Crowd monitoring Branch created

26_T1/afl_player_tracking_and_crowd_monitoring/Crowd_Monitoring/2026_T1/.gitignore

@@ -0,0 +1,60 @@
+# Python cache and build artifacts
+__pycache__/
+*.py[cod]
+*.pyo
+*.pyd
+*.so
+*.egg-info/
+build/
+dist/
+
+# Virtual environments
+.venv/
+venv/
+env/
+ENV/
+
+# Notebook and editor artifacts
+.ipynb_checkpoints/
+.vscode/
+.idea/
+
+# Test and coverage output
+.pytest_cache/
+.coverage
+.coverage.*
+htmlcov/
+
+# Logs and local environment files
+*.log
+.env
+.env.*
+
+# Model artifacts
+*.pt
+*.pth
+*.onnx
+
+# Data and generated outputs
+data/
+outputs/
+results/
+runs/
+checkpoints/
+temp/
+tmp/
+
+# Media artifacts
+*.mp4
+*.avi
+*.mov
+*.mkv
+*.png
+*.jpg
+*.jpeg
+*.csv
+*.json
+
+# OS files
+.DS_Store
+Thumbs.db

26_T1/afl_player_tracking_and_crowd_monitoring/Crowd_Monitoring/2026_T1/README.md

@@ -0,0 +1,151 @@
+# Crowd Monitoring Module (Orion Project)
+
+## Overview
+
+This repository contains the Crowd Monitoring module for the Orion project under Redback Operations.
+
+The purpose of this module is to analyse stadium crowd behaviour and density using computer vision and data analytics. The expected outputs include:
+
+- crowd heatmaps
+- density metrics
+- zone-based analytics
+- behaviour insights for integration into the Orion analytics dashboard
+
+## Objectives
+
+- Detect and analyse spectators in stadium footage
+- Estimate crowd density and distribution
+- Generate zone-based crowd analytics
+- Produce crowd heatmaps and visualisations
+- Develop AI-based crowd behaviour analysis
+- Optionally predict future attendance using machine learning models
+
+## Proposed Pipeline
+
+```text
+Video Input
+    |
+    v
+Frame Extraction (OpenCV)
+    |
+    v
+Person Detection (YOLOv8)
+    |
+    v
+Crowd Density Estimation
+    |
+    v
+Zone-based Analysis
+    |
+    v
+Heatmap Generation
+    |
+    v
+Analytics Output (JSON / CSV)
+    |
+    v
+Behaviour Analysis / Prediction
+```
+
+## Tech Stack
+
+- Python
+- YOLOv8 (Ultralytics)
+- OpenCV
+- NumPy
+- Pandas
+
+## 👥 Team Tasks (7 Members)
+
+Each team member owns one task. Follow the README in each task folder for detailed objectives and deliverables.
+
+| # | Task Folder | Team Member | Objective |
+|---|-------------|-------------|-----------|
+| 1 | **video_processing** | Member 1 | Extract frames and prepare video data |
+| 2 | **crowd_detection** | Member 2 | Detect persons using YOLOv8 |
+| 3 | **density_zoning** | Member 3 | Calculate density and zone-based analytics |
+| 4 | **heatmap** | Member 4 | Generate crowd heatmaps |
+| 5 | **analytics_output** | Member 5 | Create reports and output files (JSON/CSV) |
+| 6 | **crowd_behaviour_analytics** | Member 6 | Analyze crowd movement and behavior patterns |
+| 7 | **crowd_allocation_risk_zone** | Member 7 | Assess risk levels and crowd allocation strategy |
+
+**Optional:** `prediction_optional/` - Attendance prediction (if time permits)
+
+---
+
+## Task Guidance
+
+Each task folder contains its own `README.md` with:
+
+- 🎯 Task objective
+- 📥 Expected inputs and outputs
+- 💡 Implementation notes
+- ✅ Suggested deliverables
+
+This keeps the semester plan split into smaller, easier-to-manage work packages.
+
+---
+
+## Project Structure
+
+```text
+2026_T1/
+|-- data/                           # Sample videos and frames
+|-- docs/                           # Documentation and notes
+|-- shared/                         # Common utilities and configs
+|-- requirements.txt                # Dependencies
+|-- README.md                       # This file
+|
+|-- Task Folders (one per member):
+|-- video_processing/               # Task 1: Video extraction & preparation
+|-- crowd_detection/                # Task 2: Person detection (YOLOv8)
+|-- density_zoning/                 # Task 3: Density & zone analysis
+|-- heatmap/                        # Task 4: Heatmap generation
+|-- analytics_output/               # Task 5: Report generation
+|-- crowd_behaviour_analytics/      # Task 6: Behavior analysis
+|-- crowd_allocation_risk_zone/     # Task 7: Risk assessment & allocation
+|
+|-- Optional:
+`-- prediction_optional/            # Optional: Attendance prediction
+```
+
+---
+
+## 🚀 Getting Started
+
+1. **Find your task** in the table above
+2. **Read the README** in your task folder
+3. **Follow the implementation notes**
+4. **Deliver outputs** as specified
+5. **Update your README** with progress
+
+---
+
+## 📋 Integration Points
+
+Tasks run in sequence:
+
+```
+video_processing (Task 1)
+         ↓
+crowd_detection (Task 2)
+         ↓
+density_zoning (Task 3)
+         ↓
+heatmap (Task 4) + analytics_output (Task 5)
+         ↓
+crowd_behaviour_analytics (Task 6)
+crowd_allocation_risk_zone (Task 7)
+         ↓
+         ↓
+Dashboard / Report Integration
+```
+
+---
+
+## 💬 Collaboration
+
+- **Shared utilities:** Use files in `shared/` folder
+- **Input/Output:** Check task README for I/O specifications
+- **Questions:** Document in docs/ folder
+- **Results:** Save outputs to designated location in your task folder

26_T1/afl_player_tracking_and_crowd_monitoring/Crowd_Monitoring/2026_T1/analytics_output/README.md

@@ -0,0 +1,36 @@
+# Analytics Output
+
+## Objective
+
+Generate structured outputs that can be consumed by the Orion dashboard or related services.
+
+## Scope
+
+- Export analysis results in JSON and CSV formats
+- Define a clean schema for crowd metrics
+- Prepare data for backend and frontend integration
+
+## Inputs
+
+- Detection results
+- Density and zoning summaries
+- Heatmap metadata if relevant
+
+## Outputs
+
+- JSON files
+- CSV files
+- A documented output structure
+
+## Implementation Notes
+
+- Keep field names stable and descriptive
+- Include timestamps, frame IDs, and zone metrics where useful
+- Design the structure so it can be used before full production data exists
+- Prefer simple schemas first, then extend only if needed
+
+## Suggested Deliverables
+
+- A serializer or export script
+- Example JSON and CSV output
+- A short schema note in this folder or `docs/`

26_T1/afl_player_tracking_and_crowd_monitoring/Crowd_Monitoring/2026_T1/crowd_allocation_risk_zone/README.md

@@ -0,0 +1,43 @@
+# Crowd Allocation & Risk Zone Planning
+
+## Objective
+
+Assess crowd safety risk levels across zones and provide recommendations for crowd allocation and management strategies to prevent dangerous situations.
+
+## Scope
+
+- Identify high-risk zones based on crowd density thresholds
+- Assess cumulative risk factors (density, behavior, movement patterns)
+- Create risk zone maps for different crowd levels
+- Suggest crowd allocation strategies to balance load
+- Develop evacuation or crowd control recommendations
+
+## Inputs
+
+- Per-zone density counts from density_zoning task
+- Crowd behaviour analysis from crowd_behaviour_analytics task
+- Zone definitions and capacity data
+- Historical incident or risk data (if available)
+
+## Outputs
+
+- Risk zone classifications (low, medium, high, critical)
+- Risk heatmaps with threshold indicators
+- Crowd allocation recommendations
+- Safety alerts and warnings
+- Evacuation route suggestions (if applicable)
+
+## Implementation Notes
+
+- Define clear density thresholds for each risk level per zone
+- Combine density metrics with behavior flags to assess risk
+- Keep allocation recommendations practical and implementable
+- Focus first on identifying critical zones, then suggest improvements
+- Document risk thresholds and decision logic clearly
+
+## Suggested Deliverables
+
+- Risk zone map visualization
+- Allocation recommendation report (JSON/CSV)
+- Risk threshold configuration file
+- Examples showing critical scenarios and responses

26_T1/afl_player_tracking_and_crowd_monitoring/Crowd_Monitoring/2026_T1/crowd_behaviour_analytics/README.md

@@ -0,0 +1,36 @@
+# Crowd Behaviour Analytics
+
+## Objective
+
+Analyse movement patterns in the crowd and detect behaviour that may indicate risk or unusual conditions.
+
+## Scope
+
+- Analyse crowd movement over time
+- Detect sudden crowd movement
+- Detect abnormal behaviour
+- Detect crowd surges
+
+## Inputs
+
+- Sequential detections across frames
+- Optional tracking or motion features
+
+## Outputs
+
+- Behaviour event flags
+- Movement summaries
+- Data that can support alerting or dashboard visualisation
+
+## Implementation Notes
+
+- Start with simple movement heuristics before advanced models
+- Compare position changes across frames
+- Focus first on interpretable signals that are easy to validate
+- Document assumptions clearly because this task can become ambiguous quickly
+
+## Suggested Deliverables
+
+- A prototype behaviour analysis script
+- A few example scenarios or simulated cases
+- A list of event definitions used by the module

26_T1/afl_player_tracking_and_crowd_monitoring/Crowd_Monitoring/2026_T1/crowd_detection/README.md

@@ -0,0 +1,36 @@
+# Crowd Detection
+
+## Objective
+
+Detect spectators in stadium footage using a person-level detection pipeline.
+
+## Scope
+
+- Run person detection on frames or video
+- Focus on detecting spectators rather than general scene objects
+- Compare results against the previous segmentation-based approach where useful
+- Prepare detection outputs for density and zone analysis
+
+## Inputs
+
+- Extracted video frames
+- Sample stadium footage
+
+## Outputs
+
+- Bounding boxes for detected people
+- Confidence scores
+- Structured detection results for later tasks
+
+## Implementation Notes
+
+- Use YOLOv8 through Ultralytics
+- Start with the `person` class only
+- Save outputs in a simple format such as JSON or CSV
+- Record known failure cases such as occlusion, distance, and low lighting
+
+## Suggested Deliverables
+
+- A detection script or notebook
+- Sample visual output with boxes drawn on frames
+- A saved set of person coordinates or detections