Analyze live videos throw web-cams about the number of people, located in community centers with the help of neural networks, based on YOLO detection algorithm.
🔴 Clone project to your folder: git clone https://github.com/amarjin6/crowd-detection.git
🟡 Run from your IDE or use direct link to our SITE
🔵 We're welcome for pull requests and issue updates 📬
🟢 Enjoy!
🎌 Crowd Detection is a real-time occupancy counting system. Was created website and server part based on You only look once (YOLO) a state-of-the-art, real-time object detection system. Our model has several advantages over classifier-based systems. It looks at the whole image at test time so its predictions are informed by global context in the image. It also makes predictions with a single network evaluation unlike systems like R-CNN which require thousands for a single image. This makes it extremely fast, more than 1000x faster than R-CNN and 100x faster than Fast R-CNN.
For more information watch the 🎶 video 🎶
👑 amarjin6 • Team Lead, Back-end developer
🌑 Saydullin • Front-end developer
🌑 trypuzz • Q&A, UX designer
🌑 accuracy-itself • Back-end developer
🌑 arbuzov • Helper, Business analyst
🎟️ Coverage of more than 1% of shopping and public centers of the Republic of Belarus for the first year of software implementation
🎟️ Building a schedule of attendance of places during the day, determination of peak hour, generation of reporting documentation
🎟️ Ability to add filters to specific items/objects (humans, dogs, men < 18 y.o, women > 18 y.o, working hours)
🎟️ Platform support, ensuring the smooth operation of the system, frequent updates and new features...
