Continuing population growth will result in increasing global demand for food and fiber for the foreseeable future. During the growing season, variability in the height of crops provides important information on plant health, growth, and response to environmental effects. This paper indicates the feasibility of using structure from motion (SfM) on images collected from 120 m above ground level (AGL) with a fixed-wing unmanned aerial vehicle (UAV) to estimate sorghum plant height with reasonable accuracy on a relatively large farm field. Correlations between UAV-based estimates and ground truth were strong on all dates (R² > 0.80) but are clearly better on some dates than others. Furthermore, a new method for improving UAV-based plant height estimates with multi-level ground control points (GCPs) was found to lower the root mean square error (RMSE) by about 20%. These results indicate that GCP-based height calibration has a potential for future application where accuracy is particularly important. Lastly, the image blur appeared to have a significant impact on the accuracy of plant height estimation. A strong correlation (R² = 0.85) was observed between image quality and plant height RMSE and the influence of wind was a challenge in obtaining high-quality plant height data. A strong relationship (R² = 0.99) existed between wind speed and image blurriness.

Cotton root rot (CRR) is a persistent soilborne fungal disease that is devastating to cotton in the southwestern U.S. and Mexico. Research has shown that CRR can be prevented or at least mitigated by applying a fungicide at planting, but the fungicide should be applied precisely to minimize the quantity of product used and the treatment cost. The CRR-infested areas within a field are consistent from year to year, so it is possible to apply the fungicide only at locations where CRR is manifest, thus minimizing the amount of fungicide applied across the field. Previous studies have shown that remote sensing (RS) from manned aircraft is an effective means of delineating CRR-infested field areas. Applying various classification methods to moderate-resolution (1.0 m/pixel) RS images has recently become the conventional way to delineate CRR-infested areas. In this research, an unmanned aerial vehicle (UAV) was used to collect high-resolution remote sensing (RS) images in three Texas fields known to be infested with CRR. Supervised, unsupervised, and combined unsupervised classification methods were evaluated for differentiating CRR from healthy zones of cotton plants. Two new automated classification methods that take advantage of the high resolution inherent in UAV RS images were also evaluated. The results indicated that the new automated methods were up to 8.89% better than conventional classification methods in overall accuracy. One of these new methods, an automated method combining k-means segmentation and morphological opening and closing, provided the best results, with overall accuracy of 88.5% and the lowest errors of omission (11.44%) and commission (16.13%) of all methods considered.

Recent computer vision techniques based on convolutional neural networks (CNNs) are considered state-of-the-art tools in weed mapping. However, their performance has been shown to be sensitive to image quality degradation. Variation in lighting conditions adds another level of complexity to weed mapping. We focus on determining the influence of image quality and light consistency on the performance of CNNs in weed mapping by simulating the image formation pipeline. Faster Region-based CNN (R-CNN) and Mask R-CNN were used as CNN examples for object detection and instance segmentation, respectively, while semantic segmentation was represented by Deeplab-v3. The degradations simulated in this study included resolution reduction, overexposure, Gaussian blur, motion blur, and noise. The results showed that the CNN performance was most impacted by resolution, regardless of plant size. When the training and testing images had the same quality, Faster R-CNN and Mask R-CNN were moderately tolerant to low levels of overexposure, Gaussian blur, motion blur, and noise. Deeplab-v3, on the other hand, tolerated overexposure, motion blur, and noise at all tested levels. In most cases, quality inconsistency between the training and testing images reduced CNN performance. However, CNN models trained on low-quality images were more tolerant against quality inconsistency than those trained by high-quality images. Light inconsistency also reduced CNN performance. Increasing the diversity of lighting conditions in the training images may alleviate the performance reduction but does not provide the same benefit from the number increase of images with the same lighting condition. These results provide insights into the impact of image quality and light consistency on CNN performance. The quality threshold established in this study can be used to guide the selection of camera parameters in future weed mapping applications.

Cotton root rot (CRR), caused by the fungus Phymatotrichopsis omnivora, is a destructive cotton disease that mainly affects the crop in Texas. Flutriafol fungicide applied at or soon after planting has been proven effective at protecting cotton plants from being infected by CRR. Previous research has indicated that CRR will reoccur in the same regions of a field as in past years. CRR-infected plants can be detected with aerial remote sensing (RS). As unmanned aerial vehicles (UAVs) have been introduced into agricultural RS, the spatial resolution of farm images has increased significantly, making plant-by-plant (PBP) CRR classification possible. An unsupervised classification algorithm, PBP, based on the Superpixel concept, was developed to delineate CRR-infested areas at roughly the single-plant level. Five-band multispectral data were collected with a UAV to test these methods. The results indicated that the single-plant level classification achieved overall accuracy as high as 95.94%. Compared to regional classifications, PBP classification performed better in overall accuracy, kappa coefficient, errors of commission, and errors of omission. The single-plant fungicide application was also effective in preventing CRR.

Images captured from airborne imaging systems can be mosaicked for diverse remote sensing applications. The objective of this study was to identify appropriate mosaicking techniques and software to generate mosaicked images for use by aerial applicators and other users. Three software packages—Photoshop CC, Autostitch, and Pix4Dmapper—were selected for mosaicking airborne images acquired from a large cropping area. Ground control points were collected for georeferencing the mosaicked images and for evaluating the accuracy of eight mosaicking techniques. Analysis and accuracy assessment showed that Pix4Dmapper can be the first choice if georeferenced imagery with high accuracy is required. The spherical method in Photoshop CC can be an alternative for cost considerations, and Autostitch can be used to quickly mosaic images with reduced spatial resolution. The results also showed that the accuracy of image mosaicking techniques could be greatly affected by the size of the imaging area or the number of the images and that the accuracy would be higher for a small area than for a large area. The results from this study will provide useful information for the selection of image mosaicking software and techniques for aerial applicators and other users.