Crop Growth Monitoring Research Articles

Combining Spectral and Texture Features of UAS-Based Multispectral Images for Maize Leaf Area Index Estimation

The leaf area index (LAI) is of great significance for crop growth monitoring. Recently, unmanned aerial systems (UASs) have experienced rapid development and can provide critical data support for crop LAI monitoring. This study investigates the effects of combining spectral and texture features extracted from UAS multispectral imagery on maize LAI estimation. Multispectral images and in situ maize LAI were collected from test sites in Tongshan, Xuzhou, Jiangsu Province, China. The spectral and texture features of UAS multispectral remote sensing images are extracted using the vegetation indices (VIs) and the gray-level co-occurrence matrix (GLCM), respectively. Normalized texture indices (NDTIs), ratio texture indices (RTIs), and difference texture indices (DTIs) are calculated using two GLCM-based textures to express the influence of two different texture features on LAI monitoring at the same time. The remote sensing features are prescreened through correlation analysis. Different data dimensionality reduction or feature selection methods, including stepwise selection (ST), principal component analysis (PCA), and ST combined with PCA (ST_PCA), are coupled with support vector regression (SVR), random forest (RF), and multiple linear regression (MLR) to build the maize LAI estimation models. The results reveal that ST_PCA coupled with SVR has better performance, in terms of the VIs + DTIs (R2 = 0.876, RMSE = 0.239) and VIs + NDTIs (R2 = 0.877, RMSE = 0.236). This study introduces the potential of different texture indices for maize LAI monitoring and demonstrates the promising solution of using ST_PCA to realize the combining of spectral and texture features for improving the estimation accuracy of maize LAI.

Hyperspectral estimation of canopy chlorophyll of winter wheat by using the optimized vegetation indices

The vegetation indices (VIs) derived from the different band combinations can be used for monitoring crop quality traits. We conducted field experiments over two years time to investigate critical growth stages across four varieties and by using different nitrogen (N) application rates. In order to explore and evaluate the performance of different VIs on estimation of the canopy chlorophyll content (CCC) of winter wheat, the published and modified indices were optimized by using the random band combination through original spectrum (OS) and first-order differential (FD) treatment. The results showed that the first derivative processing improved the correlation between the red edge band and winter wheat CCC. The three-band VI can break the restriction of the number of bands on the extraction of target information, relieved the saturation problem of the dual-band VI, and improved the monitoring accuracy of winter wheat CCC. The index 2 × R1-R2-R3 was found to be the best VI for assessing the CCC of winter wheat based on the original and first-order differential spectrum (calibration R2 > 0.733), R2 and RMSE of validation set were 0.688, 0.755 and 1.515, 1.336, respectively. In addition, the index expression formula R1/(R2 × R3) was recommended as a favorable choice for monitoring the agronomic traits of crop. Moreover, the VI is suggested to use at the red edge position band to monitor crop growth indicators. In conclusion, the use of VI can better monitor winter wheat CCC which could provide a theoretical basis for precision agriculture.

Applications of nanostructured materials in agriculture: A review

The sustainability of the agricultural system has faced a constant stream of unforeseen and unavoidable difficulties over the last ten years. Due to certain properties of nanoparticles (NPs), such as absorption effectiveness, form flexibility, responsiveness, the durability of agrochemicals, superior biocompatibility, concentrated distribution size, and large surface area, nanotechnology has provided a varied variety of roles in crop production. Because NPs directly affect how efficiently inputs are managed, using nanosensors makes it simple to tackle problems in modern agricultural fields. NPs play a variety of roles, including those of fertilizers, insecticides, herbicides, and magic bullets that target particular cell components in plants. Numerous scientific studies have clarified that nanostructured materials affect seed germination, mineral nutrition, and the environment. In this chapter, we discussed how NPs are used to detect agricultural pathogens, monitor crop growth, and reduce environmental pressures to meet the growing demand for crop management that is sustainable.

Semantic Segmentation of Plant Leaves Based on Generative Adversarial Network and Attention Mechanism

Due to the rapid growth of the population, the pressure on food is increasing and the demand for higher crop yields is rising. It is crucial to periodically monitor plant phenotypic traits, and deep learning has a good effect on image recognition and segmentation. This paper proposes a method based on generative adversarial network and attention mechanism to improve the accuracy of semantic segmentation of plant leaves. First, the data set is standardized and divided into a training set and test set. The generator that produces the confrontation network uses Segnet as the backbone network and adds an attention mechanism to extract the phenotypic characteristics of plants. The discriminator utilizes a dual-input fully connected layer for true and false estimate. The experimental results show that compared with the original Segnet segmentation network, the proposed strategy improves the precision of pixel recognition PA. Also, the suggested technique has a high level of robustness and feature extraction precision. In addition to providing technical assistance for future crop cultivation and breeding, monitoring crop growth, ensuring yields as well as solving the food shortage problem.

Intelligent Agriculture Technology Based on Internet of Things

Although the application of agricultural product traceability technology is a key point to realize Modern Agricultural IoT, it has still encountered various food safety problems. For example, immature environmental monitoring technology of agricultural products, weak product traceability and imperfect product monitoring equipment. For this reason, this paper studies and compares several emerging technologies of the things Internet, then it analyzes the functional diversity and practicability of the Modern Agricultural IoT. It builds the experimental environment based on the agricultural product traceability technology, so as to realize the monitoring of crop growth environment and traceability. The result plays a positive role in popularizing the traceability technology of agricultural products and has a certain impact on the development of intelligent agriculture. It has designed and developed a set of crop growth monitoring terminal equipment through experimental debugging. Then it could obtain temperature and humidity, illumination, CO2 concentration, soil data, and other crop growth environment parameters in real time. The relevant data has provided strong support for the traceability model to realize the multi-point monitoring, intelligent control, and automatic operation of crop growing environment. Then it can be sorted and analyzed through the application layer. This system can promote the intelligent processing, improve the utilization efficiency of agricultural resources, promote the development of modern agriculture, save agricultural production costs, and increase the production and marketing. It is an innovative application of the Internet of things technology applied to agricultural production.

Design and Testing of Vehicle-Mounted Crop Growth Monitoring System

Design and Testing of Vehicle-Mounted Crop Growth Monitoring System

Combining Sentinel-1 and -3 Imagery for Retrievals of Regional Multitemporal Biophysical Parameters Under a Deep Learning Framework

Regions with excessive cloud cover lead to limited feasibility of applying optical images to monitor crop growth. In this study, we built an upsampling moving window network for regional crop growth monitoring (UMRCGM) model to estimate the two key biophysical parameters (BPs), leaf area index (LAI) and canopy chlorophyll content (CCC) during the main growth period of winter wheat by using Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-3 optical images. Sentinel-1 imagery is unaffected by cloudy weather and Sentinel-3 imagery has a wide width and short revisit period, the organic combination of the two will greatly improve the ability to monitor crop growth at a regional scale. The impact of two different types of SAR information (intensity and polarization) on the estimation of the two BPs was further analyzed. The UMRCGM model optimized the correspondence between inputs and outputs, it had more accurate LAI and CCC estimates compared with the three classical machine learning models, and had the highest accuracy at the green-up stage of winter wheat, followed by the jointing stage and the heading-filling stage, and the lowest accuracy was found at the milk maturity stage. The estimation accuracies of CCC were slightly higher than that of LAI for the first three growth stages of winter wheat, while lower than that of LAI for the milk maturity stage. This study proposes a new method for regional BPs (especially for CCC) estimation by combining SAR and optical imagery with large differences in spatial resolution under a deep learning framework.

Smart Crop Growth Monitoring Based on System Adaptivity and Edge AI

Smart Crop Growth Monitoring Based on System Adaptivity and Edge AI

Variable-Rate Fertigation Control for Hydroponics Using an On-The-Go Transpiration Monitoring System

HighlightsAn on-the-go monitoring system was developed for assessing spatial and temporal variations in crop growth.The system was used to realize real-time transpiration estimation for lettuce growth.A variable-rate fertigation system was developed based on on-the-go transpiration monitoring.The variable-rate fertigation system was validated in controlled-environment cultivation of hydroponic lettuce.Abstract. Variable-rate fertigation, as a key component of hydroponic cultivation, ensures the sustainable use of water. However, this fertigation method is challenging to implement because of the difficulty associated with assessing the water needs of plants, which vary with plant growth stage and environmental conditions. In this study, an on-the-go crop growth monitoring system was developed to measure the canopy cover of lettuce plants on a daily basis. The canopy cover during the vegetative growth period could be estimated with an accuracy of 98.5% ±1.7% compared to manual segmentation. A modified Penman-Monteith equation was used to predict the transpiration rate of the lettuce plants. In the first cultivation test, the transpiration rate model exhibited a highly linear relationship with a slope of 0.91, coefficient of determination of >0.9, and standard error of regression of <0.51, compared to the directly measured transpiration rates. In the second cultivation test, an automated system that could variably control the fertigation volume was incorporated with the on-the-go system for monitoring the lettuce transpiration in real time. The proposed system could realize on-the-go mapping of the spatial distribution of the canopy cover of the growing lettuce plants, and the variable fertigation responded to the daily water consumption of the plants with an error of only 7.3%. Moreover, the stable canopy cover growth indicated the higher efficiency of variable fertigation compared to timer-based fertigation systems. The proposed variable-rate fertigation system is a promising and practical approach to implement hydroponics with reduced water and energy consumption. Keywords: Canopy cover, Hydroponic, On-the-go monitoring, Transpiration, Variable fertigation.

Tracking crop phenology in a highly dynamic landscape with knowledge-based Landsat–MODIS data fusion

Earth observation image data are regularly used to capture surface conditions over large areas, but there is a trade-off between high (or low) spatial and low (or high) temporal resolution. The Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM) overcomes this trade-off by fusing high spatial and temporal resolution multisource image data. However, ESTARFM requires additional modifications in order to provide reliable estimates of surface conditions showing large spectral differences in highly dynamic and fragmented agricultural systems. We modified ESTARFM by taking a knowledge-based approach to track maize and rice phenology in a highly dynamic and fragmented agricultural landscape in Ethiopia in 2019. The two major improvements included: (i) Selection of Landsat-MODIS imageries based on crop sowing and harvesting information and (ii) generation and use of a land cover map to select similar pixels. We assessed model performance with the enhanced vegetation index (EVI) derived from independent Landsat image data and in-situ leaf area index (LAI) data. The improved ESTARFM workflow resulted in reliable Landsat-MODIS prediction (R2 = 0.67, RMSE = 0.07) compared to the standard ESTARFM workflow (R2 = 0.54 RMSE = 0.01) during the rapid growth stage. Our modifications outperformed the standard implementation of ESTARFM according to LAI magnitude (R2 = 0.73–0.84 versus R2 = 0.58–0.64) and phenological timing (RMSE = 8 days verses RMSE = 12 days). Our modified application of ESTARFM serves as a basis for monitoring crop growth and development in highly dynamic and fragmented agricultural systems.

Unmanned Aerial Vehicles (UAV) in Precision Agriculture: Applications and Challenges

Agriculture is the primary source of income in developing countries like India. Agriculture accounts for 17 percent of India’s total GDP, with almost 60 percent of the people directly or indirectly employed. While researchers and planters focus on a variety of elements to boost productivity, crop loss due to disease is one of the most serious issues they confront. Crop growth monitoring and early detection of pest infestations are still a problem. With the expansion of cultivation to wider fields, manual intervention to monitor and diagnose insect and pest infestations is becoming increasingly difficult. Failure to apply on time fertilizers and pesticides results in more crop loss and so lower output. Farmers are putting in greater effort to conserve crops, but they are failing most of the time because they are unable to adequately monitor the crops when they are infected by pests and insects. Pest infestation is also difficult to predict because it is not evenly distributed. In the recent past, modern equipment, tools, and approaches have been used to replace manual involvement. Unmanned aerial vehicles serve a critical role in crop disease surveillance and early detection in this setting. This research attempts to give a review of the most successful techniques to have precision-based crop monitoring and pest management in agriculture fields utilizing unmanned aerial vehicles (UAVs) or unmanned aircraft. The researchers’ reports on the various types of UAVs and their applications to early detection of agricultural diseases are rigorously assessed and compared. This paper also discusses the deployment of aerial, satellite, and other remote sensing technologies for disease detection, as well as their Quality of Service (QoS).

Estimation of Cotton Leaf Area Index (LAI) Based on Spectral Transformation and Vegetation Index

Unmanned aerial vehicles (UAV) has been increasingly applied to crop growth monitoring due to their advantages, such as their rapid and repetitive capture ability, high resolution, and low cost. LAI is an important parameter for evaluating crop canopy structure and growth without damage. Accurate monitoring of cotton LAI has guiding significance for nutritional diagnosis and the accurate fertilization of cotton. This study aimed to obtain hyperspectral images of the cotton canopy using a UAV carrying a hyperspectral sensor and to extract effective information to achieve cotton LAI monitoring. In this study, cotton field experiments with different nitrogen application levels and canopy spectral images of cotton at different growth stages were obtained using a UAV carrying hyperspectral sensors. Hyperspectral reflectance can directly reflect the characteristics of vegetation, and vegetation indices (VIs) can quantitatively describe the growth status of plants through the difference between vegetation in different band ranges and soil backgrounds. In this study, canopy spectral reflectance was extracted in order to reduce noise interference, separate overlapping samples, and highlight spectral features to perform spectral transformation; characteristic band screening was carried out; and VIs were constructed using a correlation coefficient matrix. Combined with canopy spectral reflectance and VIs, multiple stepwise regression (MSR) and extreme learning machine (ELM) were used to construct an LAI monitoring model of cotton during the whole growth period. The results show that, after spectral noise reduction, the bands screened by the successive projections algorithm (SPA) are too concentrated, while the sensitive bands screened by the shuffled frog leaping algorithm (SFLA) are evenly distributed. Secondly, the calculation of VIs after spectral noise reduction can improve the correlation between vegetation indices and LAI. The DVI (540,525) correlation was the largest after standard normal variable transformation (SNV) pretreatment, with a correlation coefficient of −0.7591. Thirdly, cotton LAI monitoring can be realized only based on spectral reflectance or VIs, and the ELM model constructed by calculating vegetation indices after SNV transformation had the best effect, with verification set R2 = 0.7408, RMSE = 1.5231, and rRMSE = 24.33%, Lastly, the ELM model based on SNV-SFLA-SNV-VIs had the best performance, with validation set R2 = 0.9066, RMSE = 0.9590, and rRMSE = 15.72%. The study results show that the UAV equipped with a hyperspectral sensor has broad prospects in the detection of crop growth index, and it can provide a theoretical basis for precise cotton field management and variable fertilization.

Study on the Optimization of Hyperspectral Characteristic Bands Combined with Monitoring and Visualization of Pepper Leaf SPAD Value.

Chlorophyll content is an important indicator of plant photosynthesis, which directly affects the growth and yield of crops. Using hyperspectral imaging technology to quickly and non-destructively estimate the soil plant analysis development (SPAD) value of pepper leaf and its distribution inversion is of great significance for agricultural monitoring and precise fertilization during pepper growth. In this study, 150 samples of pepper leaves with different leaf positions were selected, and the hyperspectral image data and SPAD value were collected for the sampled leaves. The correlation coefficient, stability competitive adaptive reweighted sampling (sCARS), and iteratively retaining informative variables (IRIV) methods were used to screen characteristic bands. These were combined with partial least-squares regression (PLSR), extreme gradient boosting (XGBoost), random forest regression (RFR), and gradient boosting decision tree (GBDT) to build regression models. The developed model was then used to build the inversion map of pepper leaf chlorophyll distribution. The research results show that: (1) The IRIV-XGBoost model demonstrates the most comprehensive performance in the modeling and inversion stages, and its , , and are 0.81, 2.76, and 2.30, respectively; (2) The IRIV-XGBoost model was used to calculate the SPAD value of each pixel of pepper leaves, and to subsequently invert the chlorophyll distribution map of pepper leaves at different leaf positions, which can provide support for the intuitive monitoring of crop growth and lay the foundation for the development of hyperspectral field dynamic monitoring sensors.

A Random Forest Algorithm for Retrieving Canopy Chlorophyll Content of Wheat and Soybean Trained with PROSAIL Simulations Using Adjusted Average Leaf Angle

Canopy chlorophyll content (CCC) is an important indicator for crop-growth monitoring and crop productivity estimation. The hybrid method, involving the PROSAIL radiative transfer model and machine learning algorithms, has been widely applied for crop CCC retrieval. However, PROSAIL’s homogeneous canopy hypothesis limits the ability to use the PROSAIL-based CCC estimation across different crops with a row structure. In addition to leaf area index (LAI), average leaf angle (ALA) is the most important canopy structure factor in the PROSAIL model. Under the same LAI, adjustment of the ALA can make a PROSAIL simulation obtain the same canopy gap as the heterogeneous canopy at a specific observation angle. Therefore, parameterization of an adjusted ALA (ALAadj) is an optimal choice to make the PROSAIL model suitable for specific row-planted crops. This paper attempted to improve PROSAIL-based CCC retrieval for different crops, using a random forest algorithm, by introducing the prior knowledge of crop-specific ALAadj. Based on the field reflectance spectrum at nadir, leaf area index, and leaf chlorophyll content, parameterization of the ALAadj in the PROSAIL model for wheat and soybean was carried out. An algorithm integrating the random forest and PROSAIL simulations with prior ALAadj information was developed for wheat and soybean CCC retrieval. Ground-measured CCC measurements were used to validate the CCC retrieved from canopy spectra. The results showed that the ALAadj values (62 degrees for wheat; 45 degrees for soybean) that were parameterized for the PROSAIL model demonstrated good discrimination between the two crops. The proposed algorithm improved the CCC retrieval accuracy for wheat and soybean, regardless of whether continuous visible to near-infrared spectra with 50 bands (RMSE from 39.9 to 32.9 μg cm−2; R2 from 0.67 to 0.76) or discrete spectra with 13 bands (RMSE from 43.9 to 33.7 μg cm−2; R2 from 0.63 to 0.74) and nine bands (RMSE from 45.1 to 37.0 μg cm−2; R2 from 0.61 to 0.71) were used. The proposed hybrid algorithm, based on PROSAIL simulations with ALAadj, has the potential for satellite-based CCC estimation across different crop types, and it also has a good reference value for the retrieval of other crop parameters.

Analysis of designs used in monitoring crop growth based on remote sensing methods

Choosing appropriate designs and methods for monitoring crop growth is a challenging process of major importance. Remote sensing from space and manned or unmanned airborne operations are used to measure crop reflectance and a wide variety of other agricultural parameters. While some experiments use only a few, specific methods and designs and organize the results in lists of evidence, other experiments use a wider range of techniques to create a more credible and comprehensive assessment of crop yield. Particular situations related to the available resources in terms of data collection and expertise in addition to the intended use of the results may require specific designs or a combination of methods and design. This review intended to explore the challenges and document a range of possible approaches for remote evaluation of crop growth. The scope of the analysis was designed to provide information on methods that work under different circumstances and why and how effective a particular method is an approach to monitoring crop growth. Considering the agricultural ecosystems as complex systems and the working methodology as having a high degree of complexity, we propose an approach suitable for complex systems. New sets of models and methods need to be developed for approaching complex systems, which are characterized by self-organization, nonlinearity, ongoing adaptation, and networking.

Research Progress on Remote Sensing Classification Methods for Farmland Vegetation

Crop planting area and spatial distribution information have important practical significance for food security, global change, and sustainable agricultural development. How to efficiently and accurately identify crops in a timely manner by remote sensing in order to determine the crop planting area and its temporal–spatial dynamic change information is a core issue of monitoring crop growth and estimating regional crop yields. Based on hundreds of relevant documents from the past 25 years, in this paper, we summarize research progress in relation to farmland vegetation identification and classification by remote sensing. The classification and identification of farmland vegetation includes classification based on vegetation index, spectral bands, multi-source data fusion, artificial intelligence learning, and drone remote sensing. Representative studies of remote sensing methods are collated, the main content of each technology is summarized, and the advantages and disadvantages of each method are analyzed. Current problems related to crop remote sensing identification are then identified and future development directions are proposed.

"Smart Crop-Field Monitoring and Irrigation System Based On IoT"

Agriculture is critical to the growth of agrarian countries like India. Agriculture-related issues have long been a roadblock to the country's growth. Smart agriculture, which involves updating existing agricultural techniques, is the only answer to this issue. As a result, the suggested approach seeks to use automation and IoT technology to make agriculture smart. Crop growth monitoring and selection, irrigation decision assistance, and other applications are enabled by the Internet of Things (IoT). To modernize and increase agricultural production, a Microcontroller Pi-based IoT watering solution is recommended. The major purpose of this research is to grow crops with the least amount of water possible. Most farmers spend hours throughout the fields in order to focus on groundwater resources to plants at the proper time. Groundwater contamination should be enhanced, and the complexity of the system circuit should be reduced. The protocol determines the quantity of water necessary analysis of the results obtained from the sensors. Six sensors detect the temperature of the food of the soil, but also the precipitation, temperatures, and duration of daylight each day, and send the data to the mobile node. Dependent on these characteristics, the proposed systems must calculate the quantity of water needed for irrigation. The usage of Crop Monitoring (PA) with virtualization is the system's key advantage, as it will evaluate and use of water nitrates while boosting crop yields and aid in analyzing field condition.

Irrigation control and image acquisition for rice cultivation in UAE desert soil

Precision water management and crop growth monitoring are essential where water is a scarce, especially in desert soils. The purpose of the study was to control the irrigation and real-time image acquisition for monitoring the rice cultivation inside the net house under the UAE desert soil. An automated data acquisition system was constructed, installed, and tested in the experimental site at Al-Foah, Al-Ain. Soil water content sensors were placed in the different depths of desert soils, and an automatic irrigation logic was implemented to maintain the average of 30% desired water content level in desert soils. The irrigation rate was controlled based on the sensor data and the on/off of the pump and valves. When the average soil water content percentage level exceeds 30%, the pump and solenoid valve automatically turned off and vice versa. A Raspberry Pi operating system was used to control the irrigation, and a Raspberry Pi camera system was used to capture the real-time images for monitoring the rice growth and development. A web server was developed to upload and display the sensor values and images using python programing language through the embedded Wi-Fi network service. The web-based monitoring system was allowed to monitor the rice field situation from anywhere and download data from the site. The existing irrigation technique would help to grow the rice in UAE desert soil environments.

Transfer-learning-based approach for leaf chlorophyll content estimation of winter wheat from hyperspectral data

Leaf chlorophyll, as a key factor for carbon circulation in the ecosystem, is significant for the photosynthetic productivity estimation and crop growth monitoring in agricultural management. Hyperspectral remote sensing (RS) provides feasible solutions for obtaining crop leaf chlorophyll content (LCC) by the advantages of its repeated and high throughput observations. However, the data redundancy and the poor robustness of the inversion models are still major obstacles that prevent the widespread application of hyperspectral RS for crop LCC evaluation. For winter wheat LCC inversion from hyperspectral observations, this study described a novel hybrid method, which is based on the combination of amplitude- and shape- enhanced 2D correlation spectrum (2DCOS) and transfer learning. The innovative feature selection method, amplitude- and shape- enhanced 2DCOS, which originated from 2DCOS, additionally considered the relationships between external perturbations and hyperspectral amplitude and shape characteristics to enhance the dynamic spectrum response. To extract the representative LCC featured wavelengths, the amplitude- and shape- enhanced 2DCOS was conducted on the leaf optical PROperties SPECTra (PROSPECT) + Scattering from Arbitrarily Inclined Leaves (SAIL) (PROSAIL) simulated dataset, which covered most possible winter wheat canopy spectra. Nine wavelengths (i.e., 455, 545, 571, 615, 641, 662, 706, 728, and 756 nm) were then extracted as the sensitive wavelengths of LCC with the amplitude- and shape- enhanced 2DCOS. These wavelengths had specificity to LCC and showed good correlation with LCC from the aspect of photosynthesis mechanism, molecular structure, and optical properties. The transfer learning techniques based on the deep neural network was then introduced to transfer the knowledge learned from the PROSAIL simulated dataset to the inversion tasks of field measured LCC. Parts of the labeled samples in field observations were used to finetune the model pre-trained by the simulated dataset to improve the inversion accuracy of the winter wheat LCC in different field scenes, aiming to reduce the need for the field measured and labeled sample size. To further ascertain the universality, transferability and predictive ability of the proposed hybrid method, field samples collected from different locations at different phenological phases, including the jointing and heading stages in 2013, 2014, and 2018, were utilized as target tasks to validate the proposed hybrid method. Moreover, the LCC of winter wheat estimated with the proposed method was evaluated with the ground-based platform and the UAV-based platform to verify the model versatility for different monitoring platforms. Various validations demonstrated that the hybrid inversion method combining the amplitude- and shape- enhanced 2DCOS and the fine-tuned transfer learning model could effectively estimate winter wheat LCC with good accuracy and robustness, and can be extended to the detection and inversion of other key variables of crops.

FoveaMask: A fast and accurate deep learning model for green fruit instance segmentation

In the process of agricultural automation production, efficient and accurate segmentation of target fruit is the basis and guarantee for numerous applications including crop growth monitoring, yield prognosis, and machine picking. Green fruit is apt to affect by complicated scenes such as occlusions and overlaps, as well as the homo-chromatic background, which brings great challenges to the recognition and segmentation. In this paper, we propose a novel methodology named FoveaMask for improving the robustness and generalization of green fruit segmentation framework. Features of input images are firstly extracted by ResNet and fused by FPN. The classification and bounding-box regression of each spatial position on the feature maps are then carried out directly by the way of full convolution. RoI Align layer is applied to fix feature region of proposals to the same size yet preserve exact spatial locations. Finally, instance-level fruit segmentation is realized by pixel-level classification on each proposal using embedded mask branches. The whole network architecture of the new model does not involve the related design and operation of anchor, which greatly improves the generalization ability for different shape fruits, alleviates the computing and storage resources, and balances the contradiction between accuracy and efficiency simultaneously. Additionally, a position attention module(PAM) is introduced into the embedding mask branch to aggregate the effective information pixels, which can improve the robustness of the segmentation model in the actual complex environment of the orchard. We test the model on green apple and immature persimmon data sets and the experimental results show that FoveaMask performs best in terms of both recognition accuracy and model complexity compared with other 11 different types of detection and segmentation models.