Computer Vision EECS 274
Popular in Course
verified elite notetaker
Popular in Electrical Engineering & Computer Science
This 47 page Class Notes was uploaded by Keshaun Larkin on Thursday October 29, 2015. The Class Notes belongs to EECS 274 at University of California - Merced taught by Staff in Fall. Since its upload, it has received 20 views. For similar materials see /class/231716/eecs-274-university-of-california-merced in Electrical Engineering & Computer Science at University of California - Merced.
Reviews for Computer Vision
Report this Material
What is Karma?
Karma is the currency of StudySoup.
Date Created: 10/29/15
EECS 274 Computer Vision Lecture 1 Introduction What is computer vision Terminator 2 Every picture tells a story Goal of computer vision is to write computer programs that can interpret images Can computers match or beat human vision Yes and no but mostly no humans are much better at hard things computers can be better at easy things Copyright AKitaoka 2003 2191amp X 2 x k Edward H Meagan M New A H Optical i USIOHS Why is computer vision difficult Inverse problem HLposed Highdimensional data Noise Variation Earth viewers 3D modeling Image from Microsoft s Virtual Earth see also Google Earth Google streetview Photosynth mm mm Photosynth What if your photo collation was an entry point into the world 39 Tryit Whammmmm I warm1019 that yuu couldu p through and explo mains Y Tea blmj 5 ThE letusvntlu Tedumlugv p Eycmrvg39 avtc vimI Dlmtos e ph a war an clue em 1 anth at muted threerdlnlzl anal svaze hcwum vcu htt91llabsivecom9hotosynth httgvvww youtu be comwatchv91 6erJ LViO by Noah Snavely Steve Seitz and Rick Szeliski Optical character recognition Technology to convert scanned docs to text If you have a scanner it probably came with OCR software MEMBER Digit recognition ATampT labs License plate readers h llwwwresearcha com ann mt Hen Wlkl edla or MildAutomath number late reco nltlon Face detection Many new digital cameras now detect faces Canon Sony Fuji Smile detection The Smile Shutter flow 1 uiym mm uujusHhexigm39 r Son C ber shot T70 Di ital Still Camera Object recognition in supermarkets LaneHaka EvolutionRobotics A smart camera is ushmounted 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 LaneHawkyou are assured to get paid for it Face recognition GEOGRAPHIC m muamamum arm Mm slwnAIanmcximnmnunu w Who is she Visionbased biometrics Login without a password Face recognition systems now beginning to appear more widely tt lwwwsensibevisioncoml Fingerprint scanners on many new laptops other devices Object recognition in mobile phones This is becoming real 39 LlnCOIn MiorosoftResearoh Point amp Find Nokia NTT Dooomo Special effects shape capture Bullet time htt www outubecomwatchVJ5 LMZTOSM The Matrix movies ESC Entertainment XYZRGB NRC Special effects motion capture Pirates ofthe Carribean Industrial Light and Magic Click here for interactive demo Sports Sportvision rst down line Nice explanation on wwwhowstuffworkscom htggWwwyoutubecomwatchvUyPU219rdvo Slide content courtesy ofAmnon Shashua Evenls 39 39 39 39 Advante gtVIsron Applications gtAWS Waming System gtrrrguwm a hip 7 Road Vehitle Pedestrian Proietliun gt CIDMIEXYEEISEHAVLES quot and more k EyeQ Vision on gt rad mm raid mm mamE Vision systems currently in highend BMW GM Volvo models By 2010 70 of car manufacturers Vicieo demo Visionbased interaction and games Nintendo Mi has camerabased IR tracking built in See Lee s work at CMU on clever tricks on using it to create a multitouch display a 393 iv Game turns movie ers into Human Jo sticks CN ET Camera tracking a crowd based on this work Visionbased HCI Reatrix httQwwwyoutubecomwatchvstQKU LMbiU Gaming Sony Eyetoy Microsoft Natal 6amp23455759 httpwwwyoutubecomwatchvAOXo httpwwwy0utubecomwatchv1BRSf hr4XE 4ampfeaturerelated CuL YHc Motion capture Markerbased motion capture htt www outubeoomwatohvV0 T8mw 9no Organic motion httQwwworganicmotioncom Looking at people a Hand gesture 7quot3 quotr1 a Head pose Expression Identity htt www outubecomwatchvNwVBZXOL1N pan 5 Vision in space NASA39S Mars Exploration Rover Spirit captured this westward view from atop a low plateau where Spirit spent the closing months of 2007 Vision systems JPL used for several tasks 0 Panorama stitching 0 3D terrain modeling 0 Obstacle detection position tracking 0 For more read Computer Vision on Marsquot by Matthies et al Gigapan httpwwwgigaganorgindexth HP TouchSmart with Gigapn demo at Chicago O Hare airport Robotics NASA s Mars Spirit Rover httpwwwmbocupprg htt lenwiki ediaor lwikiS irit rover Medical imaging Image guided surgery Grimson et al MIT 3D imaging MRI CT Digital comestics 9 V 339 Inpainting Acadlans Cajuns African Bertalmio et a1 SGGMPH 00 Debluring Fergus et a1 SIGGRAPH 06 Digital photo albums Picasa Flickr Photobucket etc Categorization Tagging Search Computational photography Image acquisition Hardwaresoftware Optics Shuttle speed Novel sensors Multiple camera Multiple shots Multi flash Applications high dynamic range imaging super resolution photomontage panorama moasicing debluring light field camera projector system Image and video search Google YouTubes Microsoft Yahoo Current state of the art You just saw examples of current systems Many of these are less than 5 years old This is a very active research area and rapidly changing Many new applications in the next 5 years To learn more about vision applications and companies David Lowe maintains an excellent overview of vision companies httpwwwcsubccaspiderIowevisionhtml Confluence of vision graphics learning sensing and signal processing Software and hardware Algorithms processing images and videos Camera acquiring imagesvideos Embedded system Topics Image formation camera model camera calibration radiometry color shading Early vision stereopsis structure from motion illumination reflectance shape from X texture Midlevel vision segmentation grouping Kalman filter particle filter shape representation Highlevel vision correspondence matching object detection object recognition visual tracking Recent topics image and video retrieval internet vision Related topics swam mus maxva mmwlihnna mamm mm Iman Mamemmb Textbooks and references Textbook Computer Vision A Modern Approach David Forsyth and Jean Ponce Computer Vision Algorithms and Applications draft Richard Szeliski Reference for background study Introductory Techniques for 3D Computer Vision Emanuele Trucco and Alessandro Verri Multiple View Geometry in Computer Vision Richard Hartley and Andrew Zisserman An Invitation to 3D Vision by Yi Ma Stefano Soatto and Jana Kosecka Robot Vision Berthold Horn Learning OpenCV Computer Vision with OpenCV Library Gary Bradski and Adrian Kaehler Reading assignments will be from the text and additional material that will be handed out or made available on the web Page All lecture slides will be available on the course website httpfacultvucmercededumhvanqcoursecse274indexhtm Grading Based on projects No midterm or final 20 Homework 40 Programming assignments 40 Term project Project 1 features Figure 1 Mulri sz ad Orienred Parclm MOPS mramd ar vc pyramid mix from one off1e Marin images The boxes tun mme L 39 39 u iv 1 mw1ich rveuuuiplm ILLIU a sampled Project 2 LucasKande Tracker httpWwwyoutubecomwatchvyo QSQSXng Project 3 object detection Term Project Openended project of your choosing Oral presentation Midterm presentation Final presentation and demo Publish your results General Comments Prerequisites these are essential Data structures A good working knowledge of MATLAB C and C programming Linear algebra Vector calculus Course does not assume prior imaging experience computer vision image processing graphics etc