{"id":26068311,"url":"https://github.com/lohithgsk/fire-hazard-detector","last_synced_at":"2026-05-08T04:02:12.622Z","repository":{"id":281019949,"uuid":"943395607","full_name":"lohithgsk/Fire-Hazard-Detector","owner":"lohithgsk","description":"The Fire Hazard Detection System combines sensor-based monitoring and AI-powered fire detection for real-time hazard prevention. An ESP32 module records environmental data and sends alerts via ThingSpeak, while a Raspberry Pi analyzes live video feeds using an Inception model to detect fire. ","archived":false,"fork":false,"pushed_at":"2025-03-06T14:54:18.000Z","size":9114,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-06T15:32:22.703Z","etag":null,"topics":["esp32","iot","raspberry-pi"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/lohithgsk.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-03-05T16:32:14.000Z","updated_at":"2025-03-06T14:54:21.000Z","dependencies_parsed_at":"2025-03-06T15:43:08.178Z","dependency_job_id":null,"html_url":"https://github.com/lohithgsk/Fire-Hazard-Detector","commit_stats":null,"previous_names":["lohithgsk/fire-hazard-detector"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lohithgsk%2FFire-Hazard-Detector","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lohithgsk%2FFire-Hazard-Detector/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lohithgsk%2FFire-Hazard-Detector/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lohithgsk%2FFire-Hazard-Detector/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lohithgsk","download_url":"https://codeload.github.com/lohithgsk/Fire-Hazard-Detector/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242616266,"owners_count":20158596,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["esp32","iot","raspberry-pi"],"created_at":"2025-03-08T22:24:08.442Z","updated_at":"2026-05-08T04:02:12.531Z","avatar_url":"https://github.com/lohithgsk.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Fire Hazard Detector\n\nThe Fire Hazard Detection System is a real-time fire detection and monitoring solution that integrates sensor-based data collection with AI-powered fire detection. It enhances early warning mechanisms and rapid response to fire hazards, reducing potential damage and risks.\n\n## System Components\n### ESP32-based Monitoring Module\n- Equipped with DHT22 (temperature \u0026 humidity), Smoke Sensor, Voltage Sensor, and an OLED screen.\n- Continuously records environmental data and applies threshold-based alerts.\n- Sends real-time sensor data to ThingSpeak for cloud storage and remote monitoring.\n\n### Raspberry Pi-based Fire Detection\n- Hosts the frontend and manages real-time video feed from a connected camera.\n- Uses an Inception model to analyze the video stream for fire detection.\n- Displays alerts and notifications when fire is detected.\n\n## Installation \u0026 Setup of the Components\n### Setting up the ESP32 Module\n1. Connect DHT22, Smoke Sensor, Voltage Sensor, and OLED Screen to the ESP32.\n2. Flash the ESP32 with code to read sensor values and send data to ThingSpeak.\n3. Set threshold values for fire hazard alerts.\n\n### Configuring the Raspberry Pi\n1. Install necessary dependencies (OpenCV, TensorFlow, Flask for the frontend).\n2. Connect a USB camera to the Raspberry Pi for live feed processing.\n3. Deploy the Inception model to detect fire in video frames.\n4. Start the web application to display sensor data and fire alerts.\n\n## Run Locally\n\n### Frontend\n\nClone the project\n\n```bash\ngit clone https://github.com/lohithgsk/Fire-Hazard-Detector.git\n```\n\nGo to the project directory\n\n```bash\ncd fire-hazard-detector\n```\n\nInstall dependencies\n\n```bash\nnpm install\n```\n\nStart the server\n\n```bash\nnpm run dev\n```\n\nBy Default, the last recorded sample from Thingspeak will be displayed. \n\n### Model\n\nInstall all the requirements for the model.\n```bash\npip install -r requirements.txt\n```\nStart up the server.\n```bash\npython app.py\n```\n\n## Application Screenshots\n\nThe About Page serves as the landing page of the application. \n\n![About Page](https://github.com/lohithgsk/Fire-Hazard-Detector/blob/main/images/About.png)\n\n\u003cbr\u003e\n\nThe Dashboard displays the sensor values in real time. The values are fetched every 5 seconds from the ThingSpeak API.\n\n![Dashboard Page](https://github.com/lohithgsk/Fire-Hazard-Detector/blob/main/images/dashboard.png)\n\n\u003cbr\u003e\n\nThe Live Video Page, displays the real time video footage run through the InceptionV1 Model.\n\n![About Page](https://github.com/lohithgsk/Fire-Hazard-Detector/blob/main/images/feed.png)\n\n## References\n\nThe Inception Model was built with complete reference to Toby Breckon's paper on real time fire detection.\n```\n[1] A. J. Dunnings and T. P. Breckon, “Experimentally Defined Convolutional Neural Network Architecture Variants for Non-Temporal Real-Time Fire Detection,” IEEE Xplore, Oct. 01, 2018. https://ieeexplore.ieee.org/document/8451657\n[2] A. Ganesh, N. Bhowmik, and T. P. Breckon, “Experimental Exploration of Compact Convolutional Neural Network Architectures for Non-Temporal Real-Time Fire Detection,” Durham Research Online (Durham University), Dec. 2019, doi: https://doi.org/10.1109/icmla.2019.00119.‌\n```\n\n## Feedback\n\nIf you have any feedback or queries, please raise an issue.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flohithgsk%2Ffire-hazard-detector","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flohithgsk%2Ffire-hazard-detector","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flohithgsk%2Ffire-hazard-detector/lists"}