🚗 Traffic Bird's Eye View Object Detection

Upload an aerial/bird's eye view image to detect traffic objects!

This application uses a specialized YOLOv8 model trained for traffic detection from aerial perspectives. Perfect for analyzing drone footage, satellite images, or overhead traffic cameras.

Supported formats: JPG, PNG, JPEG

Features:

• 🚗 Specialized traffic detection model
• 🎚️ Adjustable confidence threshold slider
• 📥 Download detection results as CSV
• 📊 Real-time filtering based on confidence scores
• 🖼️ Example images to try out

How it works:

1. Upload an aerial/bird's eye view image or select from examples below
2. Adjust the confidence threshold slider to filter detections (default: 0.25 = 25%)
3. View the annotated image with bounding boxes and labels for detected traffic objects
4. Analyze the detection data in the table with confidence scores and coordinates
5. Download the results as a CSV file for further analysis

Best Results: This model works best with:

• 🚁 Drone footage of roads and traffic
• 🛰️ Aerial photography of urban areas
• 📹 Overhead traffic camera feeds
• 🗺️ Bird's eye view street scenes

Confidence Threshold Guide:

• 0.01-0.20: Very permissive - shows many detections, including uncertain ones
• 0.25-0.50: Balanced - good mix of accuracy and detection count (recommended)
• 0.50-0.80: Conservative - only high-confidence detections
• 0.80-1.00: Very strict - only extremely confident detections

Try the example images below to see the model in action!