Original article written by Larry Hardesty can be found at MIT News.
Infrared (IR) sensing – technology at the forefront of motion and heat detection has seen great success in the commercial market. A wide range of applications for home-entertainment, healthcare equipment, temperature sensing for air conditioning, all the way to autonomous personal vehicles have been made possible with IR tech.
While IR technology has brought great benefits, the consumer-range of products (Microsoft Kinect, for example) is facing difficulties in certain lighting conditions due to the ambient interference from the sun or other sources. Simultaneously, the IR devices for commercial and industrial use go up in price considerably, having to compensate for shortcomings with high-powered laser tech and very sophisticated detection that it requires.
Team from MIT led by Li-Shiuan Peh, a professor of electrical engineering and computer science, and Jason Gao, a PhD student from the same department, have developed a solution with extremely high depth-sensing precision at the fraction of the price of an equivalent existing device. They will present their work centered around a gadget made of a smartphone with an attached $10 laser at the International Conference on Robotics and Automation in May.
Video courtesy of CSAIL
Peh’s team reached the impressive ratio of cost to performance by using camera technology, improving the traditional approach of IR sensors that measure reflections of emitted bursts of laser light. A smartphone’s camera allows them to subtract the interfering ambient infrared light from the entire IR feed detected on a 2D plane, resulting in a clean output (check the video for illustration). The depth resolution of their prototype is reportedly sufficient for vehicles moving at the speed of up to 15 km/h, with the potential to grow considerably with the staggeringly fast advances in camera technology.
Peh says: “My group has been strongly pushing for a device-centric approach to smarter cities, versus today’s largely vehicle-centric or infrastructure-centric approach. This is because phones have a more rapid upgrade-and-replacement cycle than vehicles. Cars are replaced in the timeframe of a decade, while phones are replaced every one or two years. This has led to drivers just using phone GPS today, as it works well, is pervasive, and stays up-to-date. I believe the device industry will increasingly drive the future of transportation.”
The implications of such efficient technology are immense in the world that shows promise of self-driving vehicles within our lifetime. Highly reliable recognition of obstacles on the road regardless of weather conditions, the potentially life-saving detection of other cars and pedestrians, advanced medical diagnostics, but also Amazon’s proposed autonomous drone delivery, could all become reality way sooner than we thought.
Yet again, we seem to be one step closer to today’s conceptual applications becoming tomorrow’s everyday convenience.