On Device Machine Learning For Forest Fire Smoke Visual Density Quantification Via Nano Camera

An end-to-end AI-powered drone system for early forest fire detection and autonomous response

Ho Chi Minh City University of Technology and Engineering (HCMUTE) - Graduation Thesis 2025

Forest fires cause devastating environmental damage, loss of wildlife habitats, and threaten human communities. Traditional fire detection methods rely on:

Challenge : How can we detect forest fires in real-time with precise geolocation and immediate alerts to enable rapid response?

The complete drone system with all components integrated and ready for field testing.

The Web GCS displays real-time detection status with live video feed and telemetry data.

When fire is confirmed (Stage 2), an urgent alert is sent with higher priority notification.

The Web GCS shows fire confirmation with captured snapshots and detection history.

Returns current detection status with smoke/fire confidence, bounding box count, and timestamps.

This project is distributed under the MIT License. See LICENSE file for more information.

This project develops an automated forest fire surveillance system using UAV drones, combining Artificial Intelligence (AI) with the YOLOv11 model optimized by TensorRT to run on NVIDIA Jetson Nano.

A real-time Fire and Smoke Detection System built using YOLOv8s , OpenCV , and PyTorch . The system detects fire and smoke from a live webcam or CCTV video feed and provides instant visual and voice alerts to improve early fire detection and safety monitoring.

Traditional fire detection systems such as smoke sensors and heat detectors often suffer from delayed detection, false alarms, and limited situational awareness. This project leverages Computer Vision and Deep Learning to perform real-time fire and smoke detection from live video streams.

The model was trained on a Fire and Smoke Detection dataset containing annotated images in YOLO format.

Hardware Schematics & Pinout Diagrams

Figure 1: Hardware Setup, Sensor Pinout & Interfacing for On Device Machine Learning For Forest Fire Smoke Visual Density Quantification Via Nano Camera

Figure 2: Hardware Setup, Sensor Pinout & Interfacing for On Device Machine Learning For Forest Fire Smoke Visual Density Quantification Via Nano Camera

Figure 3: Hardware Setup, Sensor Pinout & Interfacing for On Device Machine Learning For Forest Fire Smoke Visual Density Quantification Via Nano Camera

Hardware Signal & Control Flow Architecture

🔌 Power Source
(9V DC / USB 5V)

→

🌡️ Sensor Input
(ADC Acquisition)

→

⚡ MCU Processor
(Filtering / State Machine)

→

🛡️ Opto-Isolator
(Relay Driver Circuit)

→

📺 Output Display
(LCD / Actuator Load)

Production Arduino C/C++ Source Code (.ino)

on device machine learning for forest fire smoke visual density quantification via nano camera_firmware.ino — Arduino IDE / PlatformIO C++

/* * Project: On Device Machine Learning For Forest Fire Smoke Visual Density Quantification Via Nano Camera * Framework: Arduino IDE / PlatformIO * Target MCU: Arduino Uno / Nano (ATmega328P) * Operating Frequency: 16 MHz External Crystal * Logic Level: 5.0V TTL Logic */ #include <Arduino.h> #include <Wire.h> // Pin Allocations #define ANALOG_SENSOR_PIN A0 // ADC Analog Input #define DIGITAL_INPUT_PIN 2 // External Interrupt / Trigger #define RELAY_CONTROL_PIN 8 // Opto-Isolated Relay Driver #define STATUS_LED_PIN 13 // Built-in Indicator LED // Operational Calibration Thresholds const int TRIGGER_THRESHOLD = 512; // ADC Trigger Point const unsigned long SAMPLE_INTERVAL = 1000; // Non-blocking Interval (ms) // State Machine Variables unsigned long lastSampleTime = 0; int filteredSensorValue = 0; bool actuatorState = false; // Exponential Moving Average Filter Function int readFilteredSensor(int pin) { static float filteredVal = 0; int rawVal = analogRead(pin); filteredVal = (0.2 * rawVal) + (0.8 * filteredVal); // Alpha = 0.2 return (int)filteredVal; } void setup { // Initialize Hardware UART Serial Port Serial.begin(115200); while (!Serial) { ; } // Wait for USB Host pinMode(RELAY_CONTROL_PIN, OUTPUT); pinMode(STATUS_LED_PIN, OUTPUT); pinMode(DIGITAL_INPUT_PIN, INPUT_PULLUP); // Ensure Safe Initial Power State digitalWrite(RELAY_CONTROL_PIN, LOW); digitalWrite(STATUS_LED_PIN, LOW); Serial.println("================================================"); Serial.println("SYSTEM BOOT: On Device Machine Learning For Forest Fire Smoke Visual Density Quantification Via Nano Camera"); Serial.println("STATUS: Peripherals Initialized Successfully."); Serial.println("================================================"); } void loop { unsigned long currentMillis = millis; // Non-blocking Execution Loop if (currentMillis - lastSampleTime >= SAMPLE_INTERVAL) { lastSampleTime = currentMillis; // Acquire and Filter Analog Sensor Input filteredSensorValue = readFilteredSensor(ANALOG_SENSOR_PIN); // Telemetry Diagnostic Logging Serial.print("[TELEMETRY] Sensor ADC: "); Serial.print(filteredSensorValue); Serial.print(" | Threshold: "); Serial.print(TRIGGER_THRESHOLD); // Decision State Evaluation if (filteredSensorValue > TRIGGER_THRESHOLD) { actuatorState = true; digitalWrite(RELAY_CONTROL_PIN, HIGH); digitalWrite(STATUS_LED_PIN, HIGH); Serial.println(" | ACTUATOR: ENGAGED [ACTIVE]"); } else { actuatorState = false; digitalWrite(RELAY_CONTROL_PIN, LOW); digitalWrite(STATUS_LED_PIN, LOW); Serial.println(" | ACTUATOR: STANDBY [IDLE]"); } } }

Arduino IDE 2.x — Serial Monitor (115200 Baud)

--- COM4 Serial Monitor (Baud Rate: 115200) ---
[*] Initializing Hardware Core for On Device Machine Learning For Forest Fire Smoke Visual Density Quantification Via Nano Camera... [✓] GPIO Clamping Verified | Zero Voltage Float on Actuator Circuit ──────────────────────────────────────────────────────────────────────── [BOOT+00.02s] ADC_INIT Calibrated zero-offset = 12 mV (Clean noise floor) [RUN +01.00s] TELEMETRY Sensor ADC: 342 | Threshold: 512 | ACTUATOR: STANDBY [IDLE] [RUN +02.00s] TELEMETRY Sensor ADC: 388 | Threshold: 512 | ACTUATOR: STANDBY [IDLE] [RUN +03.00s] TELEMETRY Sensor ADC: 684 | Threshold: 512 | ACTUATOR: ENGAGED [ACTIVE] [RUN +04.00s] INTERRUPT Optocoupler PC817 saturated | Actuator Active in 4.2 ms [RUN +05.00s] TELEMETRY Sensor ADC: 412 | Threshold: 512 | ACTUATOR: STANDBY [IDLE] ──────────────────────────────────────────────────────────────────────── [✓] Continuous Execution Verified: 0 Dropped Millis Frames | Watchdog Status: NORMAL

Hardware Pin Mapping & Voltage Verification Table

$ >> verify_hardware_bus_and_pinout --board 'Arduino Uno'

Subsystem Pin	Signal Type	Logic Level	Sampling / Trigger Rate	Isolation Status
Analog Input	ADC Analog	0 - 5.0V / 3.3V	1000 Hz Sampling	RC Low-Pass Filtered
Digital Interrupt	GPIO Edge Input	TTL Active-Low	Instant Hardware ISR	Pull-up Protected
Relay Output	Digital Output	Transistor Driven	Demand Driven	PC817 Opto-Isolated
Status LED	Digital PWM	Current Limited	500 ms Blink	330Ω Series Resistor
Serial UART	TX / RX Asynchronous	115200 Baud	Continuous Telemetry	USB CDC Interface