www.ucl.ac.uk
Open in
urlscan Pro
2606:4700:4400::6812:27c2
Public Scan
URL:
https://www.ucl.ac.uk/news/2017/jul/measuring-distance-single-photo
Submission: On June 13 via manual from US — Scanned from DE
Submission: On June 13 via manual from US — Scanned from DE
Form analysis 2 forms found in the DOM
GET //search2.ucl.ac.uk/s/search.html
<form role="search" action="//search2.ucl.ac.uk/s/search.html" method="get">
<div class="search-form">
<span class="twitter-typeahead" style="position: relative; display: inline-block; width: 100%; direction: ltr;"><input type="search" placeholder="Search UCL websites, degrees, short courses, people and more"
aria-label="Search UCL websites, degrees, short courses" class="search-form__input search-form__input--search tt-input" name="query" value="" autocomplete="off" spellcheck="false" dir="auto" style="position: relative; vertical-align: top;">
<pre aria-hidden="true"
style="position: absolute; visibility: hidden; white-space: pre; font-family: "Helvetica Neue", Helvetica, Arial, "Lucida Grande", sans-serif; font-size: 14px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; word-spacing: 0px; letter-spacing: 0px; text-indent: 0px; text-rendering: auto; text-transform: none;"></pre>
<span class="tt-dropdown-menu"
style="position: fixed; width: 90%; left: 5%; top: 48px; right: auto; z-index: 5050; border: 1px solid rgb(170, 170, 170); border-radius: 4px; box-shadow: rgba(51, 51, 51, 0.298039) 2px 2px 2px; display: none; background-color: rgb(255, 255, 255);">
<div class="AC-result AC-result--websites"></div>
<div class="AC-result AC-result--degrees"></div>
<div class="AC-result AC-result--directory"></div>
<div class="AC-result AC-result--research"></div>
</span>
</span>
</div>
<input type="hidden" name="collection" value="website-meta">
<input type="hidden" name="profile" value="_website">
<input type="hidden" name="tab" value="websites">
<input type="submit" name="submit" value="Go" class="btn btn--primary search-form__input search-form__input--submit">
</form>POST /news/2017/jul/measuring-distance-single-photo
<form action="/news/2017/jul/measuring-distance-single-photo" method="post" id="openid-connect-login-form" accept-charset="UTF-8">
<div><input style="background: url(//cdn.ucl.ac.uk/skins/UCLIndigoSkin/default-theme/images/edit.gif);" class="ad_login_button_cross form-submit" type="submit" id="edit-openid-connect-client-windows-aad-login" name="windows_aad" value=""><input
type="hidden" name="form_build_id" value="form-zs_Tj6Sjsbcm_cGIPc2bXGYQnATQZ5w8Y-c-9ShZq1A">
<input type="hidden" name="form_id" value="openid_connect_login_form">
</div>
</form>Text Content
Close * UCL Home * Prospective students * Current students * Staff * Give UCL News Home * Home * Latest news * UCL in the media * Services for media * Student news * Staff news * Tell us your story * Contact us * UCL Home * UCL News * Measuring distance with a single photo * Home * Latest news * UCL in the media * Services for media * Student news * Staff news * Tell us your story * Contact us * Home * Latest news * UCL in the media * Services for media * Student news * Staff news * Tell us your story * Contact us * UCL Home * UCL News * Measuring distance with a single photo MEASURING DISTANCE WITH A SINGLE PHOTO 26 July 2017 Most cameras just record colour but now the 3D shapes of objects, captured through only a single lens, can be accurately estimated using new software developed by UCL computer scientists. * Video The method, published today at CVPR 2017, gives state-of-the-art results and works with existing photos, allowing any camera to map the depth for every pixel it captures. The technology has a wide variety of applications, from augmented reality in computer games and apps, to robot interaction, and self-driving cars. Historical images and videos can also be analysed by the software, which is useful for reconstruction of incidents or to automatically convert 2D films into immersive 3D. "Inferring object-range from a simple image by using real-time software has a whole host of potential uses," explained supervising researcher, Dr Gabriel Brostow (UCL Computer Science). "Depth mapping is critical for self-driving cars to avoid collisions, for example. Currently, car manufacturers use a combination of laser-scanners and/or radar sensors, which have limitations. They all use cameras too, but the individual cameras couldn't provide meaningful depth information. So far, we've optimised the software for images of residential areas, and it gives unparalleled depth mapping, even when objects are on the move." The new software was developed using machine learning methods and has been trained and tested in outdoor and urban environments. It successfully estimates depths for thin structures such as street signs and poles, as well as people and cars, and quickly predicts a dense depth map for each 512 x 256 pixel image, running at over 25 frames per second. Currently, depth mapping systems rely on bulky binocular stereo rigs or a single camera paired with a laser or light-pattern projector that don't work well outdoors because objects move too fast and sunlight dwarfs the projected patterns. There are other machine-learning based systems also seeking to get depth from single photographs, but those are trained in different ways, with some needing elusive high-quality depth information. The new technology doesn't need real-life depth datasets, and outperforms all the other systems. Once trained, it runs in the field by processing one normal single-lens photo after another. "Understanding the shape of a scene from a single image is a fundamental problem. We aren't the only ones working on it, but we have got the highest quality outdoors results, and are looking to develop it further to work with 360 degree cameras. A 360 degree depth map would be fantastically useful - it could drive wearable tech to assist disabled people with navigation, or to map real-life locations for virtual reality gaming, for example," added first author and UCL PhD student, Clément Godard (UCL Computer Science). Co-author, Dr Oisin Mac Aodha, previously at UCL and now at Caltech, added: "At the moment, our software requires a desktop computer to process individual images, but we plan on miniaturising it, so it can be run on hand-held devices such as phones and tablets, making it more accessible to app developers. We've also only optimised it for outdoor use, so our next step is to train it on indoor environments." The team has patented the technology through UCL Business, but has made the code available free for non-commercial use. Funding for the research was kindly provided by the Engineering and Physical Sciences Research Council. VIDEO LINKS * Research homepage * Dr Gabriel Brostow's academic profile * UCL Computer Science * Media coverage IMAGE * UCL MonoDepth software in action (credit: Dr Gabriel Brostow) MEDIA CONTACT BEX CAYGILL Tel: +44 (0)20 3108 3846 Email: r.caygill [at] ucl.ac.uk Share FOLLOW US * * * * * -------------------------------------------------------------------------------- UCL FACILITIES * About UCL * Faculties and departments * Library * Museums and Collections * UCL Bloomsbury Theatre * UCL Shop UCL LOCATIONS * Maps and buildings * UCL and London * UCL Global * UCL East CONNECT WITH UCL * Alumni * Businesses * Media Relations * Jobs * Support us * * * * * * * -------------------------------------------------------------------------------- * University College London, Gower Street, London, WC1E 6BT Tel: +44 (0) 20 7679 2000 * Copyright © 2022 UCL * Disclaimer * Freedom of Information * Accessibility * Privacy and Cookies * Slavery statement * Contact Us * Cookie settings Our website uses cookies Some of these cookies are essential, while others help us to improve your experience of our website. Find out more: Privacy Policy (opens in new window) Accept all cookies Manage cookies Necessary cookies Necessary cookies enable core functionality such as page navigation and access to secure areas. The website cannot function properly without these cookies, and they can only be disabled by changing your browser preferences. Analytics and customisation cookies These cookies enhance the functionality of our websites and improve your user experience. Without these cookies, certain functionality (like videos, personalised content or the ability to save your favourite content) may not work. Advertising cookies These cookies are used to make advertising messages more relevant to you. They perform functions like preventing the same ad from continuously reappearing, ensuring that ads are properly displayed for advertisers, and in some cases selecting advertisements that are based on your interests. Save preferences Withdraw consent