Aura Vision Labs – next generation video analytics
Businesses everywhere can optimise their products and performance by better knowing who their customers are and how they spend their money. Online businesses benefit from rich data on their customers’ activities, however traditional brick and mortar retailers find it very difficult to generate the same information.
UK supermarket chains spend an estimated half a billion pounds every year tracking consumer spending through loyalty cards. These schemes have until now been the primary solution for stores to approach this challenge but their effectiveness is limited by the necessary sign-up processes and their declining popularity means many customer purchases are not being tracked.
Machine learning experts at the University of Southampton have developed a deep learning technology that can solve this global problem in data capture. Jaime Lomeli and Daniel Martinho-Corbishley are building on advances from PhDs in computer vision and biometric identification at Southampton’s world-leading Department of Electronics and Computer Science through ambitious startup Aura Vision Labs.
The business aims to revolutionise in-store customer analytics for retailers before expanding to produce novel applications in other lucrative markets including smart cities, transport management and security.
Aura Vision Labs’ technology analyses video footage to track people in real-time without relying on visible faces. From any camera, the technology can detect the gender, age and ethnicity of every person in a crowd. “Computers are excellent at repetitive jobs,” co-founder Jaime explains, “but new developments mean that we are able to perform complex tasks in a more human-like manner. This is creating new opportunities to disrupt global markets.”
There are over 245 million professionally installed video surveillance cameras in operation globally, but only one per cent of this footage is currently being analysed.
“Our technology harnesses this fantastic source of video data, working with low-cost cameras and existing security systems to provide retailers with a simple, cost-effective way to gain more accurate, in-depth and real-time information than has ever been possible before,” co-founder Daniel says.
In the retail sector, Aura vision can link customer demographics to their shopping journeys through the store and ultimately the items they purchase at checkout. This achieves a far more comprehensive data coverage than loyalty cards, with a higher accuracy and detail than alternatives like WiFi and Bluetooth tracking. Customer identities are also protected in the process as the system doesn’t rely on accessing sensitive personal information.
“With this novel technology, retail marketers could go beyond simply counting customers,” Daniel continues. “Our cloud-based visitor analytics platform gives retailers a live view of visitor numbers by demographic, accompanied by a detailed understanding of their dwell time, the products they interact with and products they go on to buy. This gives traditional retailers the crucial data they need to understand their customers, improve conversion rates, act on missed opportunities and target specific segments in unprecedented detail, bridging the data divide with online retailers.”
Aura Vision Labs is seeking opportunities to demonstrate the impact of its technology within retail and is looking for investors that will work with the team to disrupt this valuable worldwide market. You can get in touch with Aura Vision Labs using the contact form on this page.
As Aura Vision Labs develops, there is potential for the technology to be applied further to other applications. For instance, the emerging international smart city revolution aims to reduce road traffic and ensure public safety through technological enhancement. The Aura Vision Labs team plans to use their technology to simultaneously track people and cars from CCTV footage, helping city operators identify atypical congestion and promote walking as part of a healthy lifestyle.
To find out more, visit the Aura Vision Labs website.