egohos-segmentation
Egocentric Hand-Object Segmentation (EgoHOS) - pixel-level hand and object segmentation in egocentric videos. Outputs fine-grained segmentation masks with hand regions highlighted. Specialized for hand-object interaction scenarios with pixel-accurate masks. Ideal for detailed interaction analysis.
npx skills add BioTender-max/awesome-bio-agent-skills --skill egohos-segmentation --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# EgoHOS - Egocentric Hand-Object Segmentation ## Overview Fine-grained hand-object segmentation system designed for egocentric (first-person) videos. EgoHOS provides pixel-level segmentation masks that precisely separate hands from objects and background, enabling detailed analysis of hand-object interactions. The system outputs colorful mask overlays that make hand regions visually distinct and easy to analyze. **Key advantage**: Pixel-level accuracy for understanding hand-object boundaries and contact regions, surpassing bounding box or keypoint approaches for interaction understanding. ## When to Use This Skill This skill should be used when: - Need pixel-accurate hand and object masks in egocentric videos - Analyzing hand-object manipulation and interactions - Studying contact regions between hands and objects - Creating training data for segmentation models - Applications requiring precise hand shape and outline - Research in fine-grained activity recognition - Building systems that need to understand hand-object contact - Generating annotated videos with segmentation overlays **Choose this when**: You need pixel-level segmentation of hands and objects, not just bounding boxe
- Overview
- When to Use This Skill
- Core Capabilities
- 1. Pixel-Level Segmentation
- 2. Video Processing with Mask Overlay
- 3. Hand-Object Interaction Analysis
- 4. Batch Processing
- Installation and Setup
- Usage Examples
- Example 1: Basic Video Segmentation
- Example 2: Extract Hand and Object ROIs
- Example 3: Track Hand-Object Contact Over Time
- Example 4: Generate Training Data
- Model Specifications
Clone repository git clone https://github.com/owenzlz/EgoHOS.git cd EgoHOS Install dependencies pip install torch torchvision opencv-python numpy pillow Download pre-trained models bash scripts/download_models.sh Run segmentation on video python demo.py \ Create virtual environment
What does the egohos-segmentation skill do?
Egocentric Hand-Object Segmentation (EgoHOS) - pixel-level hand and object segmentation in egocentric videos. Outputs fine-grained segmentation masks with hand regions highlighted. Specialized for hand-object interaction scenarios with pixel-accurate masks. Ideal for detailed interaction analysis.
How do I install it?
Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill egohos-segmentation --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From BioTender-max/awesome-bio-agent-skills, a repository with 144 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.