11 results
Search Results
Now showing 1 - 10 of 11
- ItemOptimized Deep Learning Model as a Basis for Fast UAV Mapping of Weed Species in Winter Wheat Crops(Basel : MDPI AG, 2021) de Camargo, Tibor; Schirrmann, Michael; Landwehr, Niels; Dammer, Karl-Heinz; Pflanz, MichaelWeed maps should be available quickly, reliably, and with high detail to be useful for site-specific management in crop protection and to promote more sustainable agriculture by reducing pesticide use. Here, the optimization of a deep residual convolutional neural network (ResNet-18) for the classification of weed and crop plants in UAV imagery is proposed. The target was to reach sufficient performance on an embedded system by maintaining the same features of the ResNet-18 model as a basis for fast UAV mapping. This would enable online recognition and subsequent mapping of weeds during UAV flying operation. Optimization was achieved mainly by avoiding redundant computations that arise when a classification model is applied on overlapping tiles in a larger input image. The model was trained and tested with imagery obtained from a UAV flight campaign at low altitude over a winter wheat field, and classification was performed on species level with the weed species Matricaria chamomilla L., Papaver rhoeas L., Veronica hederifolia L., and Viola arvensis ssp. arvensis observed in that field. The ResNet-18 model with the optimized image-level prediction pipeline reached a performance of 2.2 frames per second with an NVIDIA Jetson AGX Xavier on the full resolution UAV image, which would amount to about 1.78 ha h−1 area output for continuous field mapping. The overall accuracy for determining crop, soil, and weed species was 94%. There were some limitations in the detection of species unknown to the model. When shifting from 16-bit to 32-bit model precision, no improvement in classification accuracy was observed, but a strong decline in speed performance, especially when a higher number of filters was used in the ResNet-18 model. Future work should be directed towards the integration of the mapping process on UAV platforms, guiding UAVs autonomously for mapping purpose, and ensuring the transferability of the models to other crop fields.
- ItemIoT-Based Sensor Data Fusion for Determining Optimality Degrees of Microclimate Parameters in Commercial Greenhouse Production of Tomato(Basel : MDPI, 2020) Rezvani, Sayed Moin-eddin; Abyaneh, Hamid Zare; Shamshiri, Redmond R.; Balasundram, Siva K.; Dworak, Volker; Goodarzi, Mohsen; Sultan, Muhammad; Mahns, BenjaminOptimum microclimate parameters, including air temperature (T), relative humidity (RH) and vapor pressure deficit (VPD) that are uniformly distributed inside greenhouse crop production systems are essential to prevent yield loss and fruit quality. The objective of this research was to determine the spatial and temporal variations in the microclimate data of a commercial greenhouse with tomato plants located in the mid-west of Iran. For this purpose, wireless sensor data fusion was incorporated with a membership function model called Optimality Degree (OptDeg) for real-time monitoring and dynamic assessment of T, RH and VPD in different light conditions and growth stages of tomato. This approach allows growers to have a simultaneous projection of raw data into a normalized index between 0 and 1. Custom-built hardware and software based on the concept of the Internet-of-Things, including Low-Power Wide-Area Network (LoRaWAN) transmitter nodes, a multi-channel LoRaWAN gateway and a web-based data monitoring dashboard were used for data collection, data processing and monitoring. The experimental approach consisted of the collection of meteorological data from the external environment by means of a weather station and via a grid of 20 wireless sensor nodes distributed in two horizontal planes at two different heights inside the greenhouse. Offline data processing for sensors calibration and model validation was carried in multiple MATLAB Simulink blocks. Preliminary results revealed a significant deviation of the microclimate parameters from optimal growth conditions for tomato cultivation due to the inaccurate timer-based heating and cooling control systems used in the greenhouse. The mean OptDeg of T, RH and VPD were 0.67, 0.94, 0.94 in January, 0.45, 0.36, 0.42 in June and 0.44, 0.0, 0.12 in July, respectively. An in-depth analysis of data revealed that averaged OptDeg values, as well as their spatial variations in the horizontal profile were closer to the plants’ comfort zone in the cold season as compared with those in the warm season. This was attributed to the use of heating systems in the cold season and the lack of automated cooling devices in the warm season. This study confirmed the applicability of using IoT sensors for real-time model-based assessment of greenhouse microclimate on a commercial scale. The presented IoT sensor node and the Simulink model provide growers with a better insight into interpreting crop growth environment. The outcome of this research contributes to the improvement of closed-field cultivation of tomato by providing an integrated decision-making framework that explores microclimate variation at different growth stages in the production season.
- ItemGrowth Height Determination of Tree Walls for Precise Monitoring in Apple Fruit Production Using UAV Photogrammetry(Basel : MDPI, 2020) Hobart, Marius; Pflanz, Michael; Weltzien, Cornelia; Schirrmann, MichaelIn apple cultivation, spatial information about phenotypic characteristics of tree walls would be beneficial for precise orchard management. Unmanned aerial vehicles (UAVs) can collect 3D structural information of ground surface objects at high resolution in a cost-effective and versatile way by using photogrammetry. The aim of this study is to delineate tree wall height information in an apple orchard applying a low-altitude flight pattern specifically designed for UAVs. This flight pattern implies small distances between the camera sensor and the tree walls when the camera is positioned in an oblique view toward the trees. In this way, it is assured that the depicted tree crown wall area will be largely covered with a larger ground sampling distance than that recorded from a nadir perspective, especially regarding the lower crown sections. Overlapping oblique view images were used to estimate 3D point cloud models by applying structure-from-motion (SfM) methods to calculate tree wall heights from them. The resulting height models were compared with ground-based light detection and ranging (LiDAR) data as reference. It was shown that the tree wall profiles from the UAV point clouds were strongly correlated with the LiDAR point clouds of two years (2018: R2 = 0.83; 2019: R2 = 0.88). However, underestimation of tree wall heights was detected with mean deviations of −0.11 m and −0.18 m for 2018 and 2019, respectively. This is attributed to the weaknesses of the UAV point clouds in resolving the very fine shoots of apple trees. Therefore, the shown approach is suitable for precise orchard management, but it underestimated vertical tree wall expanses, and widened tree gaps need to be accounted for.
- ItemCrop Monitoring Using Sentinel-2 and UAV Multispectral Imagery: A Comparison Case Study in Northeastern Germany(Basel : MDPI, 2022) Li, Minhui; Shamshiri, Redmond R.; Weltzien, Cornelia; Schirrmann, MichaelMonitoring within-field crop variability at fine spatial and temporal resolution can assist farmers in making reliable decisions during their agricultural management; however, it traditionally involves a labor-intensive and time-consuming pointwise manual process. To the best of our knowledge, few studies conducted a comparison of Sentinel-2 with UAV data for crop monitoring in the context of precision agriculture. Therefore, prospects of crop monitoring for characterizing biophysical plant parameters and leaf nitrogen of wheat and barley crops were evaluated from a more practical viewpoint closer to agricultural routines. Multispectral UAV and Sentinel-2 imagery was collected over three dates in the season and compared with reference data collected at 20 sample points for plant leaf nitrogen (N), maximum plant height, mean plant height, leaf area index (LAI), and fresh biomass. Higher correlations of UAV data to the agronomic parameters were found on average than with Sentinel-2 data with a percentage increase of 6.3% for wheat and 22.2% for barley. In this regard, VIs calculated from spectral bands in the visible part performed worse for Sentinel-2 than for the UAV data. In addition, large-scale patterns, formed by the influence of an old riverbed on plant growth, were recognizable even in the Sentinel-2 imagery despite its much lower spatial resolution. Interestingly, also smaller features, such as the tramlines from controlled traffic farming (CTF), had an influence on the Sentinel-2 data and showed a systematic pattern that affected even semivariogram calculation. In conclusion, Sentinel-2 imagery is able to capture the same large-scale pattern as can be derived from the higher detailed UAV imagery; however, it is at the same time influenced by management-driven features such as tramlines, which cannot be accurately georeferenced. In consequence, agronomic parameters were better correlated with UAV than with Sentinel-2 data. Crop growers as well as data providers from remote sensing services may take advantage of this knowledge and we recommend the use of UAV data as it gives additional information about management-driven features. For future perspective, we would advise fusing UAV with Sentinel-2 imagery taken early in the season as it can integrate the effect of agricultural management in the subsequent absence of high spatial resolution data to help improve crop monitoring for the farmer and to reduce costs.
- ItemIn-Situ Measurement of Fresh Produce Respiration Using a Modular Sensor-Based System(Basel : MDPI, 2020) Keshri, Nandita; Truppel, Ingo; Herppich, Werner B.; Geyer, Martin; Weltzien, Cornelia; Mahajan, Pramod VIn situ, continuous and real-time monitoring of respiration (R) and respiratory quotient (RQ) are crucial for identifying the optimal conditions for the long-term storage of fresh produce. This study reports the application of a gas sensor (RMS88) and a modular respirometer for in situ real-time monitoring of gas concentrations and respiration rates of strawberries during storage in a lab-scale controlled atmosphere chamber (190 L) and of Pinova apples in a commercial storage facility (170 t). The RMS88 consisted of wireless O2 (0% to 25%) and CO2 sensors (0% to 0.5% and 0% to 5%). The modular respirometer (3.3 L for strawberries and 7.4 L for apples) consisted of a leak-proof arrangement with a water-containing base plate and a glass jar on top. Gas concentrations were continuously recorded by the RMS88 at regular intervals of 1 min for strawberries and 5 min for apples and, in real-time, transferred to a terminal program to calculate respiration rates ( RO2 and RCO2 ) and RQ. Respiration measurement was done in cycles of flushing and measurement period. A respiration measurement cycle with a measurement period of 2 h up to 3 h was shown to be useful for strawberries under air at 10 °C. The start of anaerobic respiration of strawberries due to low O2 concentration (1%) could be recorded in real-time. RO2 and RCO2 of Pinova apples were recorded every 5 min during storage and mean values of 1.6 and 2.7 mL kg−1 h−1, respectively, were obtained when controlled atmosphere (CA) conditions (2% O2, 1.3% CO2 and 2 °C) were established. The modular respirometer was found to be useful for in situ real-time monitoring of respiration rate during storage of fresh produce and offers great potential to be incorporated into RQ-based dynamic CA storage system.
- ItemSoil Nutrient Detection for Precision Agriculture Using Handheld Laser-Induced Breakdown Spectroscopy (LIBS) and Multivariate Regression Methods (PLSR, Lasso and GPR)(Basel : MDPI, 2020) Erler, Alexander; Riebe, Daniel; Beitz, Toralf; Löhmannsröben, Hans-Gerd; Gebbers, RobinPrecision agriculture (PA) strongly relies on spatially differentiated sensor information. Handheld instruments based on laser-induced breakdown spectroscopy (LIBS) are a promising sensor technique for the in-field determination of various soil parameters. In this work, the potential of handheld LIBS for the determination of the total mass fractions of the major nutrients Ca, K, Mg, N, P and the trace nutrients Mn, Fe was evaluated. Additionally, other soil parameters, such as humus content, soil pH value and plant available P content, were determined. Since the quantification of nutrients by LIBS depends strongly on the soil matrix, various multivariate regression methods were used for calibration and prediction. These include partial least squares regression (PLSR), least absolute shrinkage and selection operator regression (Lasso), and Gaussian process regression (GPR). The best prediction results were obtained for Ca, K, Mg and Fe. The coefficients of determination obtained for other nutrients were smaller. This is due to much lower concentrations in the case of Mn, while the low number of lines and very weak intensities are the reason for the deviation of N and P. Soil parameters that are not directly related to one element, such as pH, could also be predicted. Lasso and GPR yielded slightly better results than PLSR. Additionally, several methods of data pretreatment were investigated.
- ItemDirect Measurements of the Volume Flow Rate and Emissions in a Large Naturally Ventilated Building(Basel : MDPI, 2020) Janke, David; Yi, Qianying; Thormann, Lars; Hempel, Sabrina; Amon, Barbara; Nosek, Štepán; van Overbeke, Philippe; Amon, ThomasThe direct measurement of emissions from naturally ventilated dairy barns is challenging due to their large openings and the turbulent and unsteady airflow at the inlets and outlets. The aim of this study was to quantify the impacts of the number and positions of sensors on the estimation of volume flow rate and emissions. High resolution measurements of a naturally ventilated scaled building model in an atmospheric boundary layer wind tunnel were done. Tracer gas was released inside the model and measured at the outlet area, using a fast flame ionization detector (FFID). Additionally, the normal velocity on the area was measured using laser Doppler anemometry (LDA). In total, for a matrix of 65 × 4 sensor positions, the mean normal velocities and the mean concentrations were measured and used to calculate the volume flow rate and the emissions. This dataset was used as a reference to assess the accuracy while systematically reducing the number of sensors and varying the positions of them. The results showed systematic errors in the emission estimation up to +97%, when measurements of concentration and velocity were done at one constant height. This error could be lowered under 5%, when the concentrations were measured as a vertical composite sample.
- ItemApple Shape Detection Based on Geometric and Radiometric Features Using a LiDAR Laser Scanner(Basel : MDPI, 2020) Tsoulias, Nikos; Paraforos, Dimitrios S.; Xanthopoulos, George; Zude-Sasse, ManuelaYield monitoring systems in fruit production mostly rely on color features, making the discrimination of fruits challenging due to varying light conditions. The implementation of geometric and radiometric features in three-dimensional space (3D) analysis can alleviate such difficulties improving the fruit detection. In this study, a light detection and range (LiDAR) system was used to scan apple trees before (TL) and after defoliation (TD) four times during seasonal tree growth. An apple detection method based on calibrated apparent backscattered reflectance intensity (RToF) and geometric features, capturing linearity (L) and curvature (C) derived from the LiDAR 3D point cloud, is proposed. The iterative discretion of apple class from leaves and woody parts was obtained at RToF > 76.1%, L < 15.5%, and C > 73.2%. The position of fruit centers in TL and in TD was compared, showing a root mean square error (RMSE) of 5.7%. The diameter of apples estimated from the foliated trees was related to the reference values based on the perimeter of the fruits, revealing an adjusted coefficient of determination (R2adj) of 0.95 and RMSE of 9.5% at DAFB120. When comparing the results obtained on foliated and defoliated tree’s data, the estimated number of fruit’s on foliated trees at DAFB42, DAFB70, DAFB104, and DAFB120 88.6%, 85.4%, 88.5%, and 94.8% of the ground truth values, respectively. The algorithm resulted in maximum values of 88.2% precision, 91.0% recall, and 89.5 F1 score at DAFB120. The results point to the high capacity of LiDAR variables [RToF, C, L] to localize fruit and estimate its size by means of remote sensing.
- ItemDetermination of Nutrients in Liquid Manures and Biogas Digestates by Portable Energy-Dispersive X-ray Fluorescence Spectrometry(Basel : MDPI AG, 2021) Horf, Michael; Gebbers, Robin; Vogel, Sebastian; Ostermann, Markus; Piepel, Max-Frederik; Olfs, Hans-WernerKnowing the exact nutrient composition of organic fertilizers is a prerequisite for their appropriate application to improve yield and to avoid environmental pollution by over-fertilization. Traditional standard chemical analysis is cost and time-consuming and thus it is unsuitable for a rapid analysis before manure application. As a possible alternative, a handheld X-ray fluorescence (XRF) spectrometer was tested to enable a fast, simultaneous, and on-site analysis of several elements. A set of 62 liquid pig and cattle manures as well as biogas digestates were collected, intensively homogenized and analysed for the macro plant nutrients phosphorus, potassium, magnesium, calcium, and sulphur as well as the micro nutrients manganese, iron, copper, and zinc using the standard lab procedure. The effect of four different sample preparation steps (original, dried, filtered, and dried filter residues) on XRF measurement accuracy was examined. Therefore, XRF results were correlated with values of the reference analysis. The best R2s for each element ranged from 0.64 to 0.92. Comparing the four preparation steps, XRF results for dried samples showed good correlations (0.64 and 0.86) for all elements. XRF measurements using dried filter residues showed also good correlations with R2s between 0.65 and 0.91 except for P, Mg, and Ca. In contrast, correlation analysis for liquid samples (original and filtered) resulted in lower R2s from 0.02 to 0.68, except for K (0.83 and 0.87, respectively). Based on these results, it can be concluded that handheld XRF is a promising measuring system for element analysis in manures and digestates.
- ItemHyperspectral Imaging Tera Hertz System for Soil Analysis : Initial Results(Basel : MDPI, 2020) Dworak, Volker; Mahns, Benjamin; Selbeck, Jörn; Gebbers, Robin; Weltzien, CorneliaAnalyzing soils using conventional methods is often time consuming and costly due to their complexity. These methods require soil sampling (e.g., by augering), pretreatment of samples (e.g., sieving, extraction), and wet chemical analysis in the laboratory. Researchers are seeking alternative sensor-based methods that can provide immediate results with little or no excavation and pretreatment of samples. Currently, visible and infrared spectroscopy, electrical resistivity, gamma ray spectroscopy, and X-ray spectroscopy have been investigated extensively for their potential utility in soil sensing. Little research has been conducted on the application of THz (Tera Hertz) spectroscopy in soil science. The Tera Hertz band covers the frequency range between 100 GHz and 10 THz of the electromagnetic spectrum. One important feature of THz radiation is its correspondence with the particle size of the fine fraction of soil minerals (clay < 2 µm to sand < 2 mm). The particle size distribution is a fundamental soil property that governs soil water and nutrient content, among other characteristics. The interaction of THz radiation with soil particles creates detectable Mie scattering, which is the elastic scattering of electromagnetic waves by particles whose diameter corresponds approximately to the wavelength of the radiation. However, single-spot Mie scattering spectra are difficult to analyze and the understanding of interaction between THz radiation and soil material requires basic research. To improve the interpretation of THz spectra, a hyperspectral imaging system was developed. The addition of the spatial dimension to THz spectra helps to detect relevant features. Additionally, multiple samples can be scanned in parallel and measured under identical conditions, and the high number of data points within an image can improve the statistical accuracy. Technical details of the newly designed hyperspectral imaging THz system working from 250 to 370 GHz are provided. Results from measurements of different soil samples and buried objects in soil demonstrated its performance. The system achieved an optical resolution of about 2 mm. The sensitivity of signal damping to the changes in particle size of 100 µm is about 10 dB. Therefore, particle size variations in the µm range should be detectable. In conclusion, automated hyperspectral imaging reduced experimental effort and time consumption, and provided reliable results because of the measurement of hundreds of sample positions in one run. At this stage, the proposed setup cannot replace the current standard laboratory methods, but the present study represents the initial step to develop a new automated method for soil analysis and imaging.