๐ I Built DriveSafe So My Friends Never Have to Scrub Through Hours of Dashcam Footage Again
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built DriveSafe is a privacy-first AI platform that turns hours of dashcam footage into an intelligent, searchable driving history. A few of my friends drive regularly and use dashcams. Quite often, someone might cross the road unexpectedly, a close call might happen, or another driver might do somethingโฆ
I Built DriveSafe So My Friends Never Have to Scrutinize Hours of Dashcam Footage Again
DriveSafe is a privacy-first AI platform that transforms hours of dashcam footage into an intelligent, search-friendly driving history. Regular dashcam users and their friends often need to locate specific moments in lengthy recordings, such as unexpected road crossings, close calls, or unusual driver actions. However, locating a single moment within hours of video can take several minutes of manual scrubbing. DriveSafe was developed to simplify this process.
Rather than scanning through the entire video, DriveSafe utilizes AI to automatically recognize important moments like pedestrians, cyclists, near-miss vehicle encounters, and sudden scene changes. The system then generates clips and an interactive timeline, enabling users to search historical drives using natural language.
DriveSafe leverages Google's Gemma 4 model, with Temporal handling the durable video-processing workflow. The system follows this pipeline: Dashcam Video โ Temporal Workflow โ Frame Extraction โ Gemma Vision Analysis โ Event Detection โ Clip Generation โ Embeddings โ MongoDB โ Searchable Timeline.
For privacy-conscious users, DriveSafe can process video footage entirely locally by employing open-weight Gemma models alongside Ollama for offline inference. In Local Edge Mode, video frames and telemetry remain on the user's machine, rather than being transmitted to external cloud servers. This open-technology approach also allows DriveSafe to integrate Gemma, Ollama, Temporal, FFmpeg, MongoDB, and Docker into a seamless end-to-end system.
The project can also be initiated locally using Docker, incorporating MongoDB and Ollama. DriveSafe has been recognized in several categories, including Best Use of MongoDB Atlas, Best Use of Temporal, Best Use of Google Gemma, and Best Overall Project. The platform merges AI-powered video understanding with a comprehensive end-to-end product experience, including one-click Docker deployment, interactive timeline visualization, clip generation, vector search, historical drive memory, and automated verification tests.
Written by urgent.news from Dev.to's reporting โ not their text. Machine-written โ may contain errors; check the original before relying on it.