Pose AI – An AI-based, lightweight, cross-platform tool to Detect and Digitize human poses in a video stream.

Features include Multi-Person Pose estimation, Multi-Person detection & tracking, Real-time Live PoseAI, etc. The library is computationally inexpensive, and can precisely localize key points by accurately detecting the person.

Salient Characteristics

Accurate

Accurate Person detection

Precise Keypoint localization

High-Quality Model for higher Accuracy

Fast

Computationally inexpensive

Pre-Optimized for Intel/Nvidia accelerators

High Performant Model for higher performance

Robust

Person Tracking with unique ID mapping

Light Weight Python and C API

Plug & Play on customer hardware pipeline

Feature extensible

Portable

Target OS Agnostic

Portable onto embedded RTOS

Minimal external dependency

Performance

PoseAI delivers more than 97%+ accuracy for Multi-Person Pose Estimation covering Upright poses with minimal occlusion.

Superior Real-time performance on CPU and GPU.

High accuracy model delivers superior accuracy in predicting human joints

High-performant model delivers superior performance over real-time.

Use Cases:

Watch PoseAI in action here

Gesture Gaming demo here