scholarly journals Computer Vision with Deep Learning for Plant Phenotyping in Agriculture: A Survey

2020 ◽  
Author(s):  
Vineeth N Balasubramanian ◽  
Wei Guo ◽  
Akshay L Chandra ◽  
Sai Vikas Desai
Keyword(s):  
Deep Learning ◽  
Precision Agriculture ◽  
State Of The Art ◽  
Crop Management ◽  
Plant Phenotyping ◽  
Crop Monitoring ◽  
The World ◽  
Management Techniques ◽  
Art Research ◽  
Increase Crop Yield

In light of growing challenges in agriculture with ever growing food demand across the world, efficient crop management techniques are necessary to increase crop yield. Precision agriculture techniques allow the stakeholders to make effective and customized crop management decisions based on data gathered from monitoring crop environments. Plant phenotyping techniques play a major role in accurate crop monitoring. Advancements in deep learning have made previously difficult phenotyping tasks possible. This survey aims to introduce the reader to the state of the art research in deep plant phenotyping.

scholarly journals Applications of UAV Thermal Imagery in Precision Agriculture: State of the Art and Future Research Outlook

2020 ◽  
Vol 12 (9) ◽  
pp. 1491 ◽  
Author(s):  
Gaetano Messina ◽  
Giuseppe Modica
Keyword(s):  
Precision Agriculture ◽  
State Of The Art ◽  
Plant Stress ◽  
Stress Conditions ◽  
Plant Diseases ◽  
Basic Knowledge ◽  
Plant Phenotyping ◽  
Future Research ◽  
Thermal Data ◽  
Low Altitude

Low-altitude remote sensing (RS) using unmanned aerial vehicles (UAVs) is a powerful tool in precision agriculture (PA). In that context, thermal RS has many potential uses. The surface temperature of plants changes rapidly under stress conditions, which makes thermal RS a useful tool for real-time detection of plant stress conditions. Current applications of UAV thermal RS include monitoring plant water stress, detecting plant diseases, assessing crop yield estimation, and plant phenotyping. However, the correct use and interpretation of thermal data are based on basic knowledge of the nature of thermal radiation. Therefore, aspects that are related to calibration and ground data collection, in which the use of reference panels is highly recommended, as well as data processing, must be carefully considered. This paper aims to review the state of the art of UAV thermal RS in agriculture, outlining an overview of the latest applications and providing a future research outlook.

scholarly journals CropDeep: The Crop Vision Dataset for Deep-Learning-Based Classification and Detection in Precision Agriculture

Sensors ◽  
2019 ◽  
Vol 19 (5) ◽  
pp. 1058 ◽  
Author(s):  
Yang-Yang Zheng ◽  
Jian-Lei Kong ◽  
Xue-Bo Jin ◽  
Xiao-Yi Wang ◽  
Min Zuo
Keyword(s):  
Deep Learning ◽  
Precision Agriculture ◽  
Production Efficiency ◽  
State Of The Art ◽  
Detection Accuracy ◽  
Similar Species ◽  
Learning Technology ◽  
Well Performance ◽  
Species Classification ◽  
Domain Specific

Intelligence has been considered as the major challenge in promoting economic potential and production efficiency of precision agriculture. In order to apply advanced deep-learning technology to complete various agricultural tasks in online and offline ways, a large number of crop vision datasets with domain-specific annotation are urgently needed. To encourage further progress in challenging realistic agricultural conditions, we present the CropDeep species classification and detection dataset, consisting of 31,147 images with over 49,000 annotated instances from 31 different classes. In contrast to existing vision datasets, images were collected with different cameras and equipment in greenhouses, captured in a wide variety of situations. It features visually similar species and periodic changes with more representative annotations, which have supported a stronger benchmark for deep-learning-based classification and detection. To further verify the application prospect, we provide extensive baseline experiments using state-of-the-art deep-learning classification and detection models. Results show that current deep-learning-based methods achieve well performance in classification accuracy over 99%. While current deep-learning methods achieve only 92% detection accuracy, illustrating the difficulty of the dataset and improvement room of state-of-the-art deep-learning models when applied to crops production and management. Specifically, we suggest that the YOLOv3 network has good potential application in agricultural detection tasks.

scholarly journals Deep Machine Learning provides state-of-the-art performance in image-based plant phenotyping

2016 ◽  
Author(s):  
Michael P. Pound ◽  
Alexandra J. Burgess ◽  
Michael H. Wilson ◽  
Jonathan A. Atkinson ◽  
Marcus Griffiths ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Data Analysis ◽  
Paradigm Shift ◽  
State Of The Art ◽  
Plant Phenotyping ◽  
Learning Approaches ◽  
Challenging Problem ◽  
Feature Identification ◽  
Art Performance

AbstractDeep learning is an emerging field that promises unparalleled results on many data analysis problems. We show the success offered by such techniques when applied to the challenging problem of image-based plant phenotyping, and demonstrate state-of-the-art results for root and shoot feature identification and localisation. We predict a paradigm shift in image-based phenotyping thanks to deep learning approaches.

scholarly journals Image-Based Plant Disease Identification by Deep Learning Meta-Architectures

Plants ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1451
Author(s):  
Muhammad Hammad Saleem ◽  
Sapna Khanchi ◽  
Johan Potgieter ◽  
Khalid Mahmood Arif
Keyword(s):  
Deep Learning ◽  
Plant Disease ◽  
State Of The Art ◽  
Mean Average Precision ◽  
Single Shot ◽  
Average Precision ◽  
Crop Monitoring ◽  
Convolutional Networks ◽  
Fully Convolutional Networks ◽  
Agricultural Applications

The identification of plant disease is an imperative part of crop monitoring systems. Computer vision and deep learning (DL) techniques have been proven to be state-of-the-art to address various agricultural problems. This research performed the complex tasks of localization and classification of the disease in plant leaves. In this regard, three DL meta-architectures including the Single Shot MultiBox Detector (SSD), Faster Region-based Convolutional Neural Network (RCNN), and Region-based Fully Convolutional Networks (RFCN) were applied by using the TensorFlow object detection framework. All the DL models were trained/tested on a controlled environment dataset to recognize the disease in plant species. Moreover, an improvement in the mean average precision of the best-obtained deep learning architecture was attempted through different state-of-the-art deep learning optimizers. The SSD model trained with an Adam optimizer exhibited the highest mean average precision (mAP) of 73.07%. The successful identification of 26 different types of defected and 12 types of healthy leaves in a single framework proved the novelty of the work. In the future, the proposed detection methodology can also be adopted for other agricultural applications. Moreover, the generated weights can be reused for future real-time detection of plant disease in a controlled/uncontrolled environment.

scholarly journals Improving Coronavirus (COVID-19) Diagnosis using Deep Transfer Learning

2020 ◽  
Author(s):  
Arshia Rehman ◽  
Saeeda Naz ◽  
Ahmed Khan ◽  
Ahmad Zaib ◽  
Imran Razzak
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Bacterial Pneumonia ◽  
State Of The Art ◽  
High Accuracy ◽  
X Rays ◽  
Early Screening ◽  
X Ray ◽  
Learning Techniques ◽  
The World

AbstractBackgroundCoronavirus disease (COVID-19) is an infectious disease caused by a new virus. Exponential growth is not only threatening lives, but also impacting businesses and disrupting travel around the world.AimThe aim of this work is to develop an efficient diagnosis of COVID-19 disease by differentiating it from viral pneumonia, bacterial pneumonia and healthy cases using deep learning techniques.MethodIn this work, we have used pre-trained knowledge to improve the diagnostic performance using transfer learning techniques and compared the performance different CNN architectures.ResultsEvaluation results using K-fold (10) showed that we have achieved state of the art performance with overall accuracy of 98.75% on the perspective of CT and X-ray cases as a whole.ConclusionQuantitative evaluation showed high accuracy for automatic diagnosis of COVID-19. Pre-trained deep learning models develop in this study could be used early screening of coronavirus, however it calls for extensive need to CT or X-rays dataset to develop a reliable application.

scholarly journals Ideal oil and protein crops – what are users ideotypes, from the farmer to the consumer?

OCL ◽  
2018 ◽  
Vol 25 (6) ◽  
pp. D605 ◽  
Author(s):  
Perrine Tonin ◽  
Nathalie Gosselet ◽  
Emélie Halle ◽  
Marjorie Henrion
Keyword(s):  
Plant Breeding ◽  
Food Industry ◽  
Western Europe ◽  
Crop Management ◽  
Point Of View ◽  
The World ◽  
New Varieties ◽  
Management Techniques ◽  
Future Demands ◽  
The Ideal

Oil & protein ideotypes might be “ideal” in terms of agronomy, they cannot be grown if they do not meet a demand. And while plant breeding takes years to develop new varieties, consumers can change their habits very quickly. Understand the “ideal” crops from the downstream point of view is therefore of paramount importance for R&D. In this review, we look at the current and what may be the future demands for the oil and protein crops. Because of diversity of products and consumers around the world, we chose to focus on French and Western Europe productions and markets: 1) consumers are in a quest for quality, traceability and sustainability (economic, social and environmental) with specific focus on GMO-free and organic demands. Some go vegan and more and more people switch from animal to vegetal protein intakes. And they want to rethink the agriculture model. 2) The food industry must adapt to all these demands while develop solutions for technological obstacles and remain cost-competitive. 3) The farmer needs crop profitability that relies on high and steady yields, eco-friendly and cost-competitive crop management techniques and decent price.

scholarly journals Machine and Deep Learning towards COVID-19 Diagnosis and Treatment: Survey, Challenges, and Future Directions

2021 ◽  
Vol 18 (3) ◽  
pp. 1117
Author(s):  
Tarik Alafif ◽  
Abdul Muneeim Tehame ◽  
Saleh Bajaba ◽  
Ahmed Barnawi ◽  
Saad Zia
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Deep Learning ◽  
State Of The Art ◽  
Diagnosis And Treatment ◽  
Future Directions ◽  
Health Community ◽  
The World ◽  
The Status ◽  
And Performance

With many successful stories, machine learning (ML) and deep learning (DL) have been widely used in our everyday lives in a number of ways. They have also been instrumental in tackling the outbreak of Coronavirus (COVID-19), which has been happening around the world. The SARS-CoV-2 virus-induced COVID-19 epidemic has spread rapidly across the world, leading to international outbreaks. The COVID-19 fight to curb the spread of the disease involves most states, companies, and scientific research institutions. In this research, we look at the Artificial Intelligence (AI)-based ML and DL methods for COVID-19 diagnosis and treatment. Furthermore, in the battle against COVID-19, we summarize the AI-based ML and DL methods and the available datasets, tools, and performance. This survey offers a detailed overview of the existing state-of-the-art methodologies for ML and DL researchers and the wider health community with descriptions of how ML and DL and data can improve the status of COVID-19, and more studies in order to avoid the outbreak of COVID-19. Details of challenges and future directions are also provided.

scholarly journals A novel intervention for domestic violence perception

2020 ◽  
Author(s):  
Tanmay Debnath
Keyword(s):  
Domestic Violence ◽  
Deep Learning ◽  
Frequency Analysis ◽  
State Of The Art ◽  
Control Panel ◽  
Art Interpretation ◽  
Intervention Method ◽  
The World ◽  
Software Modules ◽  
Schematic Form

This paper poses a concept for the modulation of a novel intervention method that might potentially address the problem of domestic violence all around the world. This paper postulates the technical version of the module device and would adhere to the state-of-the-art interpretation of the technology stacked. Using audio perceptive software modules and scientific calculations related to the extraction of various features, including MFCCs and frequency analysis, a deep learning interpretation has been devised out and would be put into effect soon. The device is theorized to function in all environment scenarios, provided a threshold barrier that might be solved using manipulation in the control panel of the device. This paper has been framed in order where: (1) Design Workflow: A discussion has been provided regarding the designing of the device and the workflow. (2) Modules: a description of all the software modules used to build the prototype. (3) Components: Description of all the hardware modules used in the system. (4) System Workflow: Description of the physical model and visualization of the total schematic form of the model and its underlying connections.

scholarly journals The Nanosized Dye Adsorbents for Water Treatment

Nanomaterials ◽  
2020 ◽  
Vol 10 (2) ◽  
pp. 295 ◽  
Author(s):  
Shahin Homaeigohar
Keyword(s):  
Water Treatment ◽  
Energy Efficient ◽  
State Of The Art ◽  
Current Status ◽  
Clean Water ◽  
Structural Dimensionality ◽  
The World ◽  
Art Research ◽  
Living Creature ◽  
Vital Element

Clean water is a vital element for survival of any living creature and, thus, crucially important to achieve largely and economically for any nation worldwide. However, the astonishingly fast trend of industrialization and population growth and the arisen extensive water pollutions have challenged access to clean water across the world. In this regard, 1.6 million tons of dyes are annually consumed. Thereof, 10%–15% are wasted during use. To decolorize water streams, there is an urgent need for the advanced remediation approaches involving utilization of novel materials and technologies, which are cost and energy efficient. Nanomaterials, with their outstanding physicochemical properties, can potentially resolve the challenge of need to water treatment in a less energy demanding manner. In this review, a variety of the most recent (from 2015 onwards) opportunities arisen from nanomaterials in different dimensionalities, performances, and compositions for water decolorization is introduced and discussed. The state-of-the-art research studies are presented in a classified manner, particularly based on structural dimensionality, to better illustrate the current status of adsorption-based water decolorization using nanomaterials. Considering the introduction of many newly developed nano-adsorbents and their classification based on the dimensionality factor, which has never been employed for this sake in the related literature, a comprehensive review will be presented.

Sign in / Sign up

Export Citation Format

Share Document