Topics
| Filter results15 paper(s) found. |
|---|
1. Spotweeds: a Multiclass UASs Acquired Weed Image Dataset to Facilitate Site-specific Aerial Spraying Application Using Deep LearningUnmanned aerial systems (UASs)-based spot spraying application is considered a boon in Precision Agriculture (PA). Because of spot spraying, the amount of herbicide usage has reduced significantly resulting in less water contamination or crop plant injury. In the last demi-decade, Deep Learning (DL) has displayed tremendous potential to accomplish the task of identifying weeds for spot spraying application. Also, most of the ground-based weed management technologies have relied on DL techniqu... N. Rai, Y. Zhang, J. Quanbeck, A. Christensen, X. Sun |
2. A Generative Adversarial Network-based Method for High Fidelity Synthetic Data AugmentationDigital Agriculture has led to new phenotyping methods that use artificial intelligence and machine learning solutions on image and video data collected from lab, greenhouse, and field environments. The availability of accurately annotated image and video data remains a bottleneck for developing most machine learning and deep learning models. Typically, deep learning models require thousands of unique samples to accurately learn a given task. However, manual annotation of a large dataset will... S. Sridharan, S. Sornapudi, Q. Hu, S. Kumpatla, J. Bier |
3. Meta Deep Learning Using Minimal Training Images for Weed Classification in Wild BlueberryDeep learning convolutional neural networks (CNNs) have gained popularity in recent years for their ability to classify images with high levels of accuracy. In agriculture, they have been applied for disease identification, crop growth monitoring, animal behaviour tracking, and weed classification. Datasets traditionally consisting of thousands of images of each desired target are required to train CNNs. A recent survey of Nova Scotia wild blueberry (Vaccinium angustifolium Ait.) fie... P.J. Hennessy, T.J. Esau, A.W. Schumann, A.A. Farooque, Q.U. Zaman, S.N. White |
4. Generation of Site-specific Nitrogen Response Curves for Winter Wheat Using Deep LearningNitrogen response (N-response) curves are tools used to support farm management decisions. Conventionally, the N-response curve is modeled as an exponential function that aims to identify an important threshold for a given field: the economic optimum point. This is useful to determine the nitrogen rate beyond which there is no actual profit for the farmers. In this work, we show that N-response curves are not only field-specific but also site-specific and, as such, economic optimum points sho... G. Morales, J.W. Sheppard, A. Peerlinck, P. Hegedus, B. Maxwell |
5. Real-time Detection of Picking Region of Ridge Planted Strawberries Based on YOLOv5s with a Modified NeckRobotic strawberry harvesting requires machine vision system to have the ability to detect the presence, maturity, and location of strawberries. Strawberries, however, can easily be bruised, injured, and even damaged during robotic harvest if not picked properly because of their soft surfaces. Therefore, it is important to cut or pick the strawberry stems instead of picking the fruit directly. Additionally, real-time detection is critical for robotic strawberry harvesting to adapt to the chan... Z. He, K. Manoj, Q. Zhang, S. Kshetri |
6. Predicting Below and Above Ground Peanut Biomass and Maturity Using Multi-target RegressionPeanut growth and maturity prediction can help farmers and breeding programs improving crop management. Remote sensing images collected by satellites and drones make possible and accurate crop monitoring. Today, empirical relations between crop biomass and spectral reflectance could be used for prediction of single variables such as aboveground crop biomass, pod weight (PW), or peanut maturity. Robust algorithms such as multioutput regression (MTR) implemented through multioutput random fores... M.F. Oliveira, F.M. Carneiro, M. Thurmond, M.D. Del val, L.P. Oliveira, B. Ortiz, A. Sanz-saez, D. Tedesco |
7. From Fragmented Data to Unified Insights: Leveraging Data Standardization Tools for Better Collaboration and Agronomic Big Data AnalysisThe quantity and scope of agronomic data available for researchers in both industry and academia is increasing rapidly. Data sources include a myriad of different streams, such as field experiments, sensors, climatic data, socioeconomic data or remote sensing. The lack of standards and workflows frequently leads agronomic data to be fragmented and siloed, hampering collaboration efforts within research labs, university departments, or research institutes. Researchers and businesses therefore ... S. Sela |
8. Coupling Machine Learning Algorithms and GIS for Crop Yield Predictions Based on Remote Sensing Imagery and Topographic IndicesIn-season yield prediction can support crop management decisions helping farmers achieve their yield goals. The use of remote sensing to predict yield it is an alternative for non-destructive yield assessment but coupling auxiliary data such as topography features could help increase the accuracy of yield estimation. Predictive algorithms that can effectively identify, process and predict yield at field scale base on remote sensing and topography still needed. Machine learning could be an alt... M.F. Oliveira, G.T. Morata, B. Ortiz, R.P. Silva, A. Jimenez |
9. A Framework for Imputation of Missing Parts in UAV Orthomosaics Using Planetscope and Sentinel-2 DataIn recent years, the emergence of Unmanned Aerial Vehicles (UAV), also known as drones, with high spatial resolution, has broadened the application of remote sensing in agriculture. However, UAV images commonly have specific problems with missing areas due to drone flight restrictions. Data mining techniques for imputing missing data is an activity often demanded in several fields of science. In this context, this research used the same approach to predict missing parts on orthomosaics obtain... F.R. Pereira, A.A. Dos reis, R.G. Freitas, S.R. Oliveira, L.R. Amaral, G.K. Figueiredo, J.F. Antunes, R.A. Lamparelli, E. Moro, N.D. Pereira, P.S. Magalhães |
10. Identifying Key Factors Influencing Yield Spatial Pattern and Temporal Stability for Management Zone DelineationManagement zone delineation is a practical strategy for site-specific management. Numerous approaches have been used to identify these homogenous areas in the field, including approaches using multiple years of historical yield maps. However, there are still knowledge gaps in identifying variables influencing spatial and temporal variability of crop yield that should be used for management zone delineation. The objective of this study is to identify key soil and landscape properties affecting... L.N. Lacerda, Y. Miao, K. Mizuta, K. Stueve |
11. Strawberry Pest Detection Using Deep Learning and Automatic Imaging SystemStrawberry growers need to monitor pests to determine the options for pest management to reduce damage to yield and quality. However, manually counting strawberry pests using a hand lens is time-consuming and biased by the observer. Therefore, an automated rapid pest scouting method in the strawberry field can save time and improve counting consistency. This study utilized six cameras to take images of the strawberry leaf. Due to the relatively small size of the strawberry pest, six cam... C. Zhou, W. Lee, A. Pourreza, J.K. Schueller, O.E. Liburd, Y. Ampatzidis, G. Zuniga-ramirez |
12. A Bayesian Network Approach to Wheat Yield Prediction Using Topographic, Soil and Historical DataBayesian Network (BN) is the most popular approach for modeling in the agricultural domain. Many successful applications have been reported for crop yield prediction, weed infestation, and crop diseases. BN uses probabilistic relationships between variables of interest and in combination with statistical techniques the data modeling has many advantages. The main advantages are that the relationships between variables can be learned using the model as well as the potential to deal with missing... M. Karampoiki, L. Todman, S. Mahmood, A. Murdoch, D. Paraforos, J. Hammond, E. Ranieri |
13. Automated Lag Phase Detection in Wine GrapesCrop yield estimation, an important managerial tool for vineyard managers, plays a crucial role in planning pre/post-harvest operations to achieve desired yield and improve efficiency of various field operations. Although various technological approaches have been developed in the past for automated yield estimation in wine grapes, challenges such as cost and complexity of the technology, need of higher technical expertise for their operation and insufficient accuracy have caused major concer... P. Upadhyaya, M. Karkee, X. Zhang, S. Kashetri |
14. Supervised Feature Selection and Clustering for Equine Activity RecognitionIn this paper we introduce a novel supervised algorithm for equine activity recognition based on accelerometer data. By combining an approach of calculating a wide variety of time-series features with a supervised feature significance test we can obtain the best suited features using just 5 labeled samples per class and without requiring any expert domain knowledge. By using a simple cluster assignment algorithm with these obtained features, we get a classification algorithm that achieves a m... T. De waele, D. Peralta, A. Shahid, E. De poorter |
15. Increasing Precision Irrigation Efficacy for Row Crop Agriculture Through the Use of Artificial IntelligenceThe agricultural sector is the largest consumer of the world’s available fresh water resources. With fresh water scarcity increasing worldwide, more efficient use for irrigation water is necessary. Precision irrigation is described as the application of water to meet crop needs of a specific area, at the right amount and at the time that is optimum for crop health and management objectives. Irrigation becomes increasingly efficient through the use of precision irrigation tools. Howe... E. Bedwell |