ποΈ Retail People Counter Real-Time Entry/Exit Flow System
I built a real-time people counting system ππ₯ using YOLOv8 and OpenCV. It detects and tracks people crossing a line to count entries, exits, and net flow π, perfect for retail stores, gyms, or events. Supports video files, webcams, and live streams, with clear visual overlays so you see the numbers in real time.
Helps businesses make data-driven decisions on staffing, layout, and visitor flow based on accurate, real-time analytics
Demo
Demo
π― Features
π¬ Real-time People Detection: Uses YOLOv8 Large model for accurate person detection
π Flexible Line-Based Counting: Horizontal or vertical line orientation for any movement direction
π Net Flow Analysis: Shows honest flow metrics instead of misleading occupancy counts
π₯ Multiple Input Sources: Support for video files, webcam, and live footage
π§ Optimized Performance: Fine-tuned confidence thresholds and tracking parameters
πΎ Export Capability: Save processed video with counting overlays
β
Automatic Setup: Downloads required YOLO models automatically
ποΈ Command Line Interface: Comprehensive argument system for full control
π What It Measures
Important: This system tracks Entry/Exit Flow, not absolute occupancy:
β
Accurate: "12 people entered, 11 people left during this period"
β
Honest: "Net flow: +1 person increase"
β Not claiming: "There are exactly X people in the area"
This is perfect for understanding traffic patterns, peak hours, and directional flow!
0 likes Β· 20 views Β· Aug 13, 2025
Realβtime, honest people flow tracking system using YOLOv8 and OpenCV: see exactly how many people entered, exited, and the net change on screen
Timeline
Mar 13, 2024 - Apr 13, 2024