Advanced image sensors’ role in developing autonomous vehicles
Advances in machine vision technology are leading us closer to a future of driverless cars and trucks, but challenges such as the massive amount of data produced by vision systems remain, which companies are working to overcome.
Autonomous vehicles are still a few years away from commercial viability, and there are some critical obstacles to be overcome in the meantime. Many automotive manufacturers have put Level 3 autonomous vehicles on the road, but nobody has yet to pass this level of autonomy other than in a handful of prototypes.
Vision plays an important role in the viability of autonomous vehicles. Advances in vision technology are leading us closer to a future of driverless cars and trucks.
One of the biggest challenges to autonomous vehicles’ vision involves the massive amount of data produced by vision systems.
"Cameras will generate 20 to 60 megabytes, radar upward of 10 kilobytes, sonar of 10 to 100 kilobytes. GPS will run at 50 kilobytes, and LIDAR will range between 10 and 70 megabytes. Thus each autonomous vehicle will generate approximately 4 terabytes of data per day," said Brian Krzanich, Chief Executive Officer of Intel.
The sheer volume of visual data that needs to be processed, combining several streams of data at once, is one of the main vision challenges in autonomous vehicles today.
Vision technologies enhancing autonomous vehicle capabilities
Despite the current challenges, there are some technologies that are slowly pushing autonomous vehicles forward. Some companies have found ways to combine visible, stereo and infrared imaging (IR), resulting in vision systems that can see in rain, haze, fog, glare and complete darkness.
Other companies are developing vision systems with short-, medium- and long-range sensors—widely considered a crucial vision capability for autonomous vehicles—to improve the physical range of vision systems in driverless cars.
Some companies are working on processors and computers that can handle these enormous streams of information. Whatever the need is, there are innovative solutions constantly being developed as the world’s largest vision companies compete to be the biggest vision provider to autonomous vehicles.
Vision is playing a crucial role in the maturation of driverless cars and trucks. While we’re still a few years away from full deployment, the technological advances are occurring quickly and some of the main obstacles to commercial viability of autonomous vehicles are being overcome.
This article originally appeared on the AIA website. The AIA is a part of the Association for Advancing Automation (A3). A3 is a CFE Media content partner. Edited by Chris Vavra, production editor, Control Engineering, firstname.lastname@example.org.
See more from AIA below.
Original content can be found at www.visiononline.org.