{"id":287522,"date":"2013-06-24T09:00:58","date_gmt":"2013-06-24T16:00:58","guid":{"rendered":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/?p=287522"},"modified":"2016-09-12T11:47:12","modified_gmt":"2016-09-12T18:47:12","slug":"computer-vision-view-world","status":"publish","type":"post","link":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/blog\/computer-vision-view-world\/","title":{"rendered":"A Computer-Vision View of the World"},"content":{"rendered":"

A robot comes up from the subway. How does it know where it is?<\/p>\n

To most people, this sounds like the opening line of a joke, but for Jamie Shotton<\/a>, senior researcher in the Computer Vision Group at Microsoft Research Cambridge<\/a>, the \u201clost robot\u201d is a classic problem that he wants to solve through scene recognition and camera localization. From June 23 to 28, Shotton will be joining fellow researchers in Portland, Oregon, for CVPR 2013 (opens in new tab)<\/span><\/a>, where they will be sharing novel approaches to such problems and a multitude of others with academics and other industrial researchers.<\/p>\n

\u201cCVPR is the premier annual conference on computer vision,\u201d says Richard Szeliski (opens in new tab)<\/span><\/a>, a Microsoft distinguished scientist, manager of the Interactive Visual Media Group at Microsoft Research Redmond<\/a>, and one of four program chairs for CVPR 2013. \u201cAs usual, we have a very strong showing from Microsoft vision researchers from our labs worldwide. We\u2019re looking forward to presenting our work to other leading scientists and learning from them about the latest technical advances in our field.\u201d<\/p>\n

When Szeliski talks about a strong showing from Microsoft Research, he means more than just the number of attendees and the papers being presented. He also is referring to the exceptional talent of researchers such as Shotton.<\/p>\n

Getting Behind the Camera<\/h2>\n
\"Jamie

Jamie Shotton<\/p><\/div>\n

Shotton was the major contributor to the human body-part recognition algorithm used by Kinect for Windows (opens in new tab)<\/span><\/a> for skeletal tracking. Real-Time Human Pose Recognition in Parts from Single Depth Images<\/em><\/a>, co-authored by a team drawn from Microsoft Research Cambridge and the Xbox Incubation group, was awarded the best-paper prize during CVPR 2011 and the 2011 MacRobert Award (opens in new tab)<\/span><\/a> from the Royal Academy of Engineering. He was also part of the Xbox and Xbox incubation team that won the 2012 Microsoft Outstanding Technical Achievement award for incorporating the body-part-recognition algorithm into a successful product.<\/p>\n

During CVPR 2013, Shotton will be presenting his latest project, Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images<\/em><\/a>, which he co-authored with Cambridge colleagues Ben Glocker (opens in new tab)<\/span><\/a>, Christopher Zach (opens in new tab)<\/span><\/a>, Shahram Izadi (opens in new tab)<\/span><\/a>, Antonio Criminisi<\/a>, and Andrew Fitzgibbon<\/a>. Their approach uses machine learning to predict where pixels in an image live in the real, 3-D world and, in doing so, infer the position of the camera when it captured the image.<\/p>\n

\u201cWhile this is a line of research that started with Kinect body tracking,\u201d Shotton explains, \u201cit\u2019s morphed into quite a different thing. It\u2019s about predicting the position of the camera. This paper presents a new, efficient algorithm for estimating the camera position very accurately from a single depth image relative to a known scene or environment.\u201d<\/p>\n

This has important implications in robotics. The \u201clost robot\u201d problem places a robot in a random spot in an environment. When the robot starts, it needs to determine where it is. Shotton\u2019s new approach lets the robot \u201csee\u201d in a way that infers its starting position.<\/p>\n

\"Camera

Camera tracks for one of the test scenes, showing the frame by frame location of the camera as it moves around the room to scan the environment. Red points represent actual camera location. Green points show tracking as derived from a standard approach. Blue points represent the output from the new regression-forest algorithm, showing a smoother, more accurate result.<\/p><\/div>\n

Augmented reality is another area that could benefit from accurate camera localization: imagine looking at a scene through a smartphone camera and seeing information about the landmarks overlaid on the screen. Shotton also envisions the potential for enhanced navigation.<\/p>\n

\u201cFor example, when you come up out of the subway, you might be standing at an intersection,\u201d he says. \u201cA GPS can tell you which intersection, but only approximately. So you take a photo and use it to know where you\u2019re standing in the world, without needing any other information. What we have right now is just a stepping stone to the ultimate goal, which is to scale up this solution to unknown, large environments, but the results suggest this approach could scale up quite well.\u201d<\/p>\n

Thriving on Diversity<\/h2>\n

For anyone who thinks that skeletal tracking research must\u2019ve consumed all of Shotton\u2019s time during 2011, one look at his list of publications<\/a> reveals that he\u2019s interested in almost every area of computer vision. Since 2003, Shotton has authored or co-authored more than 50 research papers, on topics ranging from object recognition to human-pose estimation, gesture and action recognition, machine learning, and medical imaging.<\/p>\n

Shotton got a taste of life at Microsoft Research during an internship. That led to a scholarship from Microsoft Research for his Ph.D. studies from 2003 to 2007 and more internships at the Cambridge lab in 2003 and 2005, followed by one at the Redmond lab in 2006\u2014all boding well for a career at Microsoft Research after graduation. Shotton, though, decided to see more of the world first and spent a year working at Toshiba\u2019s research lab in Kawasaki, just outside Tokyo. In 2008, Shotton returned to the United Kingdom and joined Microsoft Research when a post-doc opportunity presented itself.<\/p>\n

\u201cJapan was a great experience,\u201d he recalls. \u201cI got exposure to a very different work environment, an interesting culture, a beautiful country, and lots of great snowboarding. I\u2019m an avid snowboarder, but lately I\u2019ve started skiing again and find I\u2019m enjoying that a lot.\u201d<\/p>\n

A perfect vacation for Shotton would involve either skiing and snow, or sunshine and salt water. He is also a certified scuba diver.<\/p>\n

\u201cAnd I used to go skydiving,\u201d he says. \u201cThat was my hobby for a while. But it takes a lot of time, because you have to be there at the drop zone every weekend for hours on end. In the U.K., this is even more time-consuming, because you\u2019re always hanging around waiting for the weather to clear\u2014not a very practical hobby.\u201d<\/p>\n

Does he have any hobbies that don\u2019t involve so much adrenaline?<\/p>\n

\u201cMusic. I have a fairly strong classical-music background,\u201d Shotton says, \u201cbecause I learned piano and cello when I was growing up. I sing in a choir: second bass. Our repertoire is mostly classical with some jazzy pieces. We\u2019re a pretty decent ensemble.\u201d<\/p>\n

With so many interests, in his personal life and in his research, it\u2019s clear that Shotton gets stimulation from the opportunity to work on a variety of challenges.<\/p>\n

\u201cOne of the things I enjoy most about working for Microsoft Research is collaborating with the amazing people here,\u201d he says. \u201cIt sounds like a clich\u00e9, but it\u2019s true. There\u2019s such a buzz, always so much going on, always something exciting. There\u2019s never a dull moment. I love the diverse projects and the diverse approaches to solving problems.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"

A robot comes up from the subway. How does it know where it is? To most people, this sounds like the opening line of a joke, but for Jamie Shotton, senior researcher in the Computer Vision Group at Microsoft Research Cambridge, the \u201clost robot\u201d is a classic problem that he wants to solve through scene […]<\/p>\n","protected":false},"author":39507,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":[],"msr_hide_image_in_river":0,"footnotes":""},"categories":[194466,194471,194455],"tags":[212252,212249,212243,212237,202141,193602,212240,212255,197837],"research-area":[13561,13556,13562],"msr-region":[],"msr-event-type":[],"msr-locale":[268875],"msr-post-option":[],"msr-impact-theme":[],"msr-promo-type":[],"msr-podcast-series":[],"class_list":["post-287522","post","type-post","status-publish","format-standard","hentry","category-algorithms","category-computer-vision","category-machine-learning","tag-lost-robot-problem","tag-body-part-recognition-algorithm","tag-camera-localization","tag-cvpr-2013","tag-jamie-shotton","tag-kinect-for-windows","tag-scene-recognition","tag-skeletal-tracking","tag-xbox","msr-research-area-algorithms","msr-research-area-artificial-intelligence","msr-research-area-computer-vision","msr-locale-en_us"],"msr_event_details":{"start":"","end":"","location":""},"podcast_url":"","podcast_episode":"","msr_research_lab":[199561,199565],"msr_impact_theme":[],"related-publications":[],"related-downloads":[],"related-videos":[],"related-academic-programs":[],"related-groups":[],"related-projects":[],"related-events":[],"related-researchers":[],"msr_type":"Post","byline":"","formattedDate":"June 24, 2013","formattedExcerpt":"A robot comes up from the subway. How does it know where it is? To most people, this sounds like the opening line of a joke, but for Jamie Shotton, senior researcher in the Computer Vision Group at Microsoft Research Cambridge, the \u201clost robot\u201d is…","locale":{"slug":"en_us","name":"English","native":"","english":"English"},"_links":{"self":[{"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/posts\/287522","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/users\/39507"}],"replies":[{"embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/comments?post=287522"}],"version-history":[{"count":7,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/posts\/287522\/revisions"}],"predecessor-version":[{"id":291770,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/posts\/287522\/revisions\/291770"}],"wp:attachment":[{"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/media?parent=287522"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/categories?post=287522"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/tags?post=287522"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=287522"},{"taxonomy":"msr-region","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-region?post=287522"},{"taxonomy":"msr-event-type","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-event-type?post=287522"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=287522"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=287522"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=287522"},{"taxonomy":"msr-promo-type","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-promo-type?post=287522"},{"taxonomy":"msr-podcast-series","embeddable":true,"href":"https:\/\/newed.any0.dpdns.org\/en-us\/research\/wp-json\/wp\/v2\/msr-podcast-series?post=287522"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}