README.md

---
title: Farm Human Recognition API
emoji: 👥
colorFrom: purple
colorTo: pink
sdk: gradio
sdk_version: 4.28.3
app_file: app.py
pinned: false
license: apache-2.0
short_description: Farm worker detection and safety analysis
---

# 👥 Farm Human Recognition API

Advanced farm worker detection and analysis using YOLOS models for workplace safety and productivity assessment.

## 🎯 Capabilities
- **Worker Detection**: Precise identification of farm workers in images
- **Safety Analysis**: Workplace safety scoring and risk assessment
- **Activity Recognition**: Classification of farm work activities
- **Productivity Metrics**: Performance analysis and recommendations

## 🤖 Models
- **YOLOS Tiny**: Fastest processing for real-time applications
- **YOLOS Small**: Balanced accuracy and speed (recommended)
- **YOLOS Base**: Highest accuracy for detailed analysis

## 📡 API Usage

### Python
```python
import requests
import base64

def detect_farm_workers(image_path, model="yolos_small"):
    with open(image_path, "rb") as f:
        image_b64 = base64.b64encode(f.read()).decode()
    
    response = requests.post(
        "https://YOUR-USERNAME-farm-human-recognition.hf.space/api/predict",
        json={"data": [image_b64, model]}
    )
    return response.json()

result = detect_farm_workers("farm_workers.jpg")
print(result)
```

## 📊 Response Format
```json
{
  "humans_detected": 3,
  "detections": [
    {
      "class": "person",
      "confidence": 0.92,
      "bbox": [120, 45, 180, 200],
      "activity": "ground_work",
      "area": 7200
    }
  ],
  "safety_analysis": {
    "status": "safe",
    "score": 0.85,
    "concerns": [],
    "workers_detected": 3
  },
  "productivity_metrics": {
    "active_workers": 3,
    "productivity_score": 0.75,
    "activity_breakdown": {
      "ground_work": 2,
      "operating_equipment": 1
    },
    "recommendations": [
      "Consider team coordination for efficiency"
    ]
  },
  "processing_time": 1.5
}
```

## 🏭 Activity Classification
- **ground_work**: Field operations, planting, harvesting
- **close_work**: Inspection, detailed tasks, quality control
- **operating_equipment**: Tractor/machinery operation
- **general_activity**: Walking, standing, general movement

## 🛡️ Safety Features
- Automatic detection of high worker density
- Equipment operation safety analysis
- Workplace hazard identification
- Safety score calculation (0-1)