Prompt:
What are some of the ways that computer vision differs from human vision? What are some techniques we can use to help the computer see / track what we’re interested in? How do you think computer vision’s capacity for tracking and surveillance affects its use in interactive art?
Response:
From my understanding plus the reading’s interpretation regarding computer vision, computer vision differs from human vision as human’s ability is sort of built-in inside our brain and takes way less energy and time to train our ability to recognize certain objects. For CV, however, they not only need numerous examples to learn certain facts, but also they consume huge amount of energy. Also, during the process of learning the ability to recognize, computer algorithms would often “cut” pictures into small pieces and train based on that while human learn to recognize as a whole.
Techniques that assist computer to see and track include frame differencing, background subtraction, brightness threshold, and simple tracking. I believe computer’s ability to track and surveillance could assist interactive art to be more interactive. For example, if I want to design a background music/scenes for a dancer, and if i want to change the background according to the dancer’s movements, I need CV as a technique to help me calculate parameters that could be applied into algorithms which later on could turn into shapes/sounds/etc..