Highlights from the 2014 LA Auto Show

Object Recognition

LEVAN learns by associating words with images

Word-picture association is one of the basic mechanisms of human memory. As children, it helps us to learn language by verbalizing what we see, as adults it is an invaluable aid to visualizing broader concepts or perhaps helping those with an LBLD (Language-Based Learning Disability). Now researchers from the University of Washington and the Allen Institute for Artificial Intelligence have created the first fully automated computer program named LEVAN that teaches itself everything there is to know about a visual concept by associating words with images.  Read More

The new AOD object-detection software system from Fujitsu

When it comes to driver awareness, we all know how hard it can be to keep an eye on every pedestrian and moving vehicle in our vicinity, particularly when driving in a busy city area. Couple this with the upcoming Kids and Transportation Safety Act in the US that dictates that all cars built from May 2018 onwards must be fitted with rear view cameras as standard, and it becomes doubly important that on-board vehicle cameras are used to their best advantage. To help in this regard, Fujitsu Semiconductor Limited is set to introduce software that assists in detecting and identifying cars, people, and other moving objects and alerts the driver of their position and direction of travel.  Read More

The Evolution-Constructed Features algorithm can identify and learn new objects without hu...

Scientists at Brigham Young University have developed an algorithm that can accurately identify objects in images or videos and can learn to recognize new objects on its own. Although other object recognition systems exist, the Evolution-Constructed Features algorithm is notable in that it decides for itself what features of an object are significant for identifying the object and is able to learn new objects without human intervention.  Read More

An iRobot PackBot navigates a school, in a demonstration of the Cognitive Patterns system

It’s sometimes easy to forget that for all their human-like qualities, robots are in fact machines. While some systems allow them to recognize basic objects, they still don’t necessarily make sense of what they’re looking at – they might see and recognize a box, for instance, but what does the presence of a box suggest to them? Now, researchers at Massachusetts-based engineering firm Aptima are developing a system known as Cognitive Patterns. It allows robots and humans to collaborate on building the robots’ understanding of the world, thus allowing them to operate on their own more effectively.  Read More

The sketch-identifying program at work

Currently, using Google’s “Search by Image” function, it’s possible to search the internet for information on something if you already have an image of that thing. Also, researchers at Carnegie Mellon University are developing a system that allows computers to match up users’ drawings of objects with photographs of those same items – the drawings have to be reasonably good, though. Now, however, a team from Rhode Island’s Brown University and the Technical University of Berlin have created software that analyzes users’ crude, cartoony sketches, and figures out what it is that they’re trying to draw.  Read More

The EyeRing system features a finger-worn camera module and wirelessly connected smartphon...

Generally speaking, the vast majority of augmented reality applications that enhance the world around us by overlaying digital content on images displayed on smartphone, tablet or computer screens are aimed squarely at the sighted user. A team from the Fluid Interfaces Group at MIT's Media Lab has developed a chunky finger-worn device called EyeRing that translates images of objects captured through a camera lens into aural feedback to aid the blind.  Read More

Kinsight is an experimental system that uses networked Kinect cameras to locate missing ob...

Have you ever wished that your computer could answer questions like “What did he mean when he said that?” or “Should I go to that party?” Well, while that may never happen, it could conceivably provide you with an answer if you asked it, “Where did I leave my wallet?” – if it were running the Kinsight system.  Read More

Toshiba Tec's new supermarket scanner is able to identify grocery items based on nothing b...

At some point, we’ve probably all had a supermarket cashier ask us to identify the mysterious fresh produce that we’re attempting to buy. Once we’ve told them what it is, they have then had to manually type in its code – they have to enter it themselves, of course, given that fruits and vegetables don’t have barcodes. Thanks to Toshiba Tec, however, those days may be coming to an end. The company’s new Object Recognition Scanner is able to instantly identify grocery items of all types based on their appearance alone.  Read More

A new radar system could be used to detect and identify objects that fall onto train track...

Although you may never have seen it happen yourself, it isn’t all that uncommon for large objects – including people – to fall onto the tracks at subway or railway platforms. While security personnel viewing CCTV feeds will catch some of these accidents, the cameras’ shots are sometimes obscured by people, poor lighting, or even the trains themselves. The results can range from lengthy delays in rail service, to fatalities. Now, however, researchers working on a project for the Université Lille Nord de France have developed a system that uses radar to automatically detect and identify objects that fall onto the tracks. When installed at a platform, the system could then shut off power to the tracks, and notify oncoming trains.  Read More

A 'heat mean signature' of a human hand is used to perceive the six segments of the overal...

When we see a hand, regardless of whether it's open, in a fist, or pointing a finger, we still recognize it as a hand. If a computer has only been taught to recognize an open hand, however, it will probably have no idea what a fisted hand is. Getting computer vision systems to interpret images more like people do - to realize that a fist is a hand, for instance - has been one of the aims of artificial intelligence researchers for some time now. Things in that field may be about to take a step forward, however, as scientists from Indiana's Purdue University have just announced two new methods of three-dimensional object recognition, both based around heat diffusion.  Read More

Looking for something? Search our 29,568 articles