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
- VisualCortex and i-PRO partner to facilitate enterprise-wide Computer Vision technology deployments in APACon August 4, 2022 at 5:19 pm
Video Intelligence Platform provider, VisualCortex, and advanced sensing technologies manufacturer, i-PRO APAC, partner to streamline end-to-end implementations for large-scale video ...
- How the Retail Industry Can Improve the Customer Experience, Increase Safety and Maximize Margins Through Computer Vision and Artificial Intelligenceon August 4, 2022 at 8:37 am
Retailers who successfully leverage computer vision with diagnostic, proactive and predictive analytics are gaining the much-needed competitive edge. In this article, we take a closer look at how ...
- Computer Vision Market to Grow at Healthy CAGR as the Potential keep on Unwinding | SkyQuest Technologyon August 4, 2022 at 5:23 am
Global Computer Vision market was valued at USD 11.02 Billion in 2021, and it is expected to reach a value of USD 30.94 Billion by 2028, at a CAGR of 15.89% over the forecast period ...
- VisualCortex and i-PRO Collaborate on Enterprise-Wide Computer Vision Tech Deploymentson August 3, 2022 at 12:26 pm
PRO, a global leader of advanced sensing technologies for Intelligent Surveillance and Public Safety, to streamline end-to-end deployment for enterprise-wide video analytics solutions within the Asia ...
- Computer Vision: How This Transformational Technology Is Changing The Way Businesses Interact With Customerson August 2, 2022 at 4:15 am
Over time, computer vision will make shopping easier, help us stay healthy and even make it easier to do things like bank on the go.
- Computer Vision Extracts Lightning From Footageon August 1, 2022 at 5:00 pm
While we may not gain a deeper scientific appreciation of lightning anytime soon, but we can capture it in various photography thanks to this project which leverages computer vision machine ...
- Computer Vision Market Size Insights 2022: Report Presents Revenue Share By Manufacturers, Future Scope And Demand Forecast To 2031on August 1, 2022 at 12:38 am
Kenneth Research, in its repository of market research reports, have recently added a report on Computer Vision Market which emphasizes on the lat ...
- Computer Vision Market Size Insights 2022: Report Presents Revenue Share by Manufacturers, Future Scope and Demand Forecast to 2031on July 31, 2022 at 5:01 pm
Aug 01, 2022 (AmericaNewsHour) -- Kenneth Research, in its repository of market research reports, have recently added a report on Computer Vision Market which emphasizes on the latest trends ...
- How Peloton is using computer vision to strengthen workoutson July 29, 2022 at 7:39 am
Were you unable to attend Transform 2022? Check out all of the summit sessions in our on-demand library now! Watch here. As you do push-ups, squats or ab work, heft dumbbells, jump or stretch, a ...
- Computer Vision Market 2022 Global Industry Forecasts Analysis, Company Profiles, Competitive Landscape and Key Regions Analysis | Top Countries Dataon July 28, 2022 at 4:46 am
Computer Vision Market size analysis, 2022 global industry research report presents a beginning to end assessment of the Computer Vision Market growth, improvement, share, zones, creators ...
via Bing News