A team from the University of Surrey has created a unique and lightweight deep neural network that could prove to be the new standard in artificial intelligence (AI) applied to video surveillance.
AI is increasingly being used to help human operators handle massive amounts of images from CCTV and other security sources. Person re-identification (ReID) is a method in which an AI is able to recognise images of the same person taken from different cameras or on different occasions. This helps to track suspects across a CCTV network covering large public space, such as an underground network. ReID is challenging for machines as they have to consider and differentiate the same person under different light sources, poses and changes in appearance such as their clothes.
In a paper to be presented at this year’s International Conference on Computer Vision in Seoul, South Korea, the most prestigious conference in visual AI, experts from Surrey’s Centre for Vision, Speech and Signal Processing (CVSSP) detail how they have developed a unique system called OSNet that has outperformed many popular identification systems already in use.
The CVSSP team has shown that OSNet is able to drill down into information from a variety of spatial scales to help accurately make a re-identification – from the smallest details such as the logo on a t-shirt to other, larger factors such as the type of coat worn by the suspect.
Incredibly, OSNet only needs 2.2 million parameters, a very small number in the context of deep neural network models, to outperform many of its competitors built on the popular ResNet50 infrastructure that uses 24 million parameters – suggesting that OSNet could become the standard in visual recognition technology.
Source: “Surrey AI research achieves world-leading technology for visual recognition of people”, University of Surrey.