Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:

 

Teaching machines to see

21.12.2015

New smartphone-based system could accelerate development of driverless cars

Two newly-developed systems for driverless cars can identify a user's location and orientation in places where GPS does not function, and identify the various components of a road scene in real time on a regular camera or smartphone, performing the same job as sensors costing tens of thousands of pounds.


This is an example of SegNet in action: the separate components of the road scene are all labelled in real time.

Credit: Alex Kendall

The separate but complementary systems have been designed by researchers from the University of Cambridge and demonstrations are freely available online. Although the systems cannot currently control a driverless car, the ability to make a machine 'see' and accurately identify where it is and what it's looking at is a vital part of developing autonomous vehicles and robotics.

The first system, called SegNet, can take an image of a street scene it hasn't seen before and classify it, sorting objects into 12 different categories -- such as roads, street signs, pedestrians, buildings and cyclists - in real time. It can deal with light, shadow and night-time environments, and currently labels more than 90% of pixels correctly. Previous systems using expensive laser or radar based sensors have not been able to reach this level of accuracy while operating in real time.

Users can visit the SegNet website and upload an image or search for any city or town in the world, and the system will label all the components of the road scene. The system has been successfully tested on both city roads and motorways.

For the driverless cars currently in development, radar and base sensors are expensive - in fact, they often cost more than the car itself. In contrast with expensive sensors, which recognise objects through a mixture of radar and LIDAR (a remote sensing technology), SegNet learns by example -- it was 'trained' by an industrious group of Cambridge undergraduate students, who manually labelled every pixel in each of 5000 images, with each image taking about 30 minutes to complete. Once the labelling was finished, the researchers then took two days to 'train' the system before it was put into action.

"It's remarkably good at recognising things in an image, because it's had so much practice," said Alex Kendall, a PhD student in the Department of Engineering. "However, there are a million knobs that we can turn to fine-tune the system so that it keeps getting better."

SegNet was primarily trained in highway and urban environments, so it still has some learning to do for rural, snowy or desert environments -- although it has performed well in initial tests for these environments.

The system is not yet at the point where it can be used to control a car or truck, but it could be used as a warning system, similar to the anti-collision technologies currently available on some passenger cars.

"Vision is our most powerful sense and driverless cars will also need to see," said Professor Roberto Cipolla, who led the research. "But teaching a machine to see is far more difficult than it sounds."

As children, we learn to recognise objects through example -- if we're shown a toy car several times, we learn to recognise both that specific car and other similar cars as the same type of object. But with a machine, it's not as simple as showing it a single car and then having it be able to recognise all different types of cars. Machines today learn under supervision: sometimes through thousands of labelled examples.

There are three key technological questions that must be answered to design autonomous vehicles: where am I, what's around me and what do I do next. SegNet addresses the second question, while a separate but complementary system answers the first by using images to determine both precise location and orientation.

The localisation system designed by Kendall and Cipolla runs on a similar architecture to SegNet, and is able to localise a user and determine their orientation from a single colour image in a busy urban scene. The system is far more accurate than GPS and works in places where GPS does not, such as indoors, in tunnels, or in cities where a reliable GPS signal is not available.

It has been tested along a kilometre-long stretch of King's Parade in central Cambridge, and it is able to determine both location and orientation within a few metres and a few degrees, which is far more accurate than GPS -- a vital consideration for driverless cars. Users can try out the system for themselves here.

The localisation system uses the geometry of a scene to learn its precise location, and is able to determine, for example, whether it is looking at the east or west side of a building, even if the two sides appear identical.

"Work in the field of artificial intelligence and robotics has really taken off in the past few years," said Kendall. "But what's cool about our group is that we've developed technology that uses deep learning to determine where you are and what's around you - this is the first time this has been done using deep learning."

"In the short term, we're more likely to see this sort of system on a domestic robot - such as a robotic vacuum cleaner, for instance," said Cipolla. "It will take time before drivers can fully trust an autonomous car, but the more effective and accurate we can make these technologies, the closer we are to the widespread adoption of driverless cars and other types of autonomous robotics."

The researchers are presenting details of the two technologies at the International Conference on Computer Vision in Santiago, Chile.

Media Contact

Sarah Collins
sarah.collins@admin.cam.ac.uk
44-012-237-65542

 @Cambridge_Uni

http://www.cam.ac.uk 

Sarah Collins | EurekAlert!

Further reports about: GPs autonomous vehicles deep learning orientation vehicles

More articles from Information Technology:

nachricht Ultra-precise chip-scale sensor detects unprecedentedly small changes at the nanoscale
18.01.2017 | The Hebrew University of Jerusalem

nachricht Data analysis optimizes cyber-physical systems in telecommunications and building automation
18.01.2017 | Fraunhofer-Institut für Algorithmen und Wissenschaftliches Rechnen SCAI

All articles from Information Technology >>>

The most recent press releases about innovation >>>

Die letzten 5 Focus-News des innovations-reports im Überblick:

Im Focus: Traffic jam in empty space

New success for Konstanz physicists in studying the quantum vacuum

An important step towards a completely new experimental access to quantum physics has been made at University of Konstanz. The team of scientists headed by...

Im Focus: How gut bacteria can make us ill

HZI researchers decipher infection mechanisms of Yersinia and immune responses of the host

Yersiniae cause severe intestinal infections. Studies using Yersinia pseudotuberculosis as a model organism aim to elucidate the infection mechanisms of these...

Im Focus: Interfacial Superconductivity: Magnetic and superconducting order revealed simultaneously

Researchers from the University of Hamburg in Germany, in collaboration with colleagues from the University of Aarhus in Denmark, have synthesized a new superconducting material by growing a few layers of an antiferromagnetic transition-metal chalcogenide on a bismuth-based topological insulator, both being non-superconducting materials.

While superconductivity and magnetism are generally believed to be mutually exclusive, surprisingly, in this new material, superconducting correlations...

Im Focus: Studying fundamental particles in materials

Laser-driving of semimetals allows creating novel quasiparticle states within condensed matter systems and switching between different states on ultrafast time scales

Studying properties of fundamental particles in condensed matter systems is a promising approach to quantum field theory. Quasiparticles offer the opportunity...

Im Focus: Designing Architecture with Solar Building Envelopes

Among the general public, solar thermal energy is currently associated with dark blue, rectangular collectors on building roofs. Technologies are needed for aesthetically high quality architecture which offer the architect more room for manoeuvre when it comes to low- and plus-energy buildings. With the “ArKol” project, researchers at Fraunhofer ISE together with partners are currently developing two façade collectors for solar thermal energy generation, which permit a high degree of design flexibility: a strip collector for opaque façade sections and a solar thermal blind for transparent sections. The current state of the two developments will be presented at the BAU 2017 trade fair.

As part of the “ArKol – development of architecturally highly integrated façade collectors with heat pipes” project, Fraunhofer ISE together with its partners...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

Event News

Sustainable Water use in Agriculture in Eastern Europe and Central Asia

19.01.2017 | Event News

12V, 48V, high-voltage – trends in E/E automotive architecture

10.01.2017 | Event News

2nd Conference on Non-Textual Information on 10 and 11 May 2017 in Hannover

09.01.2017 | Event News

 
Latest News

Helmholtz International Fellow Award for Sarah Amalia Teichmann

20.01.2017 | Awards Funding

An innovative high-performance material: biofibers made from green lacewing silk

20.01.2017 | Materials Sciences

Ion treatments for cardiac arrhythmia — Non-invasive alternative to catheter-based surgery

20.01.2017 | Life Sciences

VideoLinks
B2B-VideoLinks
More VideoLinks >>>