleton detection tool

    Skeletal detection tool included for immediate use

  • Made in Japan

    Made in Japan

Cases

More than 250 cases
TOYOTA

Toyota Motor Corporation

Wellwalk WW-2000, a robot that assists in the rehabilitation of lower limbs paralyzed by strokes and other injuries, utilizes VisionPose.

avex management

Avex Management Inc.

“Avex Street Dance Exam” App, which realizes score evaluation of dance skills through video analysis, is equipped with VisionPose.

SPORTS SCIENCE LABORATORY

Sports Science Laboratory

Using VisionPose as an Artificial Intelligence App to view easy injury pitching actions.

Lineup

VisionPose provides a set of SDK and skeletal detection tools that are useful for analysis.
Single purchase allows you to use the software permanently, with no restrictions on usage.

VisionPose Standard

Standard SDK for accuracy-oriented. 2D/3D analysis with 30 body keypoints detection and up to 60FPS* for the whole body.

* Varies depending on PC specs.

1 camera / 2D analysis / 30 keypoints

2 cameras / 3D analysis / 30 keypoints

* No camera required for file analysis
Windows C#,C++

Windows C#,C++
Linux

Compatible with network cameras or IP cameras.
※Cloud environment is available.

small edge devices

Jetson AGX Xavier
Jetson Xavier NX

Support for NVIDIA small edge devices with the same precision. For IoT development that requires space-saving integration.

VisionPose Single3D

SDK with monocular 3D analysis function. It allows you to capture motion easily without calibration.

1 camera / 2D analysis / 30 keypoints

1 camera / 3D analysis / 17 keypoints

* File analysis does not require a camera, iOS / iPad OS cannot analyze files.
* Separate application development is required for camera control of iOS / iPad OS.
iOS/iPadOS

iOS/iPadOS

SDK for iPhone / iPad application development. For application development using motion capture.

Windows Unity

Windows Unity

For creating animations of CG characters and developing games in Unity.

Email support

We will respond to e-mails during business hours (reply on the next business day).
If there is no support contract, best-effort support is provided.