(Press-News.org)
Effective weed control is crucial in agriculture to ensure high crop productivity. It entails the careful separation of weeds from crops before herbicides are sprayed in the fields. In simple terms, the goal of weed control is to remove the weeds while ensuring that the crop are not harmed. Traditional weed control methods have several drawbacks, such as crop contamination, herbicide waste, and poor accuracy. Therefore, it is essential to develop methods that can precisely locate and identify the boundary between a crop and weed and implement better weed control.
Farming robots programmed with ‘semantic segmentation’, a deep learning algorithm that accurately identifies different plants from captured images, may offer a solution to this problem. These robots can automatically distinguish weeds from crops and increase the efficiency of spraying herbicides. However, as the camera captures images of the plants, vibration of farming robots, crops and/or weeds may create a ‘motion blur’.
In a new study, a research team led by Professor Kang Ryoung Park from Dongguk University, Korea, has proposed a method that restores motion-blurred images and improves crop and weed segmentation. This is the first study that considers motion blur for crop-weed segmentation. Findings of the study were published in Plant Phenomics on February 20, 2023.
Sharing the motivation behind their study, Prof. Park states, “Motion blur severely degrades the quality of the captured crop and weed images, reducing the accuracy of high-level vision tasks. This study proposes a method that restores the motion-blurred images to perform crop and weed segmentation, making this the first study on crop and weed segmentation considering motion blur.”
The team proposed the use of “wide receptive field attention network” (WRA-Net), a deep learning model to restore motion-blurred images and improve image quality for further processing. Post-image restoration, U-Net, a semantic segmentation technology, was used to segregate crops and weeds. WRA-Net consists of an encoder, that extracts useful features from the blurred image and sends them to a decoder, that then upgrades the image. The encoder’s primary function is to provide the decoder with enriched image features to refine and improve the image quality. For effective restoration, the proposed method divides the input image into patches instead of using the entire image at once.
The group tested the WRA-Net method with three publicly available databases: BoniRob, crop/weed field image dataset (CWFID), and rice seedling and weed datasets. They also evaluated the restoration efficiency to check for similarities between the restored and original images. The semantic segmentation performance was measured using mIOU (mean intersection over union), a parameter used to assess deep learning algorithms.
Across all measured parameters, WRA-Net outperformed the other databases. It effectively restored motion-blurred images and turned out to be the best weed segmentation model. This method was also more efficient than the state-of-the-art methods in terms of segmentation accuracy. The mIOUs of test images restored by WRA-Net were 0.7741, 0.7444, and 0.7749, in CWFID, BoniRob, and rice seedling and weed database, respectively. Furthermore, WRA-Net performed well even in an embedded system (a combination of a computer processor, computer memory, and input/output peripheral devices) with limited computing resources.
So, what’s next for the team? “In future studies, we would research about the method using preprocessing to reduce the errors caused by high similarity of crop and weed and thin area of object. In addition, we would research about the feature fusion that can obtain high semantic segmentation results directly from the motion-blurred image without performing two steps of restoration and semantic segmentation,” adds Prof. Park.
Food security is gradually becoming difficult to achieve and is affected by lack of manpower and weather atrocities. This method can help overcome these issues and increase crop productivity.
Here’s wishing the authors good luck for leading us into an agricultural revolution!
###
Reference
Authors
Chaeyeong Yun, Yu Hwan Kim, Sung Jae Lee, Su Jin Im, and Kang Ryoung Park*
Affiliation
Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, Republic of Korea
END
Researchers have a new scientific tool called Polybot, combining the power of artificial intelligence with robotics. Potential applications include speeding up the discovery of wearable biomedical devices, materials for better batteries and more.
Today’s wearable technologies like smart glasses and watches are just the start. The next generation of flexible electronics will be more efficient and sustainable, better able to monitor our health and treat certain diseases, and much more. They will be composed of electronic polymer materials — a soft pliable substance that can conduct electricity.
“Just imagine the next generation of polymer ...
New York (April 25, 2022) — The American Geriatrics Society (AGS) today announced Shelley R. McDonald, DO, PhD, MCG, as 2023 Clinician of the Year. Dr. McDonald, who is an Associate Professor of Internal Medicine at Duke University School of Medicine, will be honored at the 2023 AGS Annual Scientific Meeting (#AGS23) being held in Long Beach, CA, from May 4-6 (preconference day is May 3).
“Our 2023 Clinician of the year, Dr. Shelley McDonald, is a national champion for improved perioperative care of older adults undergoing surgery,” said ...
NEW YORK, April 25, 2023 ‒ Aetion®, the global leader in real-world evidence (RWE) technology and analytics, is pleased to announce the culmination of the RCT-DUPLICATE demonstration project, with complete findings published today in The Journal of the American Medical Association (JAMA). This three-year initiative tested whether researchers asking clinical questions in real-world data (RWD) — data from patients’ day-to-day interactions with the healthcare system — would obtain similar results to findings from randomized clinical trials (RCTs). In cases where clinical trial designs aligned with real patient care processes, the RWE studies and RCTs came ...
Consumption of cannabis (marijuana) or derivatives during pregnancy can cause respiratory problems for the baby, such as impaired control of breathing and diminished sensitivity to carbon dioxide, both of which favor sudden infant death syndrome. These are the main findings of a study conducted in Brazil and reported in an article published in the British Journal of Pharmacology.
The authors are researchers at São Paulo State University (UNESP) and the University of São Paulo (USP). They gave pregnant rats a synthetic compound (WIN 55) that acts on the brain in a similar manner to natural cannabinoids. Harmful effects occurred mainly in male pups.
“Cannabis ...
Investigators at Cedars-Sinai have created computer-generated models to bridge the gap between “test tube” data about neurons and the function of those cells in the living brain. Their study, published in the peer-reviewed journal Nature Communications, could help in the development of treatments for neurological diseases and disorders that target specific neuron types based on their roles.
“This work allows us to start looking at the brain like the complex machine that it is, rather than ...
Medical centers around the world could significantly reduce their carbon footprint and expenses by turning off MRIs and putting them in the lowest power mode instead of idling them when not in use, a new study in Radiology found.
Health care is responsible for up to 4.4% of global carbon emissions, and imaging contributes an outsized share due to its energy-intensive devices, especially MRI. A 2020 study found that three CTs and four MRIs used the same amount of energy per year as a town of 852 people, for example.
Though turning a machine off is better than idling, a substantial amount of MRI energy consumption occurs in “off” ...
CHAMPAIGN, Ill. — In a new study, scientists explored the links between three measures known to independently predict healthy aging: nutrient intake, brain structure and cognitive function. Their analysis adds to the evidence that these factors jointly contribute to brain health in older adults.
Reported in the Journal of Nutrition, the study found that blood markers of two saturated fatty acids, along with certain omega-6, -7 and -9 fatty acids, correlated with better scores on tests of memory and with larger brain structures in the frontal, ...
For the first time in the University of North Carolina at Charlotte’s nearly 80-year history, a faculty member has won a NASA Exobiology grant. Assistant Professor of Bioinformatics and Genomics Richard Allen White III will use the ultra-competitive grant in his research on microbialites, a kind of “living rock” that could hold the key to how life formed on Earth.
Microbialites form when microbial mats, living colonies of mostly bacteria, transform into stronger hard structures. White explores how viruses may have helped to kickstart the transformation (i.e., lithification) of modern microbialites, which ...
Treating opioid addiction should be much easier now than it was a few years ago, thanks to pandemic-era rule changes that aim to improve access to buprenorphine, a medicine proven to help in recovery.
But a new study shows the rate of people starting on buprenorphine remained flat from 2019 through 2022, while the percentage of patients who stayed on buprenorphine for at least six months hovered at just over 20% from 2016 through 2022.
Until more health care providers start offering buprenorphine treatment -- and to take advantage of opportunities like emergency visits and hospitalizations ...
WASHINGTON, April 25, 2023 – Tsunamis are incredibly destructive waves that can destroy coastal infrastructure and cause loss of life. Early warnings for such natural disasters are difficult because the risk of a tsunami is highly dependent on the features of the underwater earthquake that triggers it.
In Physics of Fluids, by AIP Publishing, researchers from the University of California, Los Angeles and Cardiff University in the U.K. developed an early warning system that combines state-of-the-art acoustic technology with artificial intelligence to immediately classify earthquakes and determine potential tsunami ...
