15 results
Search Results
Now showing 1 - 10 of 15
- 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.
- ItemPublisher Correction: Rapid and low-cost insect detection for analysing species trapped on yellow sticky traps(London : Nature Publishing Group, 2021) Böckmann, Elias; Pfaff, Alexander; Schirrmann, Michael; Pflanz, MichaelCorrection to: Scientific Reports https://doi.org/10.1038/s41598-021-89930-w, published online 17 May 2021
- ItemMonitoring Agronomic Parameters of Winter Wheat Crops with Low-Cost UAV Imagery(Basel : MDPI, 2016) Schirrmann, Michael; Giebel, Antje; Gleiniger, Franziska; Pflanz, Michael; Lentschke, Jan; Dammer, Karl-HeinzMonitoring the dynamics in wheat crops requires near-term observations with high spatial resolution due to the complex factors influencing wheat growth variability. We studied the prospects for monitoring the biophysical parameters and nitrogen status in wheat crops with low-cost imagery acquired from unmanned aerial vehicles (UAV) over an 11 ha field. Flight missions were conducted at approximately 50 m in altitude with a commercial copter and camera system—three missions were performed between booting and maturing of the wheat plants and one mission after tillage. Ultra-high resolution orthoimages of 1.2 cm·px−1 and surface models were generated for each mission from the standard red, green and blue (RGB) aerial images. The image variables were extracted from image tone and surface models, e.g., RGB ratios, crop coverage and plant height. During each mission, 20 plots within the wheat canopy with 1 × 1 m2 sample support were selected in the field, and the leaf area index, plant height, fresh and dry biomass and nitrogen concentrations were measured. From the generated UAV imagery, we were able to follow the changes in early senescence at the individual plant level in the wheat crops. Changes in the pattern of the wheat canopy varied drastically from one mission to the next, which supported the need for instantaneous observations, as delivered by UAV imagery. The correlations between the biophysical parameters and image variables were highly significant during each mission, and the regression models calculated with the principal components of the image variables yielded R2 values between 0.70 and 0.97. In contrast, the models of the nitrogen concentrations yielded low R2 values with the best model obtained at flowering (R2 = 0.65). The nitrogen nutrition index was calculated with an accuracy of 0.10 to 0.11 NNI for each mission. For all models, information about the surface models and image tone was important. We conclude that low-cost RGB UAV imagery will strongly aid farmers in observing biophysical characteristics, but it is limited for observing the nitrogen status within wheat crops.
- ItemPrimarily tests of a optoelectronic in-canopy sensor for evaluation of vertical disease infection in cereals(New York, NY : Wiley, 2022) Dammer, Karl-Heinz; Schirrmann, MichaelBACKGROUND: Health scouting of crops by satellite, airplanes, unmanned aerial (UAV) and ground vehicles can only evaluate the crop from above. The visible leaves may show no disease symptoms, but lower, older leaves not visible from above can do. A mobile in-canopy sensor was developed, carried by a tractor to detect diseases in cereal crops. Photodiodes measure the reflected light in the red and infrared wavelength range at 10 different vertical heights in lateral directions. RESULTS: Significant differences occurred in the vegetation index NDVI of sensor levels operated inside and near the winter wheat canopy between infected (stripe rust: 2018, 2019 / leaf rust: 2020) and control plots. The differences were not significant at those sensor levels operated far above the canopy. CONCLUSIONS: Lateral reflectance measurements inside the crop canopy are able to distinguish between disease-infected and healthy crops. In future mobile in-canopy scouting could be an extension to the common above-canopy scouting praxis for making spraying decisions by the farmer or decision support systems. © 2021 The Authors. Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.
- ItemImproving Deep Learning-based Plant Disease Classification with Attention Mechanism(Berlin ; Heidelberg : Springer, 2022) Alirezazadeh, Pendar; Schirrmann, Michael; Stolzenburg, FriederIn recent years, deep learning-based plant disease classification has been widely developed. However, it is challenging to collect sufficient annotated image data to effectively train deep learning models for plant disease recognition. The attention mechanism in deep learning assists the model to focus on the informative data segments and extract the discriminative features of inputs to enhance training performance. This paper investigates the Convolutional Block Attention Module (CBAM) to improve classification with CNNs, which is a lightweight attention module that can be plugged into any CNN architecture with negligible overhead. Specifically, CBAM is applied to the output feature map of CNNs to highlight important local regions and extract more discriminative features. Well-known CNN models (i.e. EfficientNetB0, MobileNetV2, ResNet50, InceptionV3, and VGG19) were applied to do transfer learning for plant disease classification and then fine-tuned by a publicly available plant disease dataset of foliar diseases in pear trees called DiaMOS Plant. Amongst others, this dataset contains 3006 images of leaves affected by different stress symptoms. Among the tested CNNs, EfficientNetB0 has shown the best performance. EfficientNetB0+CBAM has outperformed EfficientNetB0 and obtained 86.89% classification accuracy. Experimental results show the effectiveness of the attention mechanism to improve the recognition accuracy of pre-trained CNNs when there are few training data.
- ItemGlobal data on earthworm abundance, biomass, diversity and corresponding environmental properties(London : Nature Publ. Group, 2021) Phillips, Helen R. P.; Bach, Elizabeth M.; Bartz, Marie L. C.; Bennett, Joanne M.; Beugnon, Rémy; Briones, Maria J. I.; Brown, George G.; Ferlian, Olga; Gongalsky, Konstantin B.; Guerra, Carlos A.; König-Ries, Birgitta; López-Hernández, Danilo; Loss, Scott R.; Marichal, Raphael; Matula, Radim; Minamiya, Yukio; Moos, Jan Hendrik; Moreno, Gerardo; Morón-Ríos, Alejandro; Motohiro, Hasegawa; Muys, Bart; Krebs, Julia J.; Neirynck, Johan; Norgrove, Lindsey; Novo, Marta; Nuutinen, Visa; Nuzzo, Victoria; Mujeeb Rahman, P.; Pansu, Johan; Paudel, Shishir; Pérès, Guénola; Pérez-Camacho, Lorenzo; Orgiazzi, Alberto; Ponge, Jean-François; Prietzel, Jörg; Rapoport, Irina B.; Rashid, Muhammad Imtiaz; Rebollo, Salvador; Rodríguez, Miguel Á.; Roth, Alexander M.; Rousseau, Guillaume X.; Rozen, Anna; Sayad, Ehsan; Ramirez, Kelly S.; van Schaik, Loes; Scharenbroch, Bryant; Schirrmann, Michael; Schmidt, Olaf; Schröder, Boris; Seeber, Julia; Shashkov, Maxim P.; Singh, Jaswinder; Smith, Sandy M.; Steinwandter, Michael; Russell, David J.; Szlavecz, Katalin; Talavera, José Antonio; Trigo, Dolores; Tsukamoto, Jiro; Uribe-López, Sheila; de Valença, Anne W.; Virto, Iñigo; Wackett, Adrian A.; Warren, Matthew W.; Webster, Emily R.; Schwarz, Benjamin; Wehr, Nathaniel H.; Whalen, Joann K.; Wironen, Michael B.; Wolters, Volkmar; Wu, Pengfei; Zenkova, Irina V.; Zhang, Weixin; Cameron, Erin K.; Eisenhauer, Nico; Wall, Diana H.; Brose, Ulrich; Decaëns, Thibaud; Lavelle, Patrick; Loreau, Michel; Mathieu, Jérôme; Mulder, Christian; van der Putten, Wim H.; Rillig, Matthias C.; Thakur, Madhav P.; de Vries, Franciska T.; Wardle, David A.; Ammer, Christian; Ammer, Sabine; Arai, Miwa; Ayuke, Fredrick O.; Baker, Geoff H.; Baretta, Dilmar; Barkusky, Dietmar; Beauséjour, Robin; Bedano, Jose C.; Birkhofer, Klaus; Blanchart, Eric; Blossey, Bernd; Bolger, Thomas; Bradley, Robert L.; Brossard, Michel; Burtis, James C.; Capowiez, Yvan; Cavagnaro, Timothy R.; Choi, Amy; Clause, Julia; Cluzeau, Daniel; Coors, Anja; Crotty, Felicity V.; Crumsey, Jasmine M.; Dávalos, Andrea; Cosín, Darío J. Díaz; Dobson, Annise M.; Domínguez, Anahí; Duhour, Andrés Esteban; van Eekeren, Nick; Emmerling, Christoph; Falco, Liliana B.; Fernández, Rosa; Fonte, Steven J.; Fragoso, Carlos; Franco, André L. C.; Fusilero, Abegail; Geraskina, Anna P.; Gholami, Shaieste; González, Grizelle; Gundale, Michael J.; López, Mónica Gutiérrez; Hackenberger, Branimir K.; Hackenberger, Davorka K.; Hernández, Luis M.; Hirth, Jeff R.; Hishi, Takuo; Holdsworth, Andrew R.; Holmstrup, Martin; Hopfensperger, Kristine N.; Lwanga, Esperanza Huerta; Huhta, Veikko; Hurisso, Tunsisa T.; Iannone, Basil V.; Iordache, Madalina; Irmler, Ulrich; Ivask, Mari; Jesús, Juan B.; Johnson-Maynard, Jodi L.; Joschko, Monika; Kaneko, Nobuhiro; Kanianska, Radoslava; Keith, Aidan M.; Kernecker, Maria L.; Koné, Armand W.; Kooch, Yahya; Kukkonen, Sanna T.; Lalthanzara, H.; Lammel, Daniel R.; Lebedev, Iurii M.; Le Cadre, Edith; Lincoln, Noa K.Earthworms are an important soil taxon as ecosystem engineers, providing a variety of crucial ecosystem functions and services. Little is known about their diversity and distribution at large spatial scales, despite the availability of considerable amounts of local-scale data. Earthworm diversity data, obtained from the primary literature or provided directly by authors, were collated with information on site locations, including coordinates, habitat cover, and soil properties. Datasets were required, at a minimum, to include abundance or biomass of earthworms at a site. Where possible, site-level species lists were included, as well as the abundance and biomass of individual species and ecological groups. This global dataset contains 10,840 sites, with 184 species, from 60 countries and all continents except Antarctica. The data were obtained from 182 published articles, published between 1973 and 2017, and 17 unpublished datasets. Amalgamating data into a single global database will assist researchers in investigating and answering a wide variety of pressing questions, for example, jointly assessing aboveground and belowground biodiversity distributions and drivers of biodiversity change.
- ItemProximal Soil Sensing - A Contribution for Species Habitat Distribution Modelling of Earthworms in Agricultural Soils?(San Francisco, California, US : PLOS, 2016) Schirrmann, Michael; Joschko, Monika; Gebbers, Robin; Kramer, Eckart; Zörner, Mirjam; Barkusky, Dietmar; Timmer, JensBackground: Earthworms are important for maintaining soil ecosystem functioning and serve as indicators of soil fertility. However, detection of earthworms is time-consuming, which hinders the assessment of earthworm abundances with high sampling density over entire fields. Recent developments of mobile terrestrial sensor platforms for proximal soil sensing (PSS) provided new tools for collecting dense spatial information of soils using various sensing principles. Yet, the potential of PSS for assessing earthworm habitats is largely unexplored. This study investigates whether PSS data contribute to the spatial prediction of earthworm abundances in species distribution models of agricultural soils. Methodology/Principal Findings: Proximal soil sensing data, e.g., soil electrical conductivity (EC), pH, and near infrared absorbance (NIR), were collected in real-time in a field with two management strategies (reduced tillage / conventional tillage) and sandy to loam soils. PSS was related to observations from a long-term (11 years) earthworm observation study conducted at 42 plots. Earthworms were sampled from 0.5 x 0.5 x 0.2 m³ soil blocks and identified to species level. Sensor data were highly correlated with earthworm abundances observed in reduced tillage but less correlated with earthworm abundances observed in conventional tillage. This may indicate that management influences the sensor-earthworm relationship. Generalized additive models and state-space models showed that modelling based on data fusion from EC, pH, and NIR sensors produced better results than modelling without sensor data or data from just a single sensor. Regarding the individual earthworm species, particular sensor combinations were more appropriate than others due to the different habitat requirements of the earthworms. Earthworm species with soil-specific habitat preferences were spatially predicted with higher accuracy by PSS than more ubiquitous species. Conclusions/Significance: Our findings suggest that PSS contributes to the spatial modelling of earthworm abundances at field scale and that it will support species distribution modelling in the attempt to understand the soil-earthworm relationships in agroecosystems.
- ItemDeep Learning Object Detection for Image Analysis of Cherry Fruit Fly (Rhagoletis cerasi L.) on Yellow Sticky Traps(Berlin ; Heidelberg : Springer, 2022) Salamut, Christian; Kohnert, Iris; Landwehr, Niels; Pflanz, Michael; Schirrmann, Michael; Zare, MohammadInsect populations appear with a high spatial, temporal and type-specific diversity in orchards. One of the many monitoring tools for pest management is the manual assessment of sticky traps. However, this type of assessment is laborious and time-consuming so that only a few locations can be controlled in an orchard. The aim of this study is to test state-of-the art object detection algorithms from deep learning to automatically detect cherry fruit flies (Rhagoletis cerasi), a common insect pest in cherry plantations, within images from yellow sticky traps. An image annotation database was built with images taken from yellow sticky traps with more than 1600 annotated cherry fruit flies. For better handling in the computational algorithms, the images were augmented to smaller ones by the known image preparation methods “flipping” and “cropping” before performing the deep learning. Five deep learning image recognition models were tested including Faster Region-based Convolutional Neural Network (R-CNN) with two different methods of pretraining, Single Shot Detector (SSD), RetinaNet, and You Only Look Once version 5 (YOLOv5). R‑CNN and RetinaNet models outperformed other ones with a detection average precision of 0.9. The results indicate that deep learning can act as an integral component of an automated system for high-throughput assessment of pest insects in orchards. Therefore, this can reduce the time for repetitive and laborious trap assessment but also increase the observed amount of sticky traps
- ItemEarly Detection of Stripe Rust in Winter Wheat Using Deep Residual Neural Networks(Lausanne : Frontiers Media, 2021) Schirrmann, Michael; Landwehr, Niels; Giebel, Antje; Garz, Andreas; Dammer, Karl-HeinzStripe rust (Pst) is a major disease of wheat crops leading untreated to severe yield losses. The use of fungicides is often essential to control Pst when sudden outbreaks are imminent. Sensors capable of detecting Pst in wheat crops could optimize the use of fungicides and improve disease monitoring in high-throughput field phenotyping. Now, deep learning provides new tools for image recognition and may pave the way for new camera based sensors that can identify symptoms in early stages of a disease outbreak within the field. The aim of this study was to teach an image classifier to detect Pst symptoms in winter wheat canopies based on a deep residual neural network (ResNet). For this purpose, a large annotation database was created from images taken by a standard RGB camera that was mounted on a platform at a height of 2 m. Images were acquired while the platform was moved over a randomized field experiment with Pst-inoculated and Pst-free plots of winter wheat. The image classifier was trained with 224 × 224 px patches tiled from the original, unprocessed camera images. The image classifier was tested on different stages of the disease outbreak. At patch level the image classifier reached a total accuracy of 90%. To test the image classifier on image level, the image classifier was evaluated with a sliding window using a large striding length of 224 px allowing for fast test performance. At image level, the image classifier reached a total accuracy of 77%. Even in a stage with very low disease spreading (0.5%) at the very beginning of the Pst outbreak, a detection accuracy of 57% was obtained. Still in the initial phase of the Pst outbreak with 2 to 4% of Pst disease spreading, detection accuracy with 76% could be attained. With further optimizations, the image classifier could be implemented in embedded systems and deployed on drones, vehicles or scanning systems for fast mapping of Pst outbreaks.
- 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.