(a) (b) (c)
Figure 3. Experiment on a sample image: (a) a screenshot of the open-source software IMAP that demonstrates vegetation segmentation in a rotated grid, (b) output metrics exported to a csv file, (c) a graph displaying metrics of 280 plots.
CONCLUSIONS
Adaptive griding algorithm was developed and successfully implemented on a sample field image by using geometry of a rectangle in a circle. Plot-level metrics was extracted by georeferencing pixels only within a ROI. Grid rotation and metrics extraction were interfaced graphically for user-friendly operations. The open-source software with adaptive gridding is publicly available [4] and allows the end-users to process their UAS images for high throughput phenotyping in an effective manner without knowledge of image processing. This new gridding method can be also extended to other types of images from ground and satellite platforms that contain multiple plots in various orientations.
ACKNOWLEDGMENTS
This research was funded by the U.S. Department of Agriculture, Agricultural Research Service under project numbers 6066-13000-005-00D and 3060-21000-044-00D.