Depth-sensing imaging system can peer through fog

Depth-sensing imaging system can peer through fog
The MIT system was able to resolve images of objects and gauge their depth at a range of 57 centimeters. Credit: Melanie Gonick/MIT

MIT researchers have developed a system that can produce images of objects shrouded by fog so thick that human vision can't penetrate it. It can also gauge the objects' distance.

An inability to handle misty driving conditions has been one of the chief obstacles to the development of autonomous vehicular navigation systems that use visible light, which are preferable to radar-based systems for their high resolution and ability to read road signs and track lane markers. So, the MIT system could be a crucial step toward self-driving cars.

The researchers tested the system using a small tank of water with the vibrating motor from a humidifier immersed in it. In fog so dense that could penetrate only 36 centimeters, the system was able to resolve images of objects and gauge their depth at a range of 57 centimeters.

Fifty-seven centimeters is not a great distance, but the fog produced for the study is far denser than any that a human driver would have to contend with; in the real world, a typical fog might afford a visibility of about 30 to 50 meters. The vital point is that the system performed better than human vision, whereas most imaging systems perform far worse. A navigation system that was even as good as a human driver at driving in fog would be a huge breakthrough.

"I decided to take on the challenge of developing a system that can see through actual fog," says Guy Satat, a graduate student in the MIT Media Lab, who led the research. "We're dealing with realistic fog, which is dense, dynamic, and heterogeneous. It is constantly moving and changing, with patches of denser or less-dense fog. Other methods are not designed to cope with such realistic scenarios."

Satat and his colleagues describe their system in a paper they'll present at the International Conference on Computational Photography in May. Satat is first author on the paper, and he's joined by his thesis advisor, associate professor of media arts and sciences Ramesh Raskar, and by Matthew Tancik, who was a graduate student in electrical engineering and computer science when the work was done.

Playing the odds

Like many of the projects undertaken in Raskar's Camera Culture Group, the new system uses a time-of-flight camera, which fires ultrashort bursts of laser light into a scene and measures the time it takes their reflections to return.

On a clear day, the light's return time faithfully indicates the distances of the objects that reflected it. But fog causes light to "scatter," or bounce around in random ways. In foggy weather, most of the light that reaches the camera's sensor will have been reflected by airborne water droplets, not by the types of objects that autonomous vehicles need to avoid. And even the light that does reflect from potential obstacles will arrive at different times, having been deflected by water droplets on both the way out and the way back.

Credit: Melanie Gonick/MIT

The MIT system gets around this problem by using statistics. The patterns produced by fog-reflected light vary according to the fog's density: On average, light penetrates less deeply into a thick fog than it does into a light fog. But the MIT researchers were able to show that, no matter how thick the fog, the arrival times of the reflected light adhere to a statistical pattern known as a gamma distribution.

Gamma distributions are somewhat more complex than Gaussian distributions, the common distributions that yield the familiar bell curve: They can be asymmetrical, and they can take on a wider variety of shapes. But like Gaussian distributions, they're completely described by two variables. The MIT system estimates the values of those variables on the fly and uses the resulting distribution to filter fog reflection out of the light signal that reaches the time-of-flight camera's sensor.

Crucially, the system calculates a different gamma distribution for each of the 1,024 pixels in the sensor. That's why it's able to handle the variations in fog density that foiled earlier systems: It can handle circumstances in which each pixel sees a different type of fog.

Signature shapes

The camera counts the number of light particles, or photons, that reach it every 56 picoseconds, or trillionths of a second. The MIT system uses those raw counts to produce a histogram—essentially a bar graph, with the heights of the bars indicating the photon counts for each interval. Then it finds the gamma distribution that best fits the shape of the bar graph and simply subtracts the associated photon counts from the measured totals. What remain are slight spikes at the distances that correlate with physical obstacles.

"What's nice about this is that it's pretty simple," Satat says. "If you look at the computation and the method, it's surprisingly not complex. We also don't need any prior knowledge about the fog and its density, which helps it to work in a wide range of fog conditions."

Satat tested the system using a fog chamber a meter long. Inside the chamber, he mounted regularly spaced distance markers, which provided a rough measure of visibility. He also placed a series of small objects—a wooden figurine, wooden blocks, silhouettes of letters—that the system was able to image even when they were indiscernible to the naked eye.

There are different ways to measure visibility, however: Objects with different colors and textures are visible through fog at different distances. So, to assess the system's performance, he used a more rigorous metric called optical depth, which describes the amount of that penetrates the fog.

Optical depth is independent of distance, so the performance of the system on fog that has a particular optical depth at a range of 1 meter should be a good predictor of its performance on fog that has the same optical depth at a range of 30 meters. In fact, the system may even fare better at longer distances, as the differences between photons' arrival times will be greater, which could make for more accurate histograms.

"Bad weather is one of the big remaining hurdles to address for autonomous driving technology," says Srinivasa Narasimhan, a professor of computer science at Carnegie Mellon University. "Guy and Ramesh's innovative work produces the best visibility enhancement I have seen at visible or near-infrared wavelengths and has the potential to be implemented on cars very soon."


Explore further

Computational method improves the resolution of time-of-flight depth sensors 1,000-fold

More information: Towards Photography Through Realistic Fog. web.media.mit.edu/~guysatat/fo … oughRealisticFog.pdf

This story is republished courtesy of MIT News (web.mit.edu/newsoffice/), a popular site that covers news about MIT research, innovation and teaching.

Citation: Depth-sensing imaging system can peer through fog (2018, March 21) retrieved 20 July 2019 from https://phys.org/news/2018-03-depth-sensing-imaging-peer-fog.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.
194 shares

Feedback to editors

User comments

Mar 23, 2018
Now we have driverless cars legally fatally running cyclists down because it is on camera!

A driverless car has just recently fatally run down a cyclist and it is on the cars camera, so the police are not prosecuting the car i.e. its manufacturers and are not prosecuting the safety driver! It is irrelevant the cars reactions are quicker than the safety driver, he was sitting with his feet talking no notice as he was legally entitled to do, so what is the point of a safety driver. By the time he realised the car has run the cyclist over he can only react if he's driving and he wasn't driving and now Toyota has withdrawn its driverless cars and so has firm using the cars! if he had been driving he would have anticipated the cyclist walking out into the road and taken evasive action but a driverless cars cannot anticipate human actions only humans can anticipate human actions so now we have driverless cars legally fatally running cyclsts down!

Mar 23, 2018
Human drivers anticipate human behaviour and avoid accidents

There are only a small number of driverless cars on the road and there only a small number of people involved in fatal accidents in the total number millions of cars on the road, so taking into account the driverless car ran a cyclist down in the poultry few driverless cars on the road speaks volumes, extrapolate this number to the millions of cars on the road and the number of cyclist run down will be horrific! Which proves the point, human drivers are anticipating human behaviour and avoiding accidents and unlike driverless cars that do not even get prosecuted, human drivers get prosecuted!

Mar 23, 2018
Driving with anticipation; expecting something in the road at distance

The fog vision sensor enables the car to see people on kerb, but as the driverless car has shown its no earthly use to the car being able to see people on kerb if the is not programmed with human perception! So it can anticipate a person venturing on to the road from their body language at distance and drive defensively, either stopping well short, or driving slowly, driving on the other side of the road or just coming up to halt and politely letting the pedestrians cross. In other words, driving with anticipation; expecting something in the road at distance

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more