Azriel Rosenfeld

Transcription

Humans have been perfecting their sensory abilities for millions of years. Eyesight combined with brain power allows people to identify faces, recognize objects, perceive their environment and then take action based on those observations. In the Center for Automation Research known as CfAR, Maryland researchers are committed to bringing these same sensory skills to modern computing platforms. We've been working on the problem of computer vision for over 50 years trying to get computers the ability to see with the same type of accuracy that people do to be able to recognize everyday objects, everyday actions of people and the context in which they're being done While CfAR has almost two dozen faculty and research scientists in its four unique labs it can trace its roots back to the dedicated efforts of one man. The center was established by Azriel Rosenfeld, who was a research professor here in College Park and Azriel really was the founder of the whole field of computer vision. He wrote the first textbook and he started the first journal and he started the first conference and he probably wrote most of the first few hundred papers. Research in CfAR today includes new visualization tools that are used in healthcare. These groundbreaking applications can help medical professionals gain new insight into serious conditions like traumatic brain injury or Parkinson's disease. Projects in virtual and augmented reality are also underway creating immersive interactive platforms that let people see and use information that matters most to them. CfAR has also developed a technology that allows people to access more than 10,000 news feeds from around the world simply by clicking on a map location. And if you want to know what song bird is chirping outside of your window check out BirdSnap, an electronic field guide that can identify thousands of species of birds in the wild. For public safety, CfAR is building facial recognition software that can identify people in less than perfect environments even if they're slightly out of focus or moving away from a surveillance camera. The Holy Grail here is to understand what's in an image what’s in a video, who’s in it, what they’re doing when the image was taken, where it was taken. So we consider all of this as [an] inference problem. inference problem. Given a single image or video sequence – how much information can you gather from there. Recent work in CfAR involves autonomous robotic systems designing robots that will soon be able to think and act on their own. this means that humanoid robots using skills obtained from artificial intelligence, computer vision, and language processing software could soon be helping out around your house or apartment. In our project with robots we are trying to create a technology so that robots eventually can interact with humans. So one thing is they need to understand what humans are are doing what their actions are and for that we need tools so they can pick up their action track them, and all that in real time. One project has robots watching YouTube cooking videos Hi I'm Julia your personal chef. And then using their own knowledge system to figure out the best way to make a salad. I am looking for the dressing. When these cognitive robots that see and reason and act in the world appropriately it will change fundamentally our societies. What else can I do for you today?