Computer Vision





The interactive transcript could not be loaded.



Rating is available when the video has been rented.
This feature is not available right now. Please try again later.
Published on Nov 22, 2010

There is more to getting a robot to see the world than connecting a video camera to it. Without software that can analyze the images coming from that video, a robot would not be able to make much sense of the information.

The way our eyes and brain work together is quite amazing and the inspiration for the field of Computer Vision. CV Algorithms are needed to break apart the images into meaningful pieces and begin the process of understanding context.

Much work remains to be done in the area, but progress shown in the video is certainly exciting and promising.

Video Narration:
Getting a computer to understand what it is "seeing" is a very challenging problem. To do this in real-time, even more so. In this prototype, a camera is attached to Alvaro's glasses. The black and white video is not being shown to him, but rather, that video is what the software is "seeing". The video is being analyzed by a task-specific vision algorithm and finds milk in his hand and boxes of rice on the shelves.

In the future, having a robot help in the kitchen will require it to understand what it is seeing, before it attempts to pick anything up. Or the robot might be a smart agent looking over someone with a cognitive disability and will understand what someone is attempting to do and then help coach them through the task.


When autoplay is enabled, a suggested video will automatically play next.

Up next

to add this to Watch Later

Add to

Loading playlists...