Computer Vision ECEToday’s classIntroductionsComputer VisionVision is really hardWhy computer vision mattersRidiculously brief history of computer visionCurrent state of the artEarth viewers (3D modeling)Photosynth.net3D from multiple images3D from one imageOptical character recognition (OCR)Face detectionSmile detection?Object recognition (in supermarkets)Vision-based biometricsLogin without a password…Object recognition (in mobile phones)Special effects: shape captureSpecial effects: motion captureSportsSmart carsVision-based interaction (and games)Vision in spaceIndustrial robotsMobile robotsMedical imagingRecent newsSlide 30Slide 31Slide 32Course logisticsWhat to expect from this courseQuestionsComputer VisionECE CS 543 / ECE 549 University of IllinoisInstructors: Derek Hoiem, David ForsythTA: Varsha HedauPresenter: Derek HoiemToday’s class•Introductions•Intro to computer vision•Course logistics•QuestionsIntroductionsComputer VisionMake computers understand images and video.What kind of scene?Where are the cars?How far is the building?…Vision is really hard•Vision is an amazing feat of natural intelligence–Visual cortex occupies about 50% of Macaque brain–More human brain devoted to vision than anything elseIs that a queen or a bishop?Why computer vision mattersSafetyHealth SecurityComfortAccessFunRidiculously brief history of computer vision•1966: Minsky assigns computer vision as an undergrad summer project•1960’s: interpretation of synthetic worlds•1970’s: some progress on interpreting selected images•1980’s: ANNs come and go; shift toward geometry and increased mathematical rigor•1990’s: face recognition; statistical analysis in vogue•2000’s: broader recognition; large annotated datasets available; video processing startsGuzman ‘68Ohta Kanade ‘78Turk and Pentland ‘91Current state of the art•Some examples of what current vision systems can doMany of the following slides by Steve SeitzEarth viewers (3D modeling)Image from Microsoft’s Virtual Earth(see also: Google Earth)Photosynth.netBased on Photo Tourismby Noah Snavely, Steve Seitz, and Rick Szeliski3D from multiple imagesBuilding Rome in a Day: Agarwal et al. 20093D from one imageHoiem Efros Hebert SIGGRAPH 2005Optical character recognition (OCR)Digit recognition, AT&T labshttp://www.research.att.com/~yann/Technology to convert scanned docs to text•If you have a scanner, it probably came with OCR softwareLicense plate readershttp://en.wikipedia.org/wiki/Automatic_number_plate_recognitionFace detection•Many new digital cameras now detect faces–Canon, Sony, Fuji, …Smile detection?Sony Cyber-shot® T70 Digital Still CameraObject recognition (in supermarkets)LaneHawk by EvolutionRobotics“A smart camera is flush-mounted in the checkout lane, continuously watching for items. When an item is detected and recognized, the cashier verifies the quantity of items that were found under the basket, and continues to close the transaction. The item can remain under the basket, and with LaneHawk,you are assured to get paid for it… “Vision-based biometrics“How the Afghan Girl was Identified by Her Iris Patterns” Read the story wikipediaLogin without a password…Fingerprint scanners on many new laptops, other devicesFace recognition systems now beginning to appear more widelyhttp://www.sensiblevision.com/Object recognition (in mobile phones)•This is becoming real:–Point & Find, NokiaThe Matrix movies, ESC Entertainment, XYZRGB, NRCSpecial effects: shape capturePirates of the Carribean, Industrial Light and MagicClick here for interactive demoSpecial effects: motion captureSportsSportvision first down lineNice explanation on www.howstuffworks.comSmart cars•Mobileye–Vision systems currently in high-end BMW, GM, Volvo models –By 2010: 70% of car manufacturers.Slide content courtesy of Amnon ShashuaVision-based interaction (and games)Nintendo Wii has camera-based IRtracking built in. See Lee’s work atCMU on clever tricks on using it tocreate a multi-touch display! Digimask: put your face on a 3D avatar.“Game turns moviegoers into Human Joysticks”, CNETCamera tracking a crowd, based on this work.Vision in spaceVision systems (JPL) used for several tasks•Panorama stitching•3D terrain modeling•Obstacle detection, position tracking•For more, read “Computer Vision on Mars” by Matthies et al.NASA'S Mars Exploration Rover Spirit captured this westward view from atop a low plateau where Spirit spent the closing months of 2007.Industrial robotsVision-guided robots position nut runners on wheelsMobile robotshttp://www.robocup.org/NASA’s Mars Spirit Roverhttp://en.wikipedia.org/wiki/Spirit_roverSaxena et al. 2008STAIR at StanfordMedical imagingImage guided surgeryGrimson et al., MIT3D imagingMRI, CTRecent newsRecent newsRecent newsCurrent state of the art•You just saw examples of current systems.–Most of these are less than 5 years old•This is a very active research area, and rapidly changing–Many new apps in the next 5 years•To learn more about vision applications and companies–David Lowe maintains an excellent overview of vision companies•http://www.cs.ubc.ca/spider/lowe/vision.htmlCourse logistics•Web page: http://www.cs.uiuc.edu/homes/dhoiem/courses/vision_spring10/•Attendance•Office hours•Assignments and grades•Final projectWhat to expect from this course•Broad coverage (geometry, image processing, recognition, multiview, video)•Background to delve deeper into any computer vision-related topic•Practical