--- title: How We Built HawkEye and Won Smart India Hackathon 2019 description: Team BitWise from VNIT Nagpur built HawkEye, an AI-powered vehicle monitoring system, in 36 hours to win Smart India Hackathon 2019. The system uses a... canonical: https://daily.dev/posts/how-we-built-hawkeye-and-won-smart-india-hackathon-2019-dvo97zr7a twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How We Built HawkEye and Won Smart India Hackathon 2019 | daily.dev og:description: Team BitWise from VNIT Nagpur built HawkEye, an AI-powered vehicle monitoring system, in 36 hours to win Smart India Hackathon 2019. The system uses a... og:url: https://daily.dev/posts/how-we-built-hawkeye-and-won-smart-india-hackathon-2019-dvo97zr7a og:image: https://api.daily.dev/og/posts/dvO97zR7a.png og:image:alt: How We Built HawkEye and Won Smart India Hackathon 2019 og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # How We Built HawkEye and Won Smart India Hackathon 2019 **[Medium](https://daily.dev/sources/medium_js)** · 8 min read · 0 upvotes · 0 comments ## Summary Team BitWise from VNIT Nagpur built HawkEye, an AI-powered vehicle monitoring system, in 36 hours to win Smart India Hackathon 2019. The system uses a YOLO-based license plate detection pipeline (Darknet + CUDA), Tesseract OCR for character recognition, and a Firebase-backed Android app with three role-based dashboards for Residents, Admins, and Security Guards. The architecture was designed around affordability — using commodity CCTV hardware and cloud compute — with a hybrid cloud deployment to balance cost and data privacy. Key technical decisions included choosing YOLO over traditional OpenCV edge detection for robustness, and Firebase for rapid development of real-time DB, auth, and push notifications. The team also presented limitations honestly and pitched a revenue model, which contributed to their win. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How does license plate recognition work using YOLO and Tesseract OCR together? YOLO, trained on Indian vehicle number plate datasets via the Darknet framework, first detects the bounding box of the plate within a video frame, chosen for its real-time detection speed over brittle traditional OpenCV edge-detection methods. Tesseract, an open-source OCR engine, then extracts the plate characters from that cropped region, producing the license plate number as a text string. _Anyone comparing OCR and object detection approaches for a vision pipeline can track real implementation write-ups like this on daily.dev._ ### Why choose Firebase instead of building a custom backend for a hackathon project? Firebase was chosen because it provides a real-time NoSQL database, authentication, and Firebase Cloud Messaging for push notifications out of the box, avoiding the need to rebuild any of these from scratch within a 36-hour build window. This let engineering time go toward the computer vision pipeline, which was the project's actual technical differentiator. _Developers weighing managed backend services against custom builds can follow similar trade-off discussions on daily.dev._ ## Similar posts on daily.dev - [Solar Powered Traffic Monitoring](https://daily.dev/posts/solar-powered-traffic-monitoring-fuwo67c3c) · Hackaday · 0 upvotes · 0 comments - [CVITEK CV1842H-P-based edge AI camera module offers night vision and AI-ISP support \(Crowdfunding\)](https://daily.dev/posts/cvitek-cv1842h-p-based-edge-ai-camera-module-offers-night-vision-and-ai-isp-support-crowdfunding--rnkzluhxb) · CNX Software · 0 upvotes · 0 comments - [Cost effective AI Vision for Home Cameras without any hardware upgrades.](https://daily.dev/posts/cost-effective-ai-vision-for-home-cameras-without-any-hardware-upgrades--2m2swveo9) · Medium · 0 upvotes · 0 comments --- Tags: [#computer-vision](https://daily.dev/tags/computer-vision), [#firebase](https://daily.dev/tags/firebase) [View this post on daily.dev](https://daily.dev/posts/how-we-built-hawkeye-and-won-smart-india-hackathon-2019-dvo97zr7a) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"How We Built HawkEye and Won Smart India Hackathon 2019","url":"https://daily.dev/posts/how-we-built-hawkeye-and-won-smart-india-hackathon-2019-dvo97zr7a","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-we-built-hawkeye-and-won-smart-india-hackathon-2019-dvo97zr7a"},"datePublished":"2026-07-18T07:18:42.093Z","dateModified":"2026-09-14T07:25:45.392Z","description":"Team BitWise from VNIT Nagpur built HawkEye, an AI-powered vehicle monitoring system, in 36 hours to win Smart India Hackathon 2019. The system uses a...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6ef476af2a997a202eed41f9311ae147?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6ef476af2a997a202eed41f9311ae147?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Medium","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Medium","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/medium","url":"https://daily.dev/sources/medium_js"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-we-built-hawkeye-and-won-smart-india-hackathon-2019-dvo97zr7a","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"computer-vision,firebase","timeRequired":"PT8M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Medium","item":"https://daily.dev/sources/medium_js"},{"@type":"ListItem","position":3,"name":"How We Built HawkEye and Won Smart India Hackathon 2019"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/how-we-built-hawkeye-and-won-smart-india-hackathon-2019-dvo97zr7a#faq","mainEntity":[{"@type":"Question","name":"How does license plate recognition work using YOLO and Tesseract OCR together?","acceptedAnswer":{"@type":"Answer","text":"YOLO, trained on Indian vehicle number plate datasets via the Darknet framework, first detects the bounding box of the plate within a video frame, chosen for its real-time detection speed over brittle traditional OpenCV edge-detection methods. Tesseract, an open-source OCR engine, then extracts the plate characters from that cropped region, producing the license plate number as a text string. Anyone comparing OCR and object detection approaches for a vision pipeline can track real implementation write-ups like this on daily.dev."}},{"@type":"Question","name":"Why choose Firebase instead of building a custom backend for a hackathon project?","acceptedAnswer":{"@type":"Answer","text":"Firebase was chosen because it provides a real-time NoSQL database, authentication, and Firebase Cloud Messaging for push notifications out of the box, avoiding the need to rebuild any of these from scratch within a 36-hour build window. This let engineering time go toward the computer vision pipeline, which was the project's actual technical differentiator. Developers weighing managed backend services against custom builds can follow similar trade-off discussions on daily.dev."}}]} ```