The reading sounded technical to me. It had a lot of insightful new information about interactive designs using computer vision. The author talked about Low-level computer vision algorithms and three techniques: frame differencing, background subtraction, and brightness thresholding, detecting motion using frame differencing, and differentiating pixels. Detection through brightness thresholding makes desired objects darker or lighter than their surroundings using illumination. Object tracking is related to finding injects based on the brightness of pixels. Basic interaction locating body pixels and the information can be used in graphical responses in interactive systems. He also highlights problems that come with these algorithms for instance, if people are too close or if the physical circumstances are not good enough. Using IR (infrared) helps in these situations. He also talks about how the use of a “telecentric” lens can significantly improve the performance of certain kinds of shape-based or size-based object recognition algorithms.
I liked the quote: “But even the most sophisticated algorithms and highest-quality hardware cannot help us find meaning where there is none or track an object which cannot be described in code” mainly because it emphasizes the limited capabilities of computers and highlights that without human beings and their logic the computer can do nothing because it only understands zeros and ones. I think computer vision algorithm in interactive and computer-based artworks adds more to the user’s experience, and from the reading, it is not as hard or overwhelming as it sounds. I am not a technical person, but I think that the reading provides a good overview of the potential of computer vision in interactive art. It made me think of codes or the digital world as tools with which Art can be empowered and improved and not just something that is solely technical or logical.