Plant density estimation during the emergence phase is critical for early-season decision making. Estimation of both crop and weed density is critical for addressing early season issues. Mapping of weeds in crops at any stage can be useful; however, early competition from weeds is frequently most detrimental to yield. The objectives of this study were to develop a set of algorithms that accurately estimated the crop and weed density at emergence from sUAS imagery, and to do so using methods which were operationally feasible on production-field scale. The areas of interest were Mississippi cotton fields, where weeds were present. The imagery was collected using the standard integrated camera on a DJI Phantom 4 Pro quadcopter. A Hough transform-based approach for density estimation of crop and weed was used. The detection process began by extracting all plants from the soil background based on visible atmospherically resistant index values, and further discriminated between crop and weed using Hough line transform, followed by connected component analysis. The algorithm development utilized five subsets of image data collected, where overall accuracy was 83%. The algorithm was applied to a different production cotton field in the following year. Overall accuracy remained the same; however, commission error was reduced. The addition of near infrared reflectance could improve accuracies as many errors were due to a lack of “greenness” in plants, which is the primary factor in assigning visible atmospherically resistant index values.
The hyperspectral remote sensor acquires hundreds of contiguous spectral images, resulting in large data that contain a significant amount of redundant information. This high-dimensional and redundant data always influence the efficiency of the data processing. Therefore, feature extraction becomes one of the critical tasks in hyperspectral image classification. A transform-domain-based feature extraction technique, three-dimensional discrete cosine transform (3-D DCT), is proposed. The reason behind the transform domains is that, generally, an invertible linear transform reconstructs the image data to provide the independent information about the spectra or more separable transformation coefficients. Moreover, DCT has excellent energy compaction properties for highly correlated images, such as hyperspectral images, which reduces the complexity of the separation significantly. Unlike the discrete wavelet transform that requires sequential transform to obtain the approximation and detailed coefficients, DCT extracts all coefficients simultaneously. As a result, computation time in the feature extraction can be reduced. The experimental results on three benchmark datasets (Indian Pines, Pavia University, and Salinas) show that the proposed approach produces a good classification in terms of overall accuracy, average accuracy as well as Cohen’s kappa coefficient (κ) when compared with some traditional as well as transform-based feature extraction algorithms. Experimental result also shows that the proposed method requires less computational time than the transform-based feature extraction method.
Unmanned Aerial Systems (UASs) have been touted as being of great value for agriculture. However, they have not yet permeated the fabric of the agriculture research or agriculture production systems significantly. This paper seeks to explain why adoption is low relative to excitement and to provide some guidance on what is needed for UASs to be effective in agriculture research and agriculture production.
Band selection is an important unsolved challenge in hyperspectral image processing that has been used for
dimensionality reduction and classification improvement. To date, numerous researchers have investigated the
unsupervised selection of band groups using measures such as correlation and Kullback-Leibler divergence. However,
no clear winner has emerged across data sets and detection tasks. Herein, we investigate the utility of aggregating
different proximity measures for band group selection. Specifically, we employ the Choquet integral with respect to different measures (capacities) as it is able to yield a variety of aggregation functions like t-norms, t-conorms and
averaging operators. We explore the utility of aggregation in the context of single band, single band group, band group
dimensionality reduction and multiple band group combinations in conjunction with support vector machine (SVM)
based classification. Our preliminary experiments indicate there is value in aggregating different proximity measures. In some instances an intersection operator works well while in other cases a union operator is best. As may be expected,
this can, and does vary per detection task. We also see that depending on the difficulty of the target detection problem, different aggregation, band grouping and combination strategies prevail. Advantages of our approach include; flexibility,
the aggregation operator can be learned, and the method can default to a single proximity measure if needed and result, in the worst case, in no performance loss. Experiments are performed on three hyperspectral benchmark data sets to demonstrate the applicability of the proposed concepts.