Eye-tracking aquarium tells users about the specific fish they’re watching

When you look at a tank full of fish at an aquarium, you may not know which fish is what. AI Aquariums are designed to help by overlaying information along the individual fish in question.

The AI ​​Aquarium, created by Taiwan’s Industrial Technology Research Institute (ITRI), recently won a CES Innovation Award. Here’s how it works…

An outward-facing, depth-sensing 3D camera above the tank tracks the viewer’s eyes to determine where they are looking in the tank.another camera pointing into the Aquarium tracks the location of all fish. Real-time video from his second camera is analyzed by an object recognition algorithm. The algorithm visually matches each fish to photographs of known species in a computer database.

By comparing the viewer’s line of sight and the position of the fish, the AI ​​aquarium can determine not only the individual fish currently observed, but also which species the fish belongs to. This information is displayed on a transparent micro-LED screen above the aquarium’s front glass, with the text superimposed right next to the human’s view of the fish.

AI aquarium eye-tracking and object recognition systems are reportedly immune to factors such as ambient light and water clarity
AI aquarium eye-tracking and object recognition systems are reportedly immune to factors such as ambient light and water clarity

ITRI

If viewers want more information than just the name of the fish, use simple hand gestures to prompt the system to show more details.

The AI ​​aquarium system is already in use at Taiwan’s National Museum of Marine Science and Technology. You can see it in action in the video below.

AI Aquarium

Source: ITRI



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *