No abstract

Corn (Zea mays L.) is one of the most sensitive crops to planting pattern and early-season uniformity. The most common method to determine number of plants is by visual inspection on the ground but this field activity becomes time-consuming, labor-intensive, biased, and may lead to less profitable decisions by farmers. The objective of this study was to develop a reliable, timely, and unbiased method for counting corn plants based on ultra-high-resolution imagery acquired from unmanned aerial systems (UAS) to automatically scout fields and applied to real field conditions. A ground sampling distance of 2.4 mm was targeted to extract information at a plant-level basis. First, an excess greenness (ExG) index was used to individualized green pixels from the background, then rows and inter-row contours were identified and extracted. A scalable training procedure was implemented using geometric descriptors as inputs of the classifier. Second, a decision tree was implemented and tested using two training modes in each site to expose the workflow to different ground conditions at the time of the aerial data acquisition. Differences in performance were due to training modes and spatial resolutions in the two sites. For an object classification task, an overall accuracy of 0.96, based on the proportion of corrected assessment of corn and non-corn objects, was obtained for local (per-site) classification, and an accuracy of 0.93 was obtained for the combined training modes. For successful model implementation, plants should have between two to three leaves when images are collected (avoiding overlapping between plants). Best workflow performance was reached at 2.4 mm resolution corresponding to 10 m of altitude (lower altitude); higher altitudes were gradually penalized. The latter was coincident with the larger number of detected green objects in the images and the effectiveness of geometry as descriptor for corn plant detection.

No abstract

Abstract. Precision agriculture (PA) has been commercially available for decades, however only specific technologies have been readily adopted. The overall goal of this study was to provide information of the historical changes (from 2000 to 2016), current status of PA utilization, and sales expectations in the next time period. Within this overarching objective, specific goals included 1) determining the specific technologies that farmers adopt and 2) estimating the probability of transitioning from one bundle of PA technologies to another. The three information-intensive technologies included: 1) yield monitor (YM) with or without GNSS 2) variable rate (VR) application of inputs, and 3) precision soil sampling (PSS). Combinations of these three technologies in addition to a possible “no technology adopted” response resulted in eight categories of PA technology bundles. Each year, farms were classified as having one of these eight possible bundles of PA technology. Adoption of PA technologies has increased over time, with the use of only YMs and the bundle of all three PA technologies (YM, PSS, and VR) as the two primary bundles being adopted. When only VR was adopted, there was a 47% probability that the farm would add a YM by next year. When a farm used YM, VR, and PSS, there was a 99% probability that a farm would continue using the bundle in the following year. The results are useful for farmers, extension professionals, and policymakers to understand prior adoption paths for bundles of PA technology. Future steps can connect this database on adoption of PA technology with farm meta-descriptors such as acreage, type of crop, rotation, other relevant management practices, and financial variables so to better understand how farmers are integrating technologies into their farming operations. Keywords: Adoption, Information-intensive, Markov chain, Precision agriculture, Sequential, Site specific, Soil sampling, Transition probability, Variable rate, Yield monitor.

, "Spatio-temporal evaluation of plant height in corn via unmanned aerial systems," J. Appl. Remote Sens. 11(3), 036013 (2017), doi: 10.1117/1.JRS.11.036013. Abstract. Detailed spatial and temporal data on plant growth are critical to guide crop management. Conventional methods to determine field plant traits are intensive, time-consuming, expensive, and limited to small areas. The objective of this study was to examine the integration of data collected via unmanned aerial systems (UAS) at critical corn (Zea mays L.) developmental stages for plant height and its relation to plant biomass. The main steps followed in this research were (1) workflow development for an ultrahigh resolution crop surface model (CSM) with the goal of determining plant height (CSM-estimated plant height) using data gathered from the UAS missions; (2) validation of CSM-estimated plant height with ground-truthing plant height (measured plant height); and (3) final estimation of plant biomass via integration of CSM-estimated plant height with ground-truthing stem diameter data. Results indicated a correlation between CSM-estimated plant height and ground-truthing plant height data at two weeks prior to flowering and at flowering stage, but high predictability at the later growth stage. Log-log analysis on the temporal data confirmed that these relationships are stable, presenting equal slopes for both crop stages evaluated. Concluding, data collected from low-altitude and with a low-cost sensor could be useful in estimating plant height. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.