Proceedings
Authors
| Filter results4 paper(s) found. |
|---|
1. Variability in Soil Water Content and Sensor-Based Irrigation Scheduling for Protected Ginseng ProductionGinseng is one of important medicinal plants, especially in Asian countries including Korea. Korean ginseng is mostly grown in sun-block facility on ridges, and irrigation would be critical for better production. Conventionally no irrigation or timer-controlled irrigation based on experience was practiced, and variability of... J. Cho, B. Cho, S. Chung |
2. Seasonal Patterns of Vegetative Indices Over Cropping SystemsRemote sensing of reflectance in the visible and near-infrared portions of the spectrum has been used for agronomic applications for a number of years. The combination of different wavelengths into vegetative indices have proven useful for a variety of applications that range from biomass, leaf area, leaf chlorophyll, yield, crop residue, and crop damage. To help refine our understanding of vegetative indices studies were conducted on corn (Zea mays L.), soybean (Glycine max (L.) Merr.), wheat... J.L. Hatfield, J.H. Prueger |
3. Spatial Patterns of Nitrogen Response Within Corn Production FieldsCorn (Zea mays L.) yield response to nitrogen (N) application is critical to being able to develop management practices that reduce N application or improve N use efficiency. Nitrogen rate studies have been conducted within small plots; however, there have been few field scale evaluations. This study was designed to evaluate N response across 14 corn fields in central Iowa using different rates of N applied in strips across fields. These fields ranged in size from 15 to 130 ha with N... J.L. Hatfield |
4. Using Deep Learning - Convolutional Naural Networks (CNNS) for Real-Time Fruit Detection in the TreeImage/video processing for fruit detection in the tree using hard-coded feature extraction algorithms have shown high accuracy on fruit detection during recent years. While accurate, these approaches even with high-end hardware are still computationally intensive and too slow for real-time systems. This paper details the use of deep convolution neural networks architecture based on single-stage detectors. Using deep-learning techniques eliminates the need for hard-code specific features for specific... K. Bresilla, L. Manfrini, A. Boini, G. Perulli, B. Morandi, L.C. Grappadelli |