Yes you are right. In video there are continuous streams of data for objects as well as multi-perspectives and dynamics of the objects, IOW more information. So mining info out of video should produce in general higher quality results than static images. Then there are various tricks to use to lower analysis resources like looking for changes over time by small sample probing, skipping frames at exponential backoff rates., etc.. And the more information you have as to what the video is before analysis the better.
Why do you say that should we train ourselves to prefer solutions that use more computing power? Is this because those solutions in general are more whole and manageable verses tweaked, hacked and optimized with loss of adaptability? John From: Russell Wallace [mailto:[EMAIL PROTECTED] I haven't done any video analysis myself, but it should be easier than other data types such as static images. Think of it this way: each frame of video is an image - except that other frames give you extra constraints. The added information is an asset, it makes things easier. Sure it uses more computing power, but that's not the limiting resource, and we need to train ourselves to actively prefer solutions that use more computing power. ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=231415&id_secret=28496782-e8d698
