Imaging System that Can Peer Through Fog

Driving under the terrible weather can make it very dangerous no matter who is driving. Especially while there is fog, drivers’ visibility would be decreased dramatically. Recently, MIT researchers have developed a system that, a quote from MIT News Office, “can produce images of objects shrouded by fog so thick that human vision can’t penetrate it. It can also gauge the objects’ distance.”

Unable to handle driving condition has always been a big problem on car development, the principle of this system is to use the number of light particles, or photons from the camera counts to produce a histogram, with the heights of the bars indicating the photon counts for each interval to calculate the distance with physical obstacles.

For myself, driving in the fog is always painful, because it is pretty hard to predict what will happen and understand what is happening even though I have already paid my full attention on the road. This depth-sensing imaging system I believe will really help this realistic issue. Not only for the human driving car, but it also could be a crucial step toward self-driving cars.

Self-driving cars have been developed for years, but there are still many unsolved problems. Safety is one of them. So far, many self-driving systems have simulated the function of human’s eyes and brains on the surrounding recognitions and distance prediction which means these systems also have trouble on the low-visibility situations just like the human driver. This new imaging technique I believe would push the development of driving safety technology forward in the future.

 

Source: http://news.mit.edu/2018/depth-sensing-imaging-system-can-peer-through-fog-0321

Yiyun Gong

Leave a Reply