7 juin 2019 | International, Aérospatial, C4ISR

Deep Learning Model Speeds Up, Automates Satellite Image Analysis

Lockheed Martin (NYSE: LMT) develops satellite imagery recognition system using open-source deep learning libraries to quickly identify and classify objects or targets in large areas across the world, potentially saving image analysts countless hours manually categorizing and labeling items within an image. Global Automated Target Recognition runs in the cloud, using Maxar's Geospatial Big Data platform (GBDX) to access Maxar's 100 petabyte satellite imagery library and millions of curated data labels across dozens of categories that expedite the training of deep learning algorithms. Fast GPU's let GATR scan a large area very quickly, while deep learning methods automate object recognition and reduce the need for extensive algorithm training.

GATR teaches itself what the identifying characteristics of an object area or target, for example, learning how to distinguish between a cargo plane and a military transport jet. The system scales quickly to scan large areas, including entire countries. GATR uses deep learning techniques common in the commercial sector and can identify ships, airplanes, buildings, seaports, and many other categories.

“There's more commercial satellite data than ever available today, and up until now, identifying objects has been a largely manual process,” said Maria Demaree, vice president and general manager of Lockheed Martin Space Mission Solutions. “Artificial Intelligence models like GATR keep analysts in control while letting them focus on higher-level tasks.”

GATR has a high accuracy rate, well over 90% on the models we've tested so far. It only took two hours to search the entire state of Pennsylvania for fracking sites – that's 120,000 square kilometers

“I'm not an expert on what oil production sites are, and I don't have to be,” said Mark Pritt, senior fellow at Lockheed Martin and principle investigator for GATR. “This system teaches itself the defining characteristics of an object, saving valuable time training an algorithm and ultimately letting an image analyst focus more on their mission.”

GATR builds on research Pritt's team pioneered during a Intelligence Advanced Research Projects Activity (IARPA) challenge, called the “Functional Map of the World.” The Lockheed Martin team was the only team from a company who placed in the top five.

https://news.lockheedmartin.com/news-releases?item=128745

Sur le même sujet

  • Embraer strengthens its Industrial Cooperation with the Czech Republic

    6 octobre 2024 | International, Aérospatial

    Embraer strengthens its Industrial Cooperation with the Czech Republic

    This new milestone reinforces Embraer’s commitment to strengthening its ties with its local partners, thus contributing to their growth.

  • Expect heavier hand, ‘bite’ from DOD zero-trust office, boss says

    26 juin 2024 | International, C4ISR, Sécurité

    Expect heavier hand, ‘bite’ from DOD zero-trust office, boss says

    The memo will give the young office “bite," its top boss said.

  • Saab offers Gripen technology transfer to Indian partner

    18 octobre 2019 | International, Aérospatial

    Saab offers Gripen technology transfer to Indian partner

    Saab offers Gripen technology transfer to Indian partner Bengaluru, Oct 17 (IANS) Swedish aerospace major Saab on Thursday offered technology transfer to its Indian partner for making its fighter Gripen if it wins the Indian Air Force (IAF) order to supply 114 jets. "We will transfer technology to our Indian partner for making Gripen in India if we win the IAF order," Saab India Technologies Managing Director Ola Rignell told reporters here. Technology transfer will also enable Saab to make India its production base for exporting aerospace components to countries where it has operations or customers, he said. Saab is in fray for the multi-billion-dollar global tender to make in India 110 advanced medium multi-role combat aircraft (MMRCA) with five other global aerospace majors Dassault (Rafale), Eurofighter (Typhoon), Boeing (F-18A), Lockheed Martin (F-21) and Russian Aircraft Corporation (MiG-35). The decision to make 114 fighters indigenously was taken after India cancelled the global tender for supply 126 MMRCA in July 2015 and opted in 2016 to buy 36 Rafales from the French Dassault Aviation, which won the contract for an estimated $8.4 billion (Rs 59,000 crore) from the previous NDA government. The tender, floated in April 2018, mandates the bidder to accept an Indian partner chosen by the Indian government. "It is the Indian government''s prerogative to choose the strategic partner for making the fighters in India with the winner of the bid," Rignell said. All the six firms submitted their bids in July 2018, responding to the government''s Request for Proposal (RFP) after Request for Information (RFI) in 2017. Saab, however, decided to set up its India base in Bengaluru, which is also the country''s aerospace hub with the presence of the state-run defence major HAL and aircraft design and development organisations like ADA. "We want Bengaluru to be the base to make Gripen for the IAF as the city has talent as well as resources," Rignell said. Building an ecosystem and making investments is a part of the Swedish firm''s offer to be in contention for the fighter deal. https://www.outlookindia.com/newsscroll/saab-offers-gripen-technology-transfer-to-indian-partner/1642925

Toutes les nouvelles