Markerless motion capture "VisionPose"
VisionPose is an in-house developed AI posture estimation engine that can detect skeletal information of multiple people using only a web camera.
VisionPose is an SDK (Software Development Kit) for a high-precision posture estimation AI engine that detects human skeletal information in real-time from camera footage. The skeletal data obtained from the analysis can be used for commercial purposes as well as research and development, regardless of application or genre. ■ Features - Capable of detecting 30 key points of the human body in real-time at up to 60 FPS (varies with PC specifications) - Supports 3D inference with two cameras (Standard) and 3D inference with one camera (Single3D) - Comes with two ready-to-use applications as standard - No restrictions on usage, including commercial use - Provided as an SDK, allowing development in C#/C++/Swift - Additional training is possible (additional training is an optional service and has conditions for implementation) ■ Application Areas - Sports motion analysis - Medical/rehabilitation gait analysis - Analysis of workers' tasks in industrial/factory settings - Robot motion analysis - Video analysis and monitoring of network cameras (IP cameras) - Detection of animal skeletons and posture detection - Simple motion capture for entertainment (games, avatar control)
- Company：ネクストシステム 福岡本社
- Price：100,000 yen-500,000 yen
