video1.0<iframe src="https://www.loom.com/embed/8de8b3a2ab804dd4af6d62b44f2e7d1b" frameborder="0" width="1728" height="1296" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>12961728Loomhttps://www.loom.com12961728https://cdn.loom.com/sessions/thumbnails/8de8b3a2ab804dd4af6d62b44f2e7d1b-9b9e0c0d55cb1aaf.gif593.75Hi, I'm Varunavi Tien, and in this video, I presented my project for the Catamaran Hackathon, which is an intelligent face tracker with auto-registration and unique visitor counting. The system uses a combination of YOLO for face detection and an Insight phase model for accurate identification, processing 1,502 frames in total. I implemented a dual filter to eliminate false positives and a mechanism to ensure accurate exit tracking. You can see real-time updates on unique visitor counts and logs of entries and exits stored in an SQLite database. Please check the readme file for more details, and feel free to reach out with any questions!