As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
We introduce a multi-process framework for human counting and recognition that exploits the combination of multiple deep neural networks. Deep networks have advanced the state of the art in many fields and play an essential role in computer vision for detection and recognition. However, very deep networks are still slow at inference time, and they require a substantial amount of hardware to perform complex operations. Real-time recognition from video source is still an issue due to complexity of scenario and the amount of data to process. In this paper, we propose an approach that combines multiple neural networks, that is fast and accurate.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.