Ideal for research and verification of skeletal information! An easy-to-use posture estimation AI engine with included hardware.
"VisionPose Nano" is a posture estimation AI engine that can detect skeletal information using only a webcam. It can detect a total of 30 skeletal points, including 25 joint locations on the body and 5 facial features, in 2D coordinates. Additionally, the acquired data can be exported in CSV format. Please format the exported data for analysis and other uses. ■ Features - Capable of skeletal detection with camera footage in both video and still images - Provided with hardware, achieving low cost and space efficiency - No complicated setup or installation required - Detects 30 key points, allowing easy export of skeletal information in CSV format ■ Included Applications - Posture measurement app "PoseMeasure" - VP Analyzer - BodyAndColor *For more details, please download the PDF or feel free to contact us.
Inquire About This Product
basic information
■Specifications - VisionPose is equipped with our standard pre-trained model. - The OS is NVIDIA Jetson Linux. - The analysis speed is based on the FPS value when using the included real-time video analysis app "BodyAndColor." - The "Jetson Orin Nano" allows for configuration changes between "speed-focused" and "accuracy-focused" settings. - This product does not come with an SDK. It is intended for research use and cannot be used for commercial purposes. ■Regarding the included hardware - The fan and microSD card will be delivered pre-installed in the main unit. - Monitor, keyboard, mouse, and HDMI cable are not included. - The hardware case may change depending on stock availability. There will be no impact on functionality or performance.
Price information
■Jetson Nano 【Purchase Price】98,000 yen (excluding tax) 【Package Contents】 ・Camera: 1 unit / 2D analysis ・Key Points: 30 points ・Analysis Speed (Reference Value): 4 FPS ■Jetson Orin Nano 【Purchase Price】149,800 yen (excluding tax) 【Package Contents】 ・Camera: 1 unit / 2D analysis ・Key Points: 30 points ・Analysis Speed (Reference Value): Speed-focused 30 FPS, Accuracy-focused 12 FPS
Price range
P3
Delivery Time
Applications/Examples of results
VisionPose Nano is an affordable product that is ideal for research and verification of skeletal analysis. When you contact us, we will respond to your needs based on our achievements and examples. Additionally, Next System has numerous development achievements and products in AI and XR (AR/VR/MR), so we can offer various approaches beyond this product. Please feel free to reach out to us. ■ Next System Website https://www.next-system.com ■ Product List https://www.next-system.com/product/ ■ Development Examples https://www.next-system.com/solution/ ■ Contact Information https://www.next-system.com/contact/ *For more details, please download the PDF or feel free to contact us.
Detailed information
-
VisionPose is a domestic AI posture estimation engine that enables skeletal detection through deep learning inference and analysis (PoseEstimation). The analyzed skeletal information can be applied in various fields and uses, realizing new services and functions. Additionally, there are no usage restrictions for this product, and it can be used permanently with a one-time purchase.
-
Pose Estimation is an AI technology that estimates the posture of individuals from videos and images without the use of markers. VisionPose Single3D utilizes technology to estimate 3D coordinates from 2D images, allowing for the detection of up to 30 key points in 2D coordinates and up to 17 key points in 3D coordinates using a single camera to capture human skeletal information. It can be used as an alternative to depth sensor-equipped cameras for motion capture.
-
This is our proprietary edge AI solution for posture estimation that operates on edge devices. In traditional IoT development, it was common to process AI's vast computational tasks in the cloud via the internet or to store acquired information in the cloud. However, this reliance on cloud communication can compromise real-time performance and introduce security risks associated with storing data in the cloud. In response, edge computing has emerged as a technology gaining attention alongside advancements in hardware. Recent improvements in hardware have enabled the rapid processing of AI's extensive computational tasks directly on devices in the field. It is compatible with NVIDIA's compact edge devices for AI deep learning, including "Jetson AGX Xavier," "Jetson Xavier NX," and "Jetson Nano."
-
Without attaching markers or anything to the body, it is possible to detect human movement in real-time from camera footage. Therefore, it can be used as a simple motion capture for avatar control in games and smartphones.
-
It can be used for posture assessment and movement evaluation in fields such as sports.
-
It can be used for evaluating the work of factory operators and detecting abnormal work (incorrect work).
-
VisionPose detects a total of 30 skeletal points by default. Additionally, VisionPose provides an annotation tool, allowing for accuracy improvement through additional training on areas with weak detection, as well as the ability to add skeletal points, detect only hand positions, and apply it to animals.
catalog（4）
Download All Catalogs
Company information
Under the corporate vision of "Turning dreams into reality and creating the future," we are developing cutting-edge systems and providing services through the fusion of the latest technologies (AI, XR) and content (3DCG, Movies, Music). Our uniquely developed posture analysis AI engine, "VisionPose," has already been provided to over 400 companies in Japan and is utilized in sports motion analysis, rehabilitation walking analysis, work analysis of factory workers, and entertainment-related motion capture, among others. (Examples of implementation) - Provided VisionPose to Toyota's walking assist robot "Welwalk WW-2000." - Provided VisionPose to Avex's dance skill scoring smartphone app "Dance COMMUNE." Additionally, we can perform time-series behavior analysis and abnormal behavior analysis by incorporating time-series analysis to analyze a series of movements. Furthermore, we apply ergonomic evaluations for work load analysis. Our AR signage "Kinesys" has been implemented in over 100 companies in Japan and is used for virtual fitting and interaction services.