Hacker News Reader

I don't really see how you could effectively use this technology on subjects that are not stationary and under controlled light conditions.

View on HN

I agree with you, the results (not theory) are similar to Horprasert's background subtraction paper. Both techniques have same limitations. It is pixel-by-pixel and does not take the entire scene into account.

Yet more cheap computation can adjust for whatever motion/lighting variances are present.

I think you are missing the point. It makes no sense to compute away motion if motion is what you are trying to capture.

This algorithm is intended to capture and amplify minute movements without physical contact by measuring the color of individual pixels over time.

All the processing power in the world won't help you much if there are no small movements to measure in the first place.

Reply on news.ycombinator.com