The input image (left) and the output image (right), processed by the fully convolutional neural network
CREDIT: Skoltech
Skoltech scientists have created a new monitoring system for agricultural applications that performs real-time image segmentation on board the drone to identify hogweed. The research was published in a high-profile journal, IEEE Transactions on Computers.
Sosnovsky’s hogweed is equally hazardous for farming, local ecosystems, and human health. Direct contact with human skin, especially if aggravated by exposure to the Sun, causes severe burns that require continuous medical care and take weeks to heal. The rampant spread of Sosnovsky’s hogweed has become a real environmental disaster that extends across the whole of Russia, from its central part to Siberia and from Karelia to the Caucasus. Every year, the government allocates huge budgets (last year, 350 million rubles for Moscow alone) for hogweed elimination. Eradicating the poisonous plant has become one of the biggest challenges for Russian farming, environment, and healthcare.
In the mid-20th century, there were plans to use hogweed as a fodder crop, given its quick growth, low maintenance requirements, and fast proliferation. However, it soon transpired that hogweed was no good as a livestock feed and its exceptional natural properties were a major problem rather than an advantage. One plant can produce up to 100,000 seeds per year, which are easily dispersed by the wind. This means that a single plant accidentally left behind makes the clearing operation utterly pointless.
Accurate real-time localization of hogweed was the first issue that researchers from the Skoltech Center for Computational and Data-Intensive Science and Engineering (CDISE) encountered when they started developing their monitoring platform two years ago. “Conventional monitoring methods are not effective enough, since ground observations are highly dependent on the human factor, while space remote sensing can spot large thickets only. Satellite images do not have sufficient resolution to discern individual plants. Besides, traditional monitoring strongly depends on weather and satellite revisit periods and, therefore, cannot provide up-to-date information,” lead author and Skoltech PhD graduate Alexander Menshchikov explains.
The researchers decided to use drones that are able to capture up-to-date high-resolution hogweed images even in cloudy weather and opted for in-flight data acquisition and processing on board the drone instead of the classical “data capture – orthophotomap – data analysis” scheme. “Even though the traditional approach provides exhaustive information about the area, it is nearly as effective as processing data on board with segmentation for one type of object, i.e. Sosnovsky’s hogweed. Besides, in the traditional method, after-flight image stitching and analysis takes several hours, whereas in-flight processing produces real-time data which are immediately downloaded to the base station, so that the clearing of the targeted area could start before the drone lands,” Alexander adds.
The new monitoring solution uses a drone and a compact on-board computer which runs “heavy” segmentation algorithms based on Fully Convolutional Neural Networks (FCNN) that can identify an irregularly shaped object (in this case, Sosnovsky’s hogweed) pixel-by-pixel. This will help to discern individual plants and raise the chances of killing all the weeds in the selected area.
Running FCNNs on low-power hardware, such as single-board computers (SBC), was the main hindrance for the project. Since there are only a limited number of computers that have sufficient resources and processors that support FCNN, the researchers had to find a suitable SBC architecture and optimize FCNN to make it run on the selected hardware version.
“We chose popular architectures, UNet, SegNet, and ResNet, for our neural networks and adapted them for the SBC. We installed and flight-tested our monitoring system on board the drone which covered an area of up to 28 hectares in 40 minutes, flying at an altitude of 10 meters. And it did not miss a single weed!” Skoltech assistant professor and project supervisor Andrey Somov comments.
“Our system displays a multifold increase in localization efficiency, even though it processes 4K images at a modest speed of 0.7 fps,” Andrey adds.
The new approach holds great promise for farming: it could be used to monitor other crops, identify various vegetative indicators, assess plant health and detect plant diseases by applying multispectral imagery.
#
Original Article: Artificial Intelligence and drones will help pin down Sosnovsky’s hogweed
More from: Skolkovo Institute of Science and Technology
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Monitoring system for agricultural applications
- Conservation helps farms survive, and thrive, in drought
Climate change-induced drought poses global challenges for farmers, impacting biodiversity, crop quality, livestock health, soil degradation, and economic stability.
- Advancing Agriculture: Research Driving Sustainability in Pennsylvania
Agriculture Secretary Russell Redding visited Stroud Water Research Center in Avondale, Chester County, to observe research on farming practices improving water quality and soil health. Redding, along ...
- Engineers develop innovative battery technology that could change the future of remote devices: 'An integrated device that could harvest ambient thermal energy'
With simple increases and decreases in temperature, the new battery can generate enough charge for practical applications in many industries. Engineers develop innovative battery technology that could ...
- System controls ’hoppers on pasture
WINNIPEG — Grasshoppers, as their name suggests, hop from place to place in grassy fields. By taking advantage of that natural behaviour, University of ...
- Ag Agency receives record demand for maple grants
Maple is critical to Vermont and these grants will make it more affordable for producers in our state,” said Governor Phil Scott. “Making long term investments like this will allow maple producers to ...
Go deeper with Google Headlines on:
Monitoring system for agricultural applications
[google_news title=”” keyword=”monitoring system for agricultural applications” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
Nano factory
- The best sales to shop this weekend: Baby Foot, Athleta, Bose and more
This weekend, you’ll find a deal on an Eddie Bauer camping tent, a discounted travel steamer and savings on Bose QuietComfort Ultra Headphones. All that and more below.
- Listen To The Magico M7 In London And Hear How Great Speakers Sound
The Magico M7 are four-way, six-driver floorstanding loudspeakers that use the latest Magico drive-unit technology. Be prepared to dig deep with a pair costing $375,000.
- How a Tata Nano came into our lives in 2014: Long-term ownership review
BHPian cheeku recently shared this with other enthusiasts.This review is of our *now-sold* Tata Nano 2013 LX - nicknamed Mooshak since this was one of the first cars that I had learnt driving in and I ...
- Best Monitors for Graphic Design in 2024
The ViewSonic VP2756-4K brings sharp details through UHD resolution on a 27-inch screen. It uses an IPS panel that comes with ultra-thin bezels for an immersive view and is ideal for color grading or ...
- 700 HP Chevy Silverado Fox Factory Wants To Blow Away The F-150 Raptor R
Apart from an extensive list of mechanical upgrades, Fox Factory has also made the interior of the Silverado that little more special ...
Go deeper with Google Headlines on:
Nano factory
[google_news title=”” keyword=”nano factory” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]