Manual crowd estimation, is difficult and laborious for humans. As a result, any crowd monitoring system that relies on humans for counting people in crowded scenes will be slow and unreliable. There is a need for an automatic computer vision module that can accurately count the number of people in crowded scenes based on images and videos of the crowds.
More precisely, crowd counting aims to count the number of people in a crowded scene whereas density estimation aims to map an input crowd image to its corresponding density map which indicates the number of people per pixel present in the image and the two problems have been jointly addressed by our team.
Thanks to our deep learning research team, we have designed a real-time and accurate deep neural network which can simultaneously address the problems of counting, density map estimation and localization of people in a given dense crowd image. Our crowd counting solution outperforms current state-of-the-art methods and has the ability to perform successfully on a wide range of scenarios. It is also customizable, and we can adapt it to any environment and scenarios which our customers need. For more details, please visit our demo page .
Contact us for any questions, more information, or request for a meeting.