Authors
| Filter results6 paper(s) found. |
|---|
1. A Comparison of Three-Dimensional Data Acquisition Methods for Phenotyping ApplicationsCurrently Phenotyping is primarily performed using two-dimensional imaging techniques. While this yields interesting data about a plant, a lot of information is lost using regular cameras. Since a plant is three-dimensional, the use of dedicated 3D-imaging sensors provides a much more complete insight into the phenotype of the plant. Different methods for 3D-data acquisition are available, each with their inherent advantages and disadvantages. These have to be addressed depending on the particular... O. Scholz, F. Uhrmann, S. Gerth, K. Pieger, J. Claußen |
2. Seed Localization System Suite with CNNs for Seed Spacing Estimation, Population Estimation and DoublesProper seed placement during planting is critical to achieve uniform emergence which optimizes the crop for maximum yield potential. Currently, the ideal way to determine planter performance is to manually measure plant spacing and seeding depth. However, this process is both cost- and labor-intensive and prone to human errors. Therefore, this study aimed to develop seed localization system (SLS) system to measure seed spacing and seeding depth and providing the geo-location of each planted seed.... A. Sharda, R. Harsha chepally |
3. Creating a Comprehensive Software Framework for Sensor-driven Precision AgricultureRobots and GPS-guided tractors are the backbone of smart farming and precision agriculture. Many companies and vendors contribute to the market, each offering their own customized solutions for common tasks. These developments are often based on vendor-specific, proprietary components, protocols and software. Many small companies that produce sensors, actuators or software for niche applications could contribute their expertise to the global efforts of creating smart farming solutions, if their... O. Scholz, F. Uhrmann, M. Weule, T. Meyer, A. Gilson, J. Makarov, J. Hansen, T. Henties |
4. Real-time Seed Mapping Using Direct MethodsSeed distance estimations are critical for planter evaluation and the prediction of planting parameter performance. However, these estimations are typically not conducted in real-time. In this study, we propose a real-time seed mapping approach using cameras and computer vision networks, augmented by a Kalman filter for vehicle state estimation. This process involves the transformation of pixel coordinates into real-world coordinates. We conduct a comparative analysis between these estimates and... A. Sharda, R. Harsha chepally |
5. Design and Development of a Spraying System for Under Canopy Rover and Its Integration with Computer Vision SystemChemical spraying such as herbicides, insecticides are essential in any agricultural field for controlling pest, weed etc. and ultimately increasing yield. About one-third of agricultural yields rely on the utilization of pesticides. However, around 3 billion kilograms of pesticides are used worldwide every year and effective utilization of it is merely 1%. The precise application of these chemicals is necessary to reduce negative impacts on environment as well as human health. The application... N.K. Piya, A. Sharda, J.R. Persch, D. Flippo, R. Harsha chepally |
6. Real Time Application of Neural Networks and Hardware Accelerated Image Processing Pipeline for Precise Autonomous Agricultural SystemsModern agriculture is increasingly turning to automation and precision technology to optimize crop management. In this context, our research addresses the development of an autonomous pesticide spraying rover equipped with advanced technology for precision agriculture. The primary goal is to use a neural network for real-time aphid detection in Sorghum crops, enabling targeted pesticide application only to infested plants. To accomplish this, we've integrated cutting-edge technologies and... J. Raitz persch, R. Harsha chepally, N.K. Piya |