Communications of the ACM
Surrey AI Research Achieves World-Leading Technology for Visual Recognition of People
University of Surrey researchers have developed a unique, lightweight deep neural network that could greatly enhance the use of artificial intelligence in video surveillance.
Credit: Getty Images
Researchers at the University of Surrey in the U.K. have developed a unique and lightweight deep neural network that could greatly enhance the use of artificial intelligence in video surveillance.
The system, called OSNet, can analyze information from a variety of spatial scales to accurately make a re-identification, the process by which an AI can recognize images of the same person taken from different cameras or on different occasions.
The researchers found that OSNet only needs 2.2 million parameters—a small number for deep neural network models—to outperform many of its competitors.
The small parameter size means the model can be deployed "on the edge," saving bandwidth for transmitting large quantities of video data from cameras to data servers.
Said Surrey researcher Tao Xiang, "OSNet not only shows that it's capable of outperforming its counterparts on many re-identification problems, but the results are such that we believe it could be used as a stand-alone visual recognition technology in its own right."
From University of Surrey (U.K.)
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA
No entries found