{"id":1457,"date":"2020-01-19T23:42:16","date_gmt":"2020-01-19T23:42:16","guid":{"rendered":"https:\/\/www.danielparente.net\/en\/2020\/01\/19\/artificial-intelligence-system-created-to-allows-self-driving-cars-to-see-around-corners\/"},"modified":"2020-01-19T23:42:16","modified_gmt":"2020-01-19T23:42:16","slug":"artificial-intelligence-system-created-to-allows-self-driving-cars-to-see-around-corners","status":"publish","type":"post","link":"https:\/\/www.danielparente.net\/en\/2020\/01\/19\/artificial-intelligence-system-created-to-allows-self-driving-cars-to-see-around-corners\/","title":{"rendered":"Artificial Intelligence system created to allows self-driving cars to ‘see’ around corners"},"content":{"rendered":"

[ad_1]
\n<\/p>\n

\n

An artificial intelligence system that allows self-driving cars to ‘see’ around corners in real time could help prevent accidents, according to its developers.\u00a0<\/p>\n

Researchers from Stanford University in the USA have created a system that bounces a laser beam off a wall to create an ‘image’ of objects hidden from view.<\/p>\n

The ‘image’ captured won’t make sense to a human, but using artificial intelligence technology the system can create a visual reconstruction of the hidden view.\u00a0<\/p>\n

The research was funded by US government agency DARPA (Defence Advanced Research Projects Agency), and is one of a number of similar technology programmes being developed.<\/p>\n

It could also be used by soldiers to see around walls, rescue workers searching for people and even in space travel to examine the interior caves of an asteroid.<\/p>\n

Scroll down for video<\/span><\/p>\n

\n
\n
\"\"<\/div>\n

The systems might one day let self-driving cars ‘look’ around parked cars or busy intersections to not only see cars but also read license plates<\/p>\n<\/div>\n

As well as the Stanford researchers, the team included experts from Princeton University, Southern Methodist University and Rice University.<\/p>\n

The researchers used a commercially available camera sensor and a powerful, but standard, laser in the new system –\u00a0similar to the one found in a laser pointer.\u00a0\u00a0<\/span><\/p>\n

The laser beam bounces off a visible wall onto the hidden object and then back onto the wall, creating an interference pattern known as a speckle.<\/p>\n

‘Reconstructing the hidden object from the speckle pattern requires solving a challenging computational problem’, said Metzler.<\/p>\n

He said short exposure times are necessary for real-time imaging but produce too much noise for existing algorithms to work.\u00a0<\/p>\n

\n
\n
<\/div>\n

A camera uses light scattered off of a rough wall, known as a virtual detector, to reconstruct an image of the hidden object. When using a continuous-wave laser, the camera records speckle<\/p>\n<\/div>\n

To solve this problem, the researchers turned to deep learning, a form of machine learning that is better for interpreting large and varied data.<\/p>\n

‘Compared to other approaches for non-line-of-sight imaging, our deep learning algorithm is far more robust to noise and thus can operate with much shorter exposure times,’ said co-author Prasanna Rangarajan.<\/p>\n

‘By accurately characterising the noise, we were able to synthesise data to train the algorithm to solve the reconstruction problem.’<\/p>\n

Effectively the artificial intelligence system filters out the noise to create an ‘image’ of what is hiding behind the wall or object.\u00a0<\/p>\n

He said they were able to do this using deep learning without having to capture costly training data, as would be needed by traditional machine learning.\u00a0\u00a0<\/p>\n

‘Our imaging system provides uniquely high resolutions and imaging speeds,’ said research team leader Christopher A. Metzler from Stanford University.<\/p>\n

‘These attributes enable applications that wouldn’t otherwise be possible, such as reading the license plate of a hidden car as it is driving’.<\/p>\n

It has been designed to image small objects at high resolutions, but can be combined with other systems to produce low-resolution images of larger items.\u00a0<\/p>\n

‘Non-line-of-sight imaging has important applications in medical imaging, navigation, robotics and defence,’ said co-author Felix Heide.<\/p>\n

‘Our work takes a step toward enabling its use in a variety of such applications.’<\/p>\n

They tested their new technique by recreating images of 0.4 inch tall letters and numbers hidden behind a corner.<\/p>\n

\n
\n
\"The<\/div>\n

The research was funded by DARPA, the Defence Advanced Research Projects Agency and is one of a number of similar technology programmes being developed<\/p>\n<\/div>\n

An imaging system was setup about one metre from the wall hiding the letters and they used an exposure length of a quarter of a second.<\/p>\n

This\u00a0approach produced reconstructions of the real letters that were hidden behind the wall with a resolution a quarter of the original image height.<\/span><\/p>\n

The study is part of DARPA’s Revolutionary Enhancement of Visibility by Exploiting Active Light-fields (REVEAL) program, which is developing a variety of different techniques to image hidden objects around corners.\u00a0\u00a0<\/p>\n

DARPA says on its website: ‘The REVEAL program aims to develop a comprehensive theoretical framework to enable maximum information extraction.<\/p>\n

‘Taking it from complex scenes by using all photon pathways and leveraging light’s multiple degrees of freedom.’<\/p>\n

The researchers are now working to make the system practical for more applications by extending the field of view so that it can reconstruct larger objects.<\/p>\n

The research has been published in the journal Optica<\/a>.\u00a0<\/p>\n

<\/p>\n

\n

WHAT IS DEEP LEARNING?<\/h3>\n
\n

Deep learning is a form of\u00a0machine learning concerned with algorithms which have a wide range of applications.\u00a0<\/p>\n

It is a field which was inspired by the human brain and focuses on building artificial neural networks.<\/p>\n

It was formed originally based on brain simulations and to allow learning algorithms to become better and easier to use.\u00a0<\/p>\n

Processing vast amounts of complex data then becomes much easier and allows researchers to trust algorithms to draw accurate conclusions based on the parameters the researchers have set.\u00a0<\/p>\n

Task-specific algorithms which exist are better for specific tasks and goals but deep-learning allows for a wider scope of data collection.\u00a0<\/p>\n<\/div>\n<\/div>\n

<\/mol-permabox><\/p>\n

\u00a0<\/p>\n<\/div>\n

[ad_2]
\n
Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

[ad_1] An artificial intelligence system that allows self-driving cars to ‘see’ around corners in real time could help prevent accidents, according to its developers.\u00a0 Researchers from Stanford University in the USA have created a system that bounces a laser beam off a wall to create an ‘image’ of objects hidden from view. The ‘image’ captured […]<\/p>\n","protected":false},"author":1,"featured_media":1458,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","jetpack_post_was_ever_published":false},"categories":[96],"tags":[],"class_list":["post-1457","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-autonomous-cars"],"blocksy_meta":[],"jetpack_featured_media_url":"https:\/\/e928cfdc7rs.exactdn.com\/info\/uploads\/sites\/3\/2020\/01\/Artificial-Intelligence-system-created-to-allows-self-driving-cars-to-see.jpg?strip=all","jetpack_shortlink":"https:\/\/wp.me\/p2TFCd-nv","jetpack_sharing_enabled":true,"jetpack-related-posts":[],"_links":{"self":[{"href":"https:\/\/www.danielparente.net\/en\/wp-json\/wp\/v2\/posts\/1457","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.danielparente.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.danielparente.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.danielparente.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.danielparente.net\/en\/wp-json\/wp\/v2\/comments?post=1457"}],"version-history":[{"count":0,"href":"https:\/\/www.danielparente.net\/en\/wp-json\/wp\/v2\/posts\/1457\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.danielparente.net\/en\/wp-json\/wp\/v2\/media\/1458"}],"wp:attachment":[{"href":"https:\/\/www.danielparente.net\/en\/wp-json\/wp\/v2\/media?parent=1457"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.danielparente.net\/en\/wp-json\/wp\/v2\/categories?post=1457"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.danielparente.net\/en\/wp-json\/wp\/v2\/tags?post=1457"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}