Have you noticed how computers are becoming more advanced and improving their ability to recognise faces and shapes and building associations between images? Visual search and computer vision is a new technology that could revolutionize the way we interact with the world around us. Computer vision is a new branch of artificial intelligence missed with augmented reality that teaches computers to recognise and differentiate objects and the real world, a vital technology underpinning driverless cars, facial recognition (those filters that we love on Snapchat) and even medical diagnosis.
Blippar has developed a new technology that called ‘urban visual positioning’ that has double the accuracy of a GPS and incorporates AR to identify the position of the user and overlay directional information onto the phone’s screen. No more guessing and starting to walk in one direction then having the google maps arrow suddenly reposition and realise you were walking the opposite way. The problem is that GPS signals find it hard to cope with built-up areas, rebounding off walls and tall buildings and generally being a bit off. Directions are no longer a problem since the arrow overlays in AR navigation will direct you in the right direction from the start. Imagine not having to use a GPS and having clear arrows overlaid onto an image of the real street in real time?
Blippar has been able to integrate its technology into Apple maps and make use of existing GPS technology and will show walking routes for 300 cities as well as street names and information about areas of interest also overlaid onto the on-screen map. Quite helpful considering the capabilities of current GPS maps that can hardly tell if you’re walking or not. No longer will you have to wave sporadically as your Uber swooshes past you because the GPS inaccurately shows your location. Computer vision technology could erase the need for erroneous GPS technology, by integrating the two, this will create a seamless precise experience without errors enhanced with additional information.
Blippar originated in specialising in applying AR to marketing but has now focussed its attention on “indexing and cataloging the physical world”, says Mr. Lopez from Blippar. Getting computers to comprehend the world visually is no easy task since computers see numbers and need to be trained to see interpret patterns that form digital images. “This involves breaking down thousands and thousands of images into pixels then using algorithms to teach the machine the difference between a human, a house or a car,” says Mr. Lopez. The emergence and growth of cloud computing has facilitated the creation of such technologies and more and more we see that computers are mastering the ability to ‘organise photos based on understanding composition’ and even move into real-time analysis such as the Microsoft Translate app recognising a sign and translating it instantaneously’ says Ian Hogg, principal analyst at research firm IHS Markit. It will be interesting to see how visual computing will evolve in the future, knowing that there are many useful applications such as ‘urban visual positioning’ that totally transforms GPS usage.