lots more Vision profiling. For my parents’ information, that means that I found out what specific parts of the vision system slow the Aibo down. For the Aibo, ‘slow’ means that it can process less information in a second, or another way of putting it is that its reaction time degrades. Ideally, the Aibo will make decisions at about 30 times a second. Currently, with a bunch of stuff that we’ve been adding and some bottlenecks we’ve only just discovered, it’s down to about 23-25 frames per second (fps). <\/p>\n
Moving onto more complicated things for fellow nBiters: over 50%<\/em> of the average vision frame is taken up by chromatic distortion filtering<\/strong>. I know, it seems pretty ridiculous to me as well. About 25% percent of a vision frame is just thresholding, 7% is for line recognition, and then the rest is basically python processes including the EKF. Check the Wiki for more details.<\/p>\n Anyways, here are the areas for optimization: In other news, I found another huge bug in our body transforms just a few minutes ago: turns out I was doing body rotations in the wrong order (apparently matrix multiplication order matters, who knew?) and it took me re-reading and re-reading the German, Ozzie, and Texan papers to figure the proper order out. The focal point estimates look a lot better now in cortex and so I’ll be testing distance estimates tomorrow. <\/p>\n Next up: finally figuring out the pose-estimated horizon line swiftly followed by blob rotation fun. Fun.<\/p>\n","protected":false},"excerpt":{"rendered":" lots more Vision profiling. For my parents’ information, that means that I found out what specific parts of the vision system slow the Aibo down. For the Aibo, ‘slow’ means that it can process less information in a second, or another way of putting it is that its reaction time degrades. Ideally, the Aibo will […]<\/p>\n","protected":false},"author":56,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[5,31,44,46,53,74],"tags":[],"class_list":["post-234","post","type-post","status-publish","format-standard","hentry","category-asides","category-localization","category-pose","category-profiling","category-robocup","category-vision"],"_links":{"self":[{"href":"https:\/\/research.bowdoin.edu\/robocup\/wp-json\/wp\/v2\/posts\/234","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/research.bowdoin.edu\/robocup\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/research.bowdoin.edu\/robocup\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/research.bowdoin.edu\/robocup\/wp-json\/wp\/v2\/users\/56"}],"replies":[{"embeddable":true,"href":"https:\/\/research.bowdoin.edu\/robocup\/wp-json\/wp\/v2\/comments?post=234"}],"version-history":[{"count":0,"href":"https:\/\/research.bowdoin.edu\/robocup\/wp-json\/wp\/v2\/posts\/234\/revisions"}],"wp:attachment":[{"href":"https:\/\/research.bowdoin.edu\/robocup\/wp-json\/wp\/v2\/media?parent=234"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/research.bowdoin.edu\/robocup\/wp-json\/wp\/v2\/categories?post=234"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/research.bowdoin.edu\/robocup\/wp-json\/wp\/v2\/tags?post=234"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\n-Chromatic Distortion (duh). We may be seriously screwing something up.
\n-Thresholding (duh). There may be more we can do here, either by reducing the size of the LUT or memory-wise.
\n-Python Overhead — see the tests on Trac, but I believe we’re losing about 3-4 fps just on creating python objects from c objects, a project ripe for Jeremy’s attention.<\/p>\n