Broadcast News

Bookmark and Share

Measuring Distance With A Single Photo

News Image
Most cameras just record colour but now the 3D shapes of objects, captured through only a single lens, can be accurately estimated using new software developed by UCL computer scientists.

The method, published at CVPR 2017, gives state-of-the-art results and works with existing photos, allowing any camera to map the depth for every pixel it captures.

The technology has a wide variety of applications, from augmented reality in computer games and apps, to robot interaction, and self-driving cars. Historical images and videos can also be analysed by the software, which is useful for reconstruction of incidents or to automatically convert 2D films into immersive 3D.

Dr Gabriel Brostow, UCL Computer Science supervising researcher, said: "Inferring object-range from a simple image by using real-time software has a whole host of potential uses. Depth mapping is critical for self-driving cars to avoid collisions, for example. Currently, car manufacturers use a combination of laser-scanners and/or radar sensors, which have limitations.

"They all use cameras too, but the individual cameras couldn't provide meaningful depth information. So far, we've optimised the software for images of residential areas, and it gives unparalleled depth mapping, even when objects are on the move."

The new software was developed using machine learning methods and has been trained and tested in outdoor and urban environments.

It successfully estimates depths for thin structures such as street signs and poles, as well as people and cars, and quickly predicts a dense depth map for each 512 x 256 pixel image, running at over 25 frames per second.

Currently, depth mapping systems rely on bulky binocular stereo rigs or a single camera paired with a laser or light-pattern projector that don't work well outdoors because objects move too fast and sunlight dwarfs the projected patterns.

There are other machine-learning based systems also seeking to get depth from single photographs, but those are trained in different ways, with some needing elusive high-quality depth information. The new technology doesn't need real-life depth datasets, and outperforms all the other systems. Once trained, it runs in the field by processing one normal single-lens photo after another.

First author and UCL PhD student, Clément Godard (UCL Computer Science), added: "Understanding the shape of a scene from a single image is a fundamental problem. We aren't the only ones working on it, but we have got the highest quality outdoors results, and are looking to develop it further to work with 360 degree cameras. A 360 degree depth map would be fantastically useful – it could drive wearable tech to assist disabled people with navigation, or to map real-life locations for virtual reality gaming, for example."

Co-author, Dr Oisin Mac Aodha, previously at UCL and now at Caltech, said: "At the moment, our software requires a desktop computer to process individual images, but we plan on miniaturising it, so it can be run on hand-held devices such as phones and tablets, making it more accessible to app developers. We've also only optimised it for outdoor use, so our next step is to train it on indoor environments."

The team has patented the technology for commercial use through UCL Business, but has made the code free for academic use. Funding for the research was kindly provided by the Engineering and Physical Sciences Research Council.

Go to the projects homepage, here.

Top Related Stories
Click here for the latest broadcast news stories.

Ikegami Demonstrates Broadcast Production Cameras
Following a well attended April 2024 NAB Show in Las Vegas, Ikegami demonstrated examples from its wide range of broadcast production cameras, control
Canon Europe To Offer Firmware For 4K Remote Cameras
Canon Europe is to offer firmware for 4K remote cameras and remote camera controllers intended to improve the functionality and performance of functio
Ikegami To Unveil Range Of Production Cameras At Broadcast Asia 2024
Ikegami is to introduce recent additions to its wide range of broadcast production cameras, monitors and related equipment on stand 6D3-1 (Hall 6) at
S&L Integrated Systems Relies On Marshall Cameras
S&L Integrated Systems, a leader in audio-visual technology solutions, has recently transformed courtroom experiences throughout Georgia and the surro
Vizrt Launches PTZ3 PLUS And PTZ3 UHD PLUS Cameras
Vizrt is bringing the BroadcastAV market sharply into focus with the launch of the PTZ3 PLUS and PTZ3 UHD PLUS cameras. Bridging the gap between ProAV
FOR-A Implements Complete System For MAP
FOR-A has implemented a complete system for Media and Art Production (MAP). The new facility is now online in Dubai Studio City. MAP is a leading prod
MAP Installs Lawo AoIP Infrastructure
Morocco's Radio-TV Broadcaster MAP has installed Lawo AoIP Infrastructure. According to a Moroccan proverb, the earth is a peacock, and Morocco is its
FOR-A Delivers Complete Flyaway Production Kit To MAP
FOR-A has delivered a complete flyaway production kit to Media and Art Production (MAP), based in Fujairah, United Arab Emirates. The kit was designed
Allegorithmic announces MaP|TIME Video Filter Designer for Adobe After Effects and Discreet Combustion
Allegorithmic, a young award-winning company specialising in complex media modelling technology, has announced MaP|TIME, a brand new plug-in for Adobe
zLense Launches Depth-Mapping Camera Solution
zLense has launched the world's first depth-mapping camera solution that captures 3D data and scenery in real-time and adds a 3D layer, which is optim
SMPTE Conference To Feature In-Depth Sessions
The Society of Motion Picture and Television Engineers (SMPTE), has announced that the SMPTE 2014 Annual Technical Conference and Exhibition (SMPTE 20
IBC 2013: Miranda To Demonstrate Depth Of Integration
Miranda Technologies, a Belden Brand, a global provider of integrated solutions for production, playout and delivery systems for television broadcaste
Grass Valley Showcases Breadth And Depth Of Solutions
At BroadcastAsia 2012 in Singapore, June 19-22, 2012, Grass Valley will showcase its latest suite of solutions to empower media companies with the mos
Cel-Soft Launches Automatic Depth-Chart Generator For Cel-Scope3D Stereoscopic Analyser At BVE
A major new addition to the Cel-Scope3D stereoscopic analyser was introduced by Cel-Soft on Stand L20 at BVE 2011. A new automatic logging option gene
Automatic Depth-Chart Generator For Cel-Scope3D Stereoscopic Analyser
A major new addition to the Cel-Scope3D stereoscopic analyser will be introduced by Cel-Soft on Stand L20 at BVE 2011 in London's Earls Court, between