# sheelabhadra/emergency-vehicle-detection architecture

> Architecture diagram of the GitHub repository sheelabhadra/emergency-vehicle-detection, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-05). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/sheelabhadra/emergency-vehicle-detection
- Repository: https://github.com/sheelabhadra/emergency-vehicle-detection

## Overview

This repository is a collection of research implementations for detecting emergency and alarm sounds from audio, rather than one unified application. Its user-facing workflow is to supply audio, extract signal or learned features, classify emergency presence, and inspect predictions or plots. It preserves three distinct approaches: pitch periodicity (Paper-1), MFCC/ANN classification (Paper-2), and noisy-environment alarm detection (Paper-3), alongside Paper-3’s broader audio-analysis toolkit. Paper-2 internals and several Paper-3 runtime links are documented but not excerpted, so those connections rely on README statements or are omitted.

Main entry points: [`Paper-3/pyAudioAnalysis/audioFeatureExtraction.py`](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/audioFeatureExtraction.py) (Feature extraction), [`Paper-3/pyAudioAnalysis/audioAnalysis.py`](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/audioAnalysis.py) (Analysis commands), [`Paper-3/pyAudioAnalysis/audioSegmentation.py`](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/audioSegmentation.py) (Segmentation), [`Paper-3/pyAudioAnalysis/audioBasicIO.py`](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/audioBasicIO.py) (Audio I/O)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_acquisition["Data acquisition"]
  node_dataset["Data generation<br/>[dataGen.py]"]
end

subgraph group_pitch["Pitch detection"]
  node_pitch_entry["Pitch runner<br/>[find_pitch.py]"]
  node_pitch_method["CAMDF pitch<br/>[pitch_detection.py]"]
  node_pitch_plot["Pitch plot<br/>[pitch_detection.py]"]
end

subgraph group_mfcc["MFCC classifier"]
  node_mfcc_train["MFCC training<br/>[em_detection.py]"]
  node_mfcc_infer["Clip prediction<br/>[test_audio_file.py]"]
  node_mfcc_model["ANN model<br/>[model2.h5]"]
end

subgraph group_alarm["Alarm analysis"]
  node_alarm_train["Alarm training<br/>[em_detection.py]"]
  node_alarm_infer["Audio prediction<br/>[test_audio_file.py]"]
  node_realtime["Live analysis<br/>[real_time_test.py]"]
  node_alarm_model["Trained model<br/>[model3.h5]"]
  node_audio_io["Audio I/O<br/>[audioBasicIO.py]"]
  node_features["Feature extraction"]
  node_training["Model utilities<br/>[audioTrainTest.py]"]
  node_segmentation["Segmentation"]
  node_analysis_cli["Analysis commands<br/>[audioAnalysis.py]"]
  node_visualization["Visualization"]
  node_utilities["Feature helpers<br/>[utilities.py]"]
end

node_researcher(("Audio analyst"))
node_audio["Audio recordings"]

node_researcher -->|"provides"| node_audio
node_audio -->|"analyzes"| node_pitch_entry
node_pitch_entry -->|"runs"| node_pitch_method
node_pitch_method -->|"plots"| node_pitch_plot
node_audio -->|"trains on"| node_mfcc_train
node_mfcc_train -.->|"trains"| node_mfcc_model
node_audio -->|"predicts"| node_mfcc_infer
node_mfcc_infer -.->|"loads"| node_mfcc_model
node_audio -->|"trains on"| node_alarm_train
node_alarm_train -->|"imports"| node_audio_io
node_alarm_train -->|"imports"| node_features
node_audio -->|"predicts"| node_alarm_infer
node_alarm_infer -.->|"uses"| node_alarm_model
node_audio -.->|"analyzes live"| node_realtime
node_analysis_cli -->|"imports"| node_audio_io
node_analysis_cli -->|"imports"| node_features
node_analysis_cli -->|"imports"| node_training
node_analysis_cli -->|"imports"| node_segmentation
node_analysis_cli -->|"imports"| node_visualization
node_features -->|"imports"| node_audio_io
node_features -->|"imports"| node_utilities
node_segmentation -->|"imports"| node_features
node_segmentation -->|"imports"| node_training
node_segmentation -->|"imports"| node_audio_io
node_visualization -->|"imports"| node_features
node_visualization -->|"imports"| node_training

click node_dataset "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Data-aquisition/dataGen.py"
click node_pitch_entry "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-1/find_pitch.py"
click node_pitch_method "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-1/pitch_detection.py"
click node_pitch_plot "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-1/pitch_detection.py"
click node_mfcc_train "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-2/em_detection.py"
click node_mfcc_infer "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-2/test_audio_file.py"
click node_mfcc_model "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-2/model2.h5"
click node_alarm_train "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/em_detection.py"
click node_alarm_infer "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/test_audio_file.py"
click node_realtime "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/real_time_test.py"
click node_alarm_model "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/model3.h5"
click node_audio_io "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/audioBasicIO.py"
click node_features "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/audioFeatureExtraction.py"
click node_training "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/audioTrainTest.py"
click node_segmentation "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/audioSegmentation.py"
click node_analysis_cli "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/audioAnalysis.py"
click node_visualization "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/audioVisualization.py"
click node_utilities "https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/utilities.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_dataset toneBlue
class node_pitch_entry,node_pitch_method,node_pitch_plot toneAmber
class node_mfcc_train,node_mfcc_infer,node_mfcc_model toneMint
class node_alarm_train,node_alarm_infer,node_realtime,node_alarm_model,node_audio_io,node_features,node_training,node_segmentation,node_analysis_cli,node_visualization,node_utilities toneRose
class node_researcher,node_audio toneIndigo
```

## Components

### Data acquisition

- [Data generation](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Data-aquisition/dataGen.py): `Data-aquisition/dataGen.py`

### Pitch detection

- [Pitch runner](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-1/find_pitch.py): `Paper-1/find_pitch.py`
- [CAMDF pitch](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-1/pitch_detection.py): `Paper-1/pitch_detection.py`
- [Pitch plot](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-1/pitch_detection.py): `Paper-1/pitch_detection.py`

### MFCC classifier

- [MFCC training](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-2/em_detection.py): `Paper-2/em_detection.py`
- [Clip prediction](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-2/test_audio_file.py): `Paper-2/test_audio_file.py`
- [ANN model](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-2/model2.h5): `Paper-2/model2.h5`

### Alarm analysis

- [Alarm training](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/em_detection.py): `Paper-3/em_detection.py`
- [Audio prediction](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/test_audio_file.py): `Paper-3/test_audio_file.py`
- [Live analysis](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/real_time_test.py): `Paper-3/real_time_test.py`
- [Trained model](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/model3.h5): `Paper-3/model3.h5`
- [Audio I/O](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/audioBasicIO.py): `Paper-3/pyAudioAnalysis/audioBasicIO.py`
- [Feature extraction](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/audioFeatureExtraction.py): `Paper-3/pyAudioAnalysis/audioFeatureExtraction.py`
- [Model utilities](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/audioTrainTest.py): `Paper-3/pyAudioAnalysis/audioTrainTest.py`
- [Segmentation](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/audioSegmentation.py): `Paper-3/pyAudioAnalysis/audioSegmentation.py`
- [Analysis commands](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/audioAnalysis.py): `Paper-3/pyAudioAnalysis/audioAnalysis.py`
- [Visualization](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/audioVisualization.py): `Paper-3/pyAudioAnalysis/audioVisualization.py`
- [Feature helpers](https://github.com/sheelabhadra/emergency-vehicle-detection/blob/master/Paper-3/pyAudioAnalysis/utilities.py): `Paper-3/pyAudioAnalysis/utilities.py`

### Other components

- **Audio analyst**
- **Audio recordings**

## Connections

- Audio analyst → Audio recordings: provides (evidence: `README.md`)
- Audio recordings → Pitch runner: analyzes (evidence: `Paper-1/find_pitch.py`)
- Pitch runner → CAMDF pitch: runs (evidence: `Paper-1/find_pitch.py`)
- CAMDF pitch → Pitch plot: plots (evidence: `Paper-1/pitch_detection.py`)
- Audio recordings → MFCC training: trains on (evidence: `README.md`)
- MFCC training → ANN model: trains (evidence: `README.md`)
- Audio recordings → Clip prediction: predicts (evidence: `README.md`)
- Clip prediction → ANN model: loads (evidence: `README.md`)
- Audio recordings → Alarm training: trains on (evidence: `README.md`)
- Alarm training → Audio I/O: imports (evidence: `Paper-3/em_detection.py`)
- Alarm training → Feature extraction: imports (evidence: `Paper-3/em_detection.py`)
- Audio recordings → Audio prediction: predicts (evidence: `README.md`)
- Audio prediction → Trained model: uses (evidence: `README.md`)
- Audio recordings → Live analysis: analyzes live
- Analysis commands → Audio I/O: imports (evidence: `Paper-3/pyAudioAnalysis/audioAnalysis.py`)
- Analysis commands → Feature extraction: imports (evidence: `Paper-3/pyAudioAnalysis/audioAnalysis.py`)
- Analysis commands → Model utilities: imports (evidence: `Paper-3/pyAudioAnalysis/audioAnalysis.py`)
- Analysis commands → Segmentation: imports (evidence: `Paper-3/pyAudioAnalysis/audioAnalysis.py`)
- Analysis commands → Visualization: imports (evidence: `Paper-3/pyAudioAnalysis/audioAnalysis.py`)
- Feature extraction → Audio I/O: imports (evidence: `Paper-3/pyAudioAnalysis/audioFeatureExtraction.py`)
- Feature extraction → Feature helpers: imports (evidence: `Paper-3/pyAudioAnalysis/audioFeatureExtraction.py`)
- Segmentation → Feature extraction: imports (evidence: `Paper-3/pyAudioAnalysis/audioSegmentation.py`)
- Segmentation → Model utilities: imports (evidence: `Paper-3/pyAudioAnalysis/audioSegmentation.py`)
- Segmentation → Audio I/O: imports (evidence: `Paper-3/pyAudioAnalysis/audioSegmentation.py`)
- Visualization → Feature extraction: imports (evidence: `Paper-3/pyAudioAnalysis/audioVisualization.py`)
- Visualization → Model utilities: imports (evidence: `Paper-3/pyAudioAnalysis/audioVisualization.py`)
