Advantage of multispectral imaging with sub-centimeter resolution in precision agriculture: generalization of training for supervised classification

2016 ◽  
Vol 18 (4) ◽  
pp. 615-634 ◽  
Author(s):  
F. Rodriguez-Moreno ◽  
J. Kren ◽  
F. Zemek ◽  
J. Novak ◽  
V. Lukas ◽  
...  
Keyword(s):  
Precision Agriculture ◽  
Supervised Classification ◽  
Multispectral Imaging

scholarly journals Active and Passive Electro-Optical Sensors for Health Assessment in Food Crops

Sensors ◽  
2020 ◽  
Vol 21 (1) ◽  
pp. 171
Author(s):  
Thomas Fahey ◽  
Hai Pham ◽  
Alessandro Gardi ◽  
Roberto Sabatini ◽  
Dario Stefanelli ◽  
...  
Keyword(s):  
Crop Yield ◽  
Optical Sensors ◽  
Precision Agriculture ◽  
Multispectral Imaging ◽  
Plant Stress ◽  
Plant Diseases ◽  
Added Value ◽  
High Rate ◽  
Future Research ◽  
Atmospheric Conditions

In agriculture, early detection of plant stresses is advantageous in preventing crop yield losses. Remote sensors are increasingly being utilized for crop health monitoring, offering non-destructive, spatialized detection and the quantification of plant diseases at various levels of measurement. Advances in sensor technologies have promoted the development of novel techniques for precision agriculture. As in situ techniques are surpassed by multispectral imaging, refinement of hyperspectral imaging and the promising emergence of light detection and ranging (LIDAR), remote sensing will define the future of biotic and abiotic plant stress detection, crop yield estimation and product quality. The added value of LIDAR-based systems stems from their greater flexibility in capturing data, high rate of data delivery and suitability for a high level of automation while overcoming the shortcomings of passive systems limited by atmospheric conditions, changes in light, viewing angle and canopy structure. In particular, a multi-sensor systems approach and associated data fusion techniques (i.e., blending LIDAR with existing electro-optical sensors) offer increased accuracy in plant disease detection by focusing on traditional optimal estimation and the adoption of artificial intelligence techniques for spatially and temporally distributed big data. When applied across different platforms (handheld, ground-based, airborne, ground/aerial robotic vehicles or satellites), these electro-optical sensors offer new avenues to predict and react to plant stress and disease. This review examines the key sensor characteristics, platform integration options and data analysis techniques recently proposed in the field of precision agriculture and highlights the key challenges and benefits of each concept towards informing future research in this very important and rapidly growing field.

scholarly journals WeedMap: A Large-Scale Semantic Weed Mapping Framework Using Aerial Multispectral Imaging and Deep Neural Network for Precision Farming

2018 ◽  
Vol 10 (9) ◽  
pp. 1423 ◽  
Author(s):  
Inkyu Sa ◽  
Marija Popović ◽  
Raghav Khanna ◽  
Zetao Chen ◽  
Philipp Lottes ◽  
...  
Keyword(s):  
Neural Network ◽  
Precision Agriculture ◽  
Large Scale ◽  
Deep Neural Network ◽  
Near Infrared ◽  
Multispectral Imaging ◽  
Precision Farming ◽  
High Fidelity ◽  
Ground Sample ◽  
Global Consistency

The ability to automatically monitor agricultural fields is an important capability in precision farming, enabling steps towards more sustainable agriculture. Precise, high-resolution monitoring is a key prerequisite for targeted intervention and the selective application of agro-chemicals. The main goal of this paper is developing a novel crop/weed segmentation and mapping framework that processes multispectral images obtained from an unmanned aerial vehicle (UAV) using a deep neural network (DNN). Most studies on crop/weed semantic segmentation only consider single images for processing and classification. Images taken by UAVs often cover only a few hundred square meters with either color only or color and near-infrared (NIR) channels. Although a map can be generated by processing single segmented images incrementally, this requires additional complex information fusion techniques which struggle to handle high fidelity maps due to their computational costs and problems in ensuring global consistency. Moreover, computing a single large and accurate vegetation map (e.g., crop/weed) using a DNN is non-trivial due to difficulties arising from: (1) limited ground sample distances (GSDs) in high-altitude datasets, (2) sacrificed resolution resulting from downsampling high-fidelity images, and (3) multispectral image alignment. To address these issues, we adopt a stand sliding window approach that operates on only small portions of multispectral orthomosaic maps (tiles), which are channel-wise aligned and calibrated radiometrically across the entire map. We define the tile size to be the same as that of the DNN input to avoid resolution loss. Compared to our baseline model (i.e., SegNet with 3 channel RGB (red, green, and blue) inputs) yielding an area under the curve (AUC) of [background=0.607, crop=0.681, weed=0.576], our proposed model with 9 input channels achieves [0.839, 0.863, 0.782]. Additionally, we provide an extensive analysis of 20 trained models, both qualitatively and quantitatively, in order to evaluate the effects of varying input channels and tunable network hyperparameters. Furthermore, we release a large sugar beet/weed aerial dataset with expertly guided annotations for further research in the fields of remote sensing, precision agriculture, and agricultural robotics.

scholarly journals A Multispectral Camera Development: From the Prototype Assembly until Its Use in a UAV System

Sensors ◽  
2020 ◽  
Vol 20 (21) ◽  
pp. 6129
Author(s):  
Alejandro Morales ◽  
Raul Guerra ◽  
Pablo Horstrand ◽  
Maria Diaz ◽  
Adan Jimenez ◽  
...  
Keyword(s):  
Precision Agriculture ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Multispectral Imaging ◽  
Ease Of Use ◽  
Oxide Semiconductor ◽  
Forensic Sciences ◽  
Capture Process ◽  
Cmos Sensor ◽  
Multispectral Camera

Multispectral imaging (MI) techniques are being used very often to identify different properties of nature in several domains, going from precision agriculture to environmental studies, not to mention quality inspection of pharmaceutical production, art restoration, biochemistry, forensic sciences or geology, just to name some. Different implementations are commercially available from the industry and yet there is quite an interest from the scientific community to spread its use to the majority of society by means of cost effectiveness and ease of use for solutions. These devices make the most sense when combined with unmanned aerial vehicles (UAVs), going a step further and alleviating repetitive routines which could be strenuous if traditional methods were adopted. In this work, a low cost and modular solution for a multispectral camera is presented, based on the use of a single panchromatic complementary metal oxide semiconductor (CMOS) sensor combined with a rotating wheel of interchangeable band pass optic filters. The system is compatible with open source hardware permitting one to capture, process, store and/or transmit data if needed. In addition, a calibration and characterization methodology has been developed for the camera, allowing not only for quantifying its performance, but also able to characterize other CMOS sensors in the market in order to select the one that best suits the budget and application. The process was experimentally validated by mounting the camera in a Dji Matrice 600 UAV to uncover vegetation indices in a reduced area of palm trees plantation. Results are presented for the normalized difference vegetation index (NDVI) showing a generated colored map with the captured information.

scholarly journals Predicting Phosphorus and Potato Yield Using Active and Passive Sensors

Agriculture ◽  
2020 ◽  
Vol 10 (11) ◽  
pp. 564
Author(s):  
Ahmed Jasim ◽  
Ahmed Zaeen ◽  
Lakesh K. Sharma ◽  
Sukhwinder K. Bali ◽  
Chunzeng Wang ◽  
...  
Keyword(s):  
Precision Agriculture ◽  
Multispectral Imaging ◽  
P Uptake ◽  
Potato Yield ◽  
Sensor Data ◽  
Poor Correlation ◽  
Linear Regression Models ◽  
Plant P Uptake ◽  
Passive Sensors ◽  
Potato Yields

Applications of remote sensing are important in improving potato production through the broader adoption of precision agriculture. This technology could be useful in decreasing the potential contamination of soil and water due to the over-fertilization of agriculture crops. The objective of this study was to assess the utility of active sensors (Crop Circle™, Holland Scientific, Inc., Lincoln, NE, USA and GreenSeeker™, Trimble Navigation Limited, Sunnyvale, CA, USA) and passive sensors (multispectral imaging with Unmanned Arial Vehicles (UAVs)) to predict total potato yield and phosphorus (P) uptake. The experimental design was a randomized complete block with four replications and six P treatments, ranging from 0 to 280 kg P ha−1, as triple superphosphate (46% P2O5). Vegetation indices (VIs) and plant pigment levels were calculated at various time points during the potato growth cycle, correlated with total potato yields and P uptake by the stepwise fitting of multiple linear regression models. Data generated by Crop Circle™ and GreenSeeker™ had a low predictive value of potato yields, especially early in the season. Crop Circle™ performed better than GreenSeeker™ in predicting plant P uptake. In contrast, the passive sensor data provided good estimates of total yields early in the season but had a poor correlation with P uptake. The combined use of active and passive sensors presents an opportunity for better P management in potatoes.

scholarly journals Processing and Use of Satellite Images in Order to Extract Useful Information in Precision Agriculture

2016 ◽  
Vol 73 (2) ◽  
pp. 238 ◽  
Author(s):  
Mihai Valentin Herbei ◽  
Cosmin Alin Popescu ◽  
Radu Bertici ◽  
Adrian Smuleac ◽  
George Popescu
Keyword(s):  
Maximum Likelihood ◽  
Precision Agriculture ◽  
Urban Areas ◽  
Supervised Classification ◽  
Satellite Images ◽  
Satellite Image ◽  
Likelihood Method ◽  
Large Area ◽  
Area Of Interest ◽  
Maximum Similarity

Image analysis methods were developed and diversified greatly in recent years due to increasing speed and accuracy in providing information regarding land cover and vegetation in urban areas. The aim of this paper is to process satellite images for monitoring agricultural areas. Satellite images used in this study are medium and high resolution images taken from QuickBird and SPOT systems. Based on these images, a supervised classification was performed of a very large area, having as result the land use classes. Supervised classification can be defined as the ability to group the pixels that compose the satellite image, digitally, in accordance with their real significance. Gaussian algorithm of maximum similarity (Maximum likelihood) was used, referred to in the specialty literature as maximum likelihood method or probabilistic classification, and based on the use of probability theory (function Gaussian) to compare the spectral values of each pixel in hand with statistical " fingerprint "of each area of interest. Practically, conditional probabilities were calculated of belonging to one class or another. The points in the middle of the group have a higher probability of belonging to the certain class, probability intervals (concentric isolines or contours of equal probability) being delimited graphically by izocontours expressing spectral variations within each set of training.

scholarly journals Recent Advances of Hyperspectral Imaging Technology and Applications in Agriculture

2020 ◽  
Vol 12 (16) ◽  
pp. 2659 ◽  
Author(s):  
Bing Lu ◽  
Phuong D. Dao ◽  
Jiangui Liu ◽  
Yuhong He ◽  
Jiali Shang
Keyword(s):  
Hyperspectral Imaging ◽  
Precision Agriculture ◽  
Multispectral Imaging ◽  
Spectral Response ◽  
Physiological Status ◽  
Advanced Technique ◽  
Imaging Technology ◽  
Hyperspectral Sensors ◽  
Recent Advances ◽  
Agricultural Applications

Remote sensing is a useful tool for monitoring spatio-temporal variations of crop morphological and physiological status and supporting practices in precision farming. In comparison with multispectral imaging, hyperspectral imaging is a more advanced technique that is capable of acquiring a detailed spectral response of target features. Due to limited accessibility outside of the scientific community, hyperspectral images have not been widely used in precision agriculture. In recent years, different mini-sized and low-cost airborne hyperspectral sensors (e.g., Headwall Micro-Hyperspec, Cubert UHD 185-Firefly) have been developed, and advanced spaceborne hyperspectral sensors have also been or will be launched (e.g., PRISMA, DESIS, EnMAP, HyspIRI). Hyperspectral imaging is becoming more widely available to agricultural applications. Meanwhile, the acquisition, processing, and analysis of hyperspectral imagery still remain a challenging research topic (e.g., large data volume, high data dimensionality, and complex information analysis). It is hence beneficial to conduct a thorough and in-depth review of the hyperspectral imaging technology (e.g., different platforms and sensors), methods available for processing and analyzing hyperspectral information, and recent advances of hyperspectral imaging in agricultural applications. Publications over the past 30 years in hyperspectral imaging technology and applications in agriculture were thus reviewed. The imaging platforms and sensors, together with analytic methods used in the literature, were discussed. Performances of hyperspectral imaging for different applications (e.g., crop biophysical and biochemical properties’ mapping, soil characteristics, and crop classification) were also evaluated. This review is intended to assist agricultural researchers and practitioners to better understand the strengths and limitations of hyperspectral imaging to agricultural applications and promote the adoption of this valuable technology. Recommendations for future hyperspectral imaging research for precision agriculture are also presented.

Multispectral Imaging to define morpho-molecular classes of human HCC

2020 ◽  
Author(s):  
T Ritz ◽  
J Baues ◽  
O Krenkel ◽  
P Schirmacher ◽  
T Longerich
Keyword(s):  
Multispectral Imaging

Environmental Benefits of Precision Agriculture Adoption

2020 ◽  
pp. 637-656 ◽  
Author(s):  
Marco Medici ◽  
Søren Marcus Pedersen ◽  
Giacomo Carli ◽  
Maria Rita Tagliaventi
Keyword(s):  
Environmental Impacts ◽  
Precision Agriculture ◽  
New Technologies ◽  
Environmental Benefits ◽  
Herbicide Application ◽  
Pesticide Application ◽  
Policy Makers ◽  
Application Rates ◽  
Biodiversity Policy ◽  
Lime Application

The purpose of this study is to analyse the environmental benefits of precision agriculture technology adoption obtained from the mitigation of negative environmental impacts of agricultural inputs in modern farming. Our literature review of the environmental benefits related to the adoption of precision agriculture solutions is aimed at raising farmers' and other stakeholders' awareness of the actual environmental impacts from this set of new technologies. Existing studies were categorised according to the environmental impacts of different agricultural activities: nitrogen application, lime application, pesticide application, manure application and herbicide application. Our findings highlighted the effects of the reduction of input application rates and the consequent impacts on climate, soil, water and biodiversity. Policy makers can benefit from the outcomes of this study developing an understanding of the environmental impact of precision agriculture in order to promote and support initiatives aimed at fostering sustainable agriculture.

Sign in / Sign up

Export Citation Format

Share Document