Researchers from UCLA Samueli School of Engineering and Stanford have demonstrated a computer system that can discover and identify the real-world objects it “sees” based on the same method of visual learning that humans use.
The system is an advance in a type of technology called “computer vision,” which enables computers to read and identify visual images. It is an important step toward general artificial intelligence systems–computers that learn on their own, are intuitive, make decisions based on reasoning and interact with humans in a more human-like way. Although current AI computer vision systems are increasingly powerful and capable, they are task-specific, meaning their ability to identify what they see is limited by how much they have been trained and programmed by humans.
Even today’s best computer vision systems cannot create a full picture of an object after seeing only certain parts of it–and the systems can be fooled by viewing the object in an unfamiliar setting. Engineers are aiming to make computer systems with those abilities–just like humans can understand that they are looking at a dog, even if the animal is hiding behind a chair and only the paws and tail are visible. Humans, of course, can also easily intuit where the dog’s head and the rest of its body are, but that ability still eludes most artificial intelligence systems.
Current computer vision systems are not designed to learn on their own. They must be trained on exactly what to learn, usually by reviewing thousands of images in which the objects they are trying to identify are labeled for them.
Computers, of course, also cannot explain their rationale for determining what the object in a photo represents: AI-based systems do not build an internal picture or a common-sense model of learned objects the way humans do.
The engineers’ new method, described in the Proceedings of the National Academy of Sciences, shows a way around these shortcomings.
The approach is made up of three broad steps. First, the system breaks up an image into small chunks, which the researchers call “viewlets.” Second, the computer learns how these viewlets fit together to form the object in question. And finally, it looks at what other objects are in the surrounding area, and whether or not information about those objects is relevant to describing and identifying the primary object.
To help the new system “learn” more like humans, the engineers decided to immerse it in an internet replica of the environment humans live in.
“Fortunately, the internet provides two things that help a brain-inspired computer vision system learn the same way humans do,” said Vwani Roychowdhury, a UCLA professor of electrical and computer engineering and the study’s principal investigator. “One is a wealth of images and videos that depict the same types of objects. The second is that these objects are shown from many perspectives–obscured, bird’s eye, up-close–and they are placed in different kinds of environments.”
To develop the framework, the researchers drew insights from cognitive psychology and neuroscience.
“Starting as infants, we learn what something is because we see many examples of it, in many contexts,” Roychowdhury said. “That contextual learning is a key feature of our brains, and it helps us build robust models of objects that are part of an integrated worldview where everything is functionally connected.”
The researchers tested the system with about 9,000 images, each showing people and other objects. The platform was able to build a detailed model of the human body without external guidance and without the images being labeled.
The engineers ran similar tests using images of motorcycles, cars and airplanes. In all cases, their system performed better or at least as well as traditional computer vision systems that have been developed with many years of training.
The Latest on: Computer vision
via Google News
The Latest on: Computer vision
- Snapshot of the Emerging ICT Led Innovations in Artificial Intelligence, Machine Learning, Analytics, and Computer Visionon September 6, 2019 at 8:29 am
DUBLIN, Sept. 6, 2019 /PRNewswire/ -- The "Recent Innovations in Information Technology, Computing, and Communications" report has been added to ResearchAndMarkets.com's offering. This provides a ...
- Analytics in the IoT public sector: Perfecting with computer visionon September 5, 2019 at 9:12 pm
No matter how complex private-sector deployments of cognitive computing, the Internet of Things, or advanced analytics may be, the goals are still relatively simple. The objectives in business are to ...
- UW launches new school of computer science, responding to student demand and workforce needon September 5, 2019 at 3:06 pm
The vision for a new School of Computer, Data and Information Sciences reflects a number of forces coming together on the flagship campus. Computer science is now the most popular undergraduate major ...
- How does a computer ‘see’ gender?on September 5, 2019 at 11:15 am
Machine vision tools like facial recognition are increasingly being ... to examine thousands of image search results in our own studies. But unlike traditional computer programs – which follow a ...
- AI in Computer Vision Market is Gaining an Upward Trend Due to Rising Demand for Mobile Edge Computingon September 5, 2019 at 4:45 am
The AI in computer vision market will surpass a valuation of USD 27 billion, attaining a CAGR of 45% during the forecast period (2017-2023), Market Research Future (MRFR) unveils in a detailed report.
- DeepBlue Technology and NUS School of Computing to collaborate on computer vision researchon September 5, 2019 at 4:05 am
SHANGHAI, Sept. 5, 2019 /PRNewswire/ -- DeepBlue Technology today announced its collaboration with the School of Computing at the National University of Singapore (NUS) to jointly conduct research on ...
- Microsoft’s Vision AI Developer Kit is now generally availableon September 3, 2019 at 6:14 pm
In May 2018 — during its annual Build developer conference in Seattle — Microsoft announced a partnership with Qualcomm to create what it described as a developer kit for computer vision ...
- What is Metrology Part 11: Computer Visionon August 30, 2019 at 12:41 am
Computer vision is an interdisciplinary scientific field that deals with how computers can be made to analyze data from digital images or videos. From the perspective of engineering, it seeks to ...
- AIKEA Raspberry Pi home security system with AI computer visionon August 29, 2019 at 11:46 pm
If you would like to equip your home security system with an AI computer vision enabled Raspberry Pi home security camera, the AIKEA camera system launched by this week may be worth more investigation ...
- Five Providers of Computer Vision Software Named IDC Innovatorson August 28, 2019 at 8:13 pm
International Data Corporation (IDC) recently published an IDC Innovators report profiling five companies that offer compelling and differentiated computer vision software. The five companies are ...
via Bing News