Real-Time Smoke and Fire Detection with YOLOv11

Overview

This project aims to develop a real-time smoke and fire detection system leveraging the power of YOLOv11, a state-of-the-art object detection model. By providing early and accurate detection of fire and smoke, this system enhances safety measures across various environments, helping to mitigate potential hazards and property damage.

Dataset

The dataset is a comprehensive, well-annotated collection of images containing instances of fire and smoke under diverse conditions. It is carefully curated to ensure robustness in model training, validation, and evaluation.

Classes

• Fire
• Smoke

Annotations

Each image is annotated with precise bounding boxes around instances of fire and smoke, enabling accurate localization and detection.

Dataset Distribution

• Training Set: 9,156 images
• Validation Set: 872 images
• Test Set: 435 images

Key Features

• Real-Time Detection: Processes video feeds in real-time, providing instant alerts upon detecting fire or smoke.
• High Accuracy: Utilizes YOLOv11’s advanced capabilities to achieve robust performance even in complex conditions.
• Customizable & Scalable: The model can be fine-tuned and adapted to various environments, making it ideal for applications in industrial safety, residential monitoring, and surveillance systems.

Usage

This dataset is designed for training and evaluating object detection models tailored for real-time fire and smoke detection. It is suitable for: - Surveillance systems (CCTV monitoring, smart security cameras) - Industrial safety applications (factories, warehouses, refineries) - Residential safety solutions (smart home fire detection) - Autonomous monitoring systems (drones, robotics, IoT devices)

Installation & Setup

Get started by cloning the dataset from Roboflow:

from roboflow import Roboflow
rf = Roboflow(api_key="YOUR_API_KEY")
project = rf.workspace("sayed-gamall").project("fire-smoke-detection-yolov11")
dataset = project.version(2).download("yolov11")

Get Started

1. Download the dataset using the above script.
2. Train your YOLOv11 model with the dataset.
3. Deploy the trained model for real-time fire and smoke detection.
4. Integrate alerts and notifications for automated safety monitoring.

This dataset provides a strong foundation for developing intelligent fire and smoke detection systems that can significantly improve safety and emergency response times.

🚀 Ready to Train?

Start building your real-time fire and smoke detection model today with Roboflow! 🔥

The Fire and Smoke Detection Dataset is a comprehensive collection of images and annotations specifically curated for training object detection models, such as YOLOv10, to recognize and classify instances of fire and smoke in various real-world scenarios. This dataset is designed to empower computer vision applications for early fire detection, safety monitoring, and disaster prevention.

Citation: If you use this dataset in your research or projects, please consider citing it as follows: https://universe.roboflow.com/middle-east-tech-university/fire-and-smoke-detection-hiwia

This dataset contains 11027 labeled images for the detection of fire and smoke instances in diverse real-world scenarios. The annotations are provided in YOLO format with bounding boxes and class labels for two classes: fire and smoke. The dataset is divided into an 80% training set with 10,090 fire instances and 9724 smoke instances, a 10% Validation set with 1,255 fire and 1,241 smoke instances, and a 10% Test set with 1,255 fire and 1,241 smoke instances. This dataset is suitable for training and evaluating fire and smoke detection models, such as YOLOv8, YOLOv9, and similar deep learning-based frameworks in the context of emergency response, wildfire monitoring, and smart surveillance.

Fire Detection Dataset - 85 videos

The dataset comprises 85 videos containing fire and smoke scenes, varying in length and content. Each video frame is annotated with bounding boxes that localize instances of fire and smoke, making it a comprehensive resource for fire monitoring, wildfire detection, and real-time monitoring systems. Designed to support detection systems, deep learning, and model training, this dataset is essential for improving fire management, early detection, and fire safety applications.

By leveraging this dataset, researchers and developers can enhance detection algorithms, train machine learning models, and improve accuracy in identifying fire events, smoke detection, and burnt areas under diverse environmental conditions.- Get the data

Each video sequence has been meticulously annotated by experts with precise bounding boxes that accurately localize all visible instances of fire and smoke throughout the frames.

💵 Buy the Dataset: This is a limited preview of the data. To access the full dataset, please contact us at https://unidata.pro to discuss your requirements and pricing options.

Researchers working on early warning systems will find the extensive footage of incipient fire stages especially valuable. Supports creation of fire prevention systems by analyzing fire behavior in different contexts.

🌐 UniData provides high-quality datasets, content moderation, data collection and annotation for your AI/ML projects

FASDD is a largest and most generalized Flame And Smoke Detection Dataset for object detection tasks, characterized by the utmost complexity in fire scenes, the highest heterogeneity in feature distribution, and the most significant variations in image size and shape. FASDD serves as a benchmark for developing advanced fire detection models, which can be deployed on watchtowers, drones, or satellites in a space-air-ground integrated observation network for collaborative fire warning. This endeavor provides valuable insights for government decision-making and fire rescue operations. FASDD contains fire, smoke, and confusing non-fire/non-smoke images acquired at different distances (near and far), different scenes (indoor and outdoor), different light intensities (day and night), and from various visual sensors (surveillance cameras, UAVs, and satellites). FASDD consists of three sub-datasets, a Computer Vision (CV) dataset (i.e. FASDD_CV), a Unmanned Aerial Vehicle (UAV) dataset (i.e. FASDD_UAV), and an Remote Sensing (RS) dataset (i.e. FASDD_RS). FASDD comprises 122,634 samples, with 70,581 annotated as positive samples and 52,073 labeled as negative samples. There are 113,154 instances of flame objects and 73,072 instances of smoke objects in the entire dataset. FASDD_CV contains 95,314 samples for general computer vision, while FASDD_UAV consists of 25,097 samples captured by UAV, and FASDD_RS comprises 2,223 samples from satellite imagery. FASDD_CV contains 73,297 fire instances and 53,080 smoke instances. The CV dataset exhibits considerable variation in image size, ranging from 78 to 10,600 pixels in width and 68 to 8,858 pixels in height. The aspect ratios of the images also vary significantly, ranging from 1:6.6 to 1:0.18. FASDD_UAV contains 36,308 fire instances and 17,222 smoke instances, with image aspect ratios primarily distributed between 4:3 and 16:9. In FASDD_RS, there are 2,770 smoke instances and 3,549 flame instances. The sizes of remote sensing images are predominantly around 1,000×1,000 pixels.FASDD is provided in three compressed files: FASDD_CV.zip, FASDD_UAV.zip, and FASDD_RS.zip, which correspond to the CV dataset, the UAV dataset, and the RS dataset, respectively. Additionally, there is a FASDD_RS_SWIR. zip folder storing pseudo-color images for detecting flame objects in remote sensing imagery. Each zip file contains two folders: "images" for storing the source data and "annotations" for storing the labels. The "annotations" folder consists of label files in four formats: YOLO, VOC, COCO, and TDML. The dataset is divided randomly into training, validation, and test sets, with a ratio of 1/2, 1/3, and 1/6, respectively, within each label format. In FASDD_CV, FASDD_UAV, and FASDD_RS, images and their corresponding annotation files have been individually sorted starting from 0. The flame and smoke objects in FASDD are given the labels "fire" and "smoke" for the object detection task, respectively. The names of all images and annotation files are prefixed with "Fire", "Smoke", "FireAndSmoke", and "NeitherFireNorSmoke", representing different categories for scene classification tasks.When using this dataset, please cite the following paper. Thank you very much for your support and cooperation：################################################################################使用数据集请引用对应论文，非常感谢您的关注和支持：Wang, M., Yue, P., Jiang, L., Yu, D., Tuo, T., & Li, J. (2025). An open flame and smoke detection dataset for deep learning in remote sensing based fire detection. Geo-spatial Information Science, 28(2), 511-526.################################################################################

Here are a few use cases for this project:

1. Fire Emergency Identification: The model can be used in fire detection systems in public and private buildings. When it identifies fire or smoke and the presence of a human, it could trigger alarms and deploy necessary measures such as spraying fire retardant or auto-dialing emergency services.

2. Personal Safety Applications: In smart home systems, the model could provide real-time alerts to homeowners if fire or smoke is detected, especially if there's a human present, indicating potential danger.

3. Forest Fire Surveillance: The model can analyze drone or satellite imagery to identify forest fires and detect if anyone is trapped or injured within the vicinity, helping to strategize the response.

4. Industrial Safety: The model can be used in industries, particularly those with higher fire risk like oil and gas, chemical, and manufacturing, to monitor for fire or smoke and ensure the safety of the workers.

5. Disaster Response Training: The model can be used in simulations to train emergency response teams. For instance, the model would identify fire, smoke, and humans in various scenarios, providing realistic training opportunities for firefighters and rescue teams.

The 'Forest Fire, Smoke, and Non-Fire Image Dataset' is a meticulously organized collection of images sourced from reputable platforms such as Kaggle, Yandex, and various other forest fire image galleries available on Google. This dataset has been specifically developed to create a robust system for accurately detecting forest fires and smoke using multiclass image classification techniques.

DATASET COMPOSITION This dataset comprises a total of 42,900 images, distributed across three categories: "fire," "smoke," and "non-fire." It is a balanced dataset divided into training and testing set folders. The training set includes 10,800 samples for each category: fire, smoke, and non-fire. Additionally, 3,500 samples for each category were set aside in the testing set to evaluate the system's effectiveness.

CLASS BALANCE The dataset is intentionally balanced to provide an equal representation of each category, ensuring that the model is not biased towards any particular class. This balance is maintained in both the training and testing sets.

USE CASE The dataset is suitable for training and evaluating models designed for fire and smoke detection in images. Researchers, developers, and data scientists can use this dataset to build and validate algorithms that can identify and classify instances of fire and smoke accurately.

ACKNOWLEDGMENT Images in this dataset have been sourced from publicly available repositories. We thank the creators for their contributions.

Dataset

This dataset was created by cubeai

Contents

This dataset contains 20945 images.

Images splitted to train(%72),test(%10),validation(%18).

This dataset contains 3000 images from Hardhat-Vest dataset in order to increase model performance

Fire And Smoke Detection V2

## Overview

Fire And Smoke Detection V2 is a dataset for object detection tasks - it contains Fire Smoke annotations for 10,206 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

Test3 Fire And Smoke Detection

## Overview

Test3 Fire And Smoke Detection is a dataset for object detection tasks - it contains Fire Smoke annotations for 1,508 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Fire & Smoke Detection Dataset | YOLO *Curated by Azimjon Akhtamov, AI Researcher at CBNU*

Contact: azimjaan21@gmail.com

🔥 Overview: The Fire & Smoke Detection Dataset is designed for training object detection models, specifically YOLO, to identify fire and smoke in real-world scenarios. This dataset is ideal for fire safety applications, early wildfire detection, and industrial hazard monitoring.

📌 Why This Dataset?

🚀 Optimized for YOLO – Cleanly labeled for efficient object detection. 🌍 Real-world diversity – Covers various environments (urban, forest, industrial, and indoor settings). 📸 High-quality images – Well-annotated dataset with bounding boxes for fire and smoke. 🔍 Dataset Details:

Total Images: 17,000 + images Annotations: Bounding box format (YOLO, COCO) Classes: 🔥 Fire | 💨 Smoke Sources: Collected from real-world incidents, CCTV footage, and synthetic augmentations ⚡ Use Cases: ✅ Fire safety monitoring in factories and buildings ✅ Wildfire detection using drones & surveillance systems ✅ Smoke detection for early warning systems

📥 How to Use: 1️⃣ Download the dataset from Kaggle. 2️⃣ Load into YOLOv5 or YOLOv8 for training. 3️⃣ Fine-tune for real-time fire detection applications.

💡 About the Author: This dataset is curated by Azimjon Akhtamov, an AI researcher at Chungbuk National University (CBNU), South Korea, specializing in Computer Vision, Object Detection, and Industrial Safety AI applications.

About This Dataset

This dataset is a comprehensive, multi-scale collection for fire and smoke detection, created by merging two separate, publicly available datasets. It is designed to be robust for various scenarios, containing examples of both large-scale conflagrations and small-scale ignition sources like lighters, candles, and matches.

This work is a derivative of, and would not be possible without, the original datasets provided by:

1. Smoke Fire Detection YOLO by Sayed Gamal: * Link: https://www.kaggle.com/datasets/sayedgamal99/smoke-fire-detection-yolo

   • License: Creative Commons Zero v1.0 Universal (Public Domain)

2. Flame Dataset (Candle,Lighter,Match Stick Flames) by Sreemanta Barman: * Link: https://www.kaggle.com/datasets/sreemantabarman/flame-dataset-candlelightermatch-stick-flames

   • License: CC BY-NC-SA 4.0

License

In accordance with the "ShareAlike" (SA) clause of the more restrictive source license, this derivative dataset is also shared under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) license.

Smoke and fire detection technology is a key technology for automatically realizing forest monitoring and forest fire warning. One of the most popular algorithms for object detection tasks is YOLOv5. However, it suffers from some challenges, such as high computational load and limited detection performance. This paper proposes a high-performance lightweight network model for detecting forest smoke and fire based on YOLOv5 to overcome these problems. C3Ghost and Ghost modules are introduced into the Backbone and Neck network to achieve the purpose of reducing network parameters and improving the feature’s expressing performance. Coordinate Attention (CA) module is introduced into the Backbone network to highlight the object’s important information about smoke and fire and to suppress irrelevant background information. In Neck network part, in order to distinguish the importance of different features in feature fusing process, the weight parameter of feature fusion is added which is based on PAN (path aggregation network) structure, which is named PAN-weight. Multiple sets of controlled experiments were conducted to confirm the proposed method’s performance. Compared with YOLOv5s, the proposed method reduced the model size and FLOPs by 44.75% and 47.46% respectively, while increased precision and mAP(mean average precision)@0.5 by 2.53% and 1.16% respectively. The experimental results demonstrated the usefulness and superiority of the proposed method. The core code and dataset required for the experiment are saved in this article at https://github.com/vinchole/zzzccc.git.

GFO Fire And Smoke Detection

## Overview

GFO Fire And Smoke Detection is a dataset for object detection tasks - it contains Fire Smoke annotations for 400 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

The real-time capabilities of different models on fire-smoke detection.

Dataset Overview: This dataset contains annotated images of fire and smoke, designed for training object detection models in scenarios involving fire hazards. It is ideal for applications such as surveillance, early fire detection systems, and environmental monitoring. The dataset provides clear annotations in the YOLO format, with two primary classes: fire (0) and smoke (1).

Classes:

0: Fire – Images containing visible flames or areas where a fire is clearly present. 1: Smoke – Images with visible smoke, either in the early stages of fire development or from environmental factors. Dataset Composition:

The dataset includes >35k images labeled for fire and smoke detection. The images vary in lighting conditions, resolutions, and environmental contexts to ensure the model generalizes well in different real-world scenarios. Training Data: Images used for model training, featuring balanced examples of both fire and smoke. Validation Data: Used for tuning model hyperparameters and validating the performance of models. Test Data: Held-out data to evaluate the final model's performance, containing unseen images of fire and smoke.

Applications:

Fire Detection Systems: This dataset can be used to train AI models to detect fires in surveillance videos and initiate early warning systems in industrial or urban environments. Environmental Monitoring: Detecting wildfires or smoke from pollution in forests and other remote areas. Surveillance Systems: For safety monitoring in areas prone to fire hazards such as factories, warehouses, and large buildings. Annotations:

All images are annotated in the YOLO format, where each label file corresponds to an image and includes the bounding box coordinates for the detected objects (fire and smoke). Bounding boxes and labels are in the format:

Smoke and Fire Detection Videos Dataset with annotated frames for training AI to accurately detect and localize fire and smoke in diverse scenes

Quick Start Guide

Problem Type : Binary Classification Target Variable : Fire Alarm

Context

A smoke detector is a device that senses smoke, typically as an indicator of fire. Smoke detectors are usually housed in plastic enclosures, typically shaped like a disk about 150 millimetres (6 in) in diameter and 25 millimetres (1 in) thick, but shape and size vary.

--> Types of Smoke Detectors

1. Photoelectric Smoke Detector

A photoelectric smoke detector contains a source of infrared, visible, or ultraviolet light, a lens, and a photoelectric receiver. In some types, the light emitted by the light source passes through the air being tested and reaches the photosensor. The received light intensity will be reduced due to scattering from particles of smoke, air-borne dust, or other substances; the circuitry detects the light intensity and generates an alarm if it is below a specified threshold, potentially due to smoke. Such detectors are also known as optical detectors.

1. Ionization Smoke Detector

An ionization smoke detector uses a radioisotope to ionize air. If any smoke particles enter the open chamber, some of the ions will attach to the particles and not be available to carry the current in that chamber. An electronic circuit detects that a current difference has developed between the open and sealed chambers, and sounds the alarm

The author of this dataset has successfully created a smoke detection device with the help of IOT devices and AI model. (Check Acknowledgement )

About the dataset

Collection of training data is performed with the help of IOT devices since the goal is to develop a AI based smoke detector device. Many different environments and fire sources have to be sampled to ensure a good dataset for training. A short list of different scenarios which are captured:

• Normal indoor
• Normal outdoor
• Indoor wood fire, firefighter training area
• Indoor gas fire, firefighter training area
• Outdoor wood, coal, and gas grill
• Outdoor high humidity
• etc.

The dataset is nearly 60.000 readings long. The sample rate is 1Hz for all sensors. To keep track of the data, a UTC timestamp is added to every sensor reading.

Acknowledgement / Credits

The data is collected by Stefan Blattmann in his project Real-time Smoke Detection with AI-based Sensor Fusion. Author's GitHub : https://github.com/Blatts01

1) Data Introduction • The Forest Fire Dataset is an image classification dataset consisting of images related to wildfires and smoke. It is designed to serve as visual training material for the development of fire and smoke detection algorithms. The dataset includes two classification labels: 'fire' for wildfire images and 'smoke' for smoke-related images.

2) Data Utilization (1) Characteristics of the Forest Fire Dataset: • The dataset contains images of fires and smoke captured in various environments, making it suitable for the development of early detection and classification systems. • Most of the images are sourced from the wildfire detection dataset released by the University of Science and Technology of China (USTC), and they contain a wide range of visual features reflecting real wildfire scenarios.

(2) Applications of the Forest Fire Dataset: • Development of wildfire and smoke recognition AI models: Can be used to train image-based artificial intelligence models that automatically classify the presence of fire or smoke. • Experiments for disaster response system development: Useful as foundational data for building technologies such as forest surveillance, CCTV video analysis, and real-time alert systems. • Environmental research and climate change applications: Can be used to analyze wildfire occurrence patterns and assess the effectiveness of fire detection algorithms under climate change scenarios.