Mardanisamani Sara, Ayalew Tewodros W, Badhon Minhajul Arifin, Khan Nazifa Azam, Hasnat Gazi, Duddu Hema, Shirtliffe Steve, Vail Sally, Stavness Ian, Eramian Mark
Department of Computer Science, University of Saskatchewan, Saskatoon, Saskatchewan, Canada.
Department of Plant Sciences, University of Saskatchewan, Saskatoon, Saskatchewan, Canada.
Plant Phenomics. 2021 Dec 8;2021:9764514. doi: 10.34133/2021/9764514. eCollection 2021.
To develop new crop varieties and monitor plant growth, health, and traits, automated analysis of aerial crop images is an attractive alternative to time-consuming manual inspection. To perform per-microplot phenotypic analysis, localizing and detecting individual microplots in an orthomosaic image of a field are major steps. Our algorithm uses an automatic initialization of the known field layout over the orthomosaic images in roughly the right position. Since the orthomosaic images are stitched from a large number of smaller images, there can be distortion causing microplot rows not to be entirely straight and the automatic initialization to not correctly position every microplot. To overcome this, we have developed a three-level hierarchical optimization method. First, the initial bounding box position is optimized using an objective function that maximizes the level of vegetation inside the area. Then, columns of microplots are repositioned, constrained by their expected spacing. Finally, the position of microplots is adjusted individually using an objective function that simultaneously maximizes the area of the microplot overlapping vegetation, minimizes spacing variance between microplots, and maximizes each microplot's alignment relative to other microplots in the same row and column. The orthomosaics used in this study were obtained from multiple dates of canola and wheat breeding trials. The algorithm was able to detect 99.7% of microplots for canola and 99% for wheat. The automatically segmented microplots were compared to ground truth segmentations, resulting in an average DSC of 91.2% and 89.6% across all microplots and orthomosaics in the canola and wheat datasets.
为了培育新的作物品种并监测植物生长、健康状况和性状，对航空作物图像进行自动分析是一种有吸引力的替代方法，可以取代耗时的人工检查。为了进行每微区表型分析，在田间正射镶嵌图像中定位和检测单个微区是主要步骤。我们的算法在正射镶嵌图像上大致正确的位置自动初始化已知的田间布局。由于正射镶嵌图像是由大量较小的图像拼接而成的，可能会存在失真，导致微区行不完全笔直，并且自动初始化不能正确定位每个微区。为了克服这个问题，我们开发了一种三级分层优化方法。首先，使用一个目标函数优化初始边界框位置，该目标函数使区域内的植被水平最大化。然后，在预期间距的约束下重新定位微区列。最后，使用一个目标函数单独调整微区的位置，该目标函数同时最大化微区与植被重叠的面积，最小化微区之间的间距方差，并最大化每个微区相对于同一行和列中其他微区的对齐度。本研究中使用的正射镶嵌图像来自油菜和小麦育种试验的多个日期。该算法能够检测出99.7%的油菜微区和99%的小麦微区。将自动分割的微区与地面真值分割进行比较，在油菜和小麦数据集中，所有微区和正射镶嵌图像的平均DSC分别为91.2%和89.6%。
