Getting Started GuideΒΆ
This section provides the fundamental information needed to understand and use StreamPoseML.
- Installation
- Quick Start Guide
- Core Concepts
- Understanding how StreamPoseML works
- Pose Detection and Keypoint Extraction
- From Frames to Movement: Sequence Processing
- Making Movement Measurable: Feature Engineering
- Building Your Movement Library: Dataset Creation
- Teaching Computers to Recognize Movements: Model Training
- Putting It All Together: Real-time Classification
- Where to Go From Here
- Annotation Format and Usage
- Segmentation Strategies Explained
- Understanding Segmentation in StreamPoseML
- Why Segmentation Matters
- Available Segmentation Strategies
- Strategy 1: None
- Strategy 2: Split on Label
- Strategy 3: Window
- Strategy 4: Flatten into Columns
- Strategy 5: Flatten on Example
- Choosing the Right Segmentation Strategy
- Practical Example
- Advanced Usage
- Conclusion
- OpenPose and MediaPipe Integration
- Understanding Pose Format Compatibility
- Why Pose Format Compatibility Matters
- How the Conversion Works
- The Transformation Process
- Key Differences Between BlazePose and OpenPose
- Joint Mapping
- How to Use OpenPose Compatibility
- Important Implementation Details
- The Plumb Line Concept
- Example Code
- Limitations
- Conclusion