1. Automatic Detection and Segmentation of Lentil Crop Breeding Plots From Multi-Spectral Images Captured by UAV-Mounted Camera
- Author
-
Steve Shirtliffe, Mark Eramian, Ilya Ovsyannikov, Arafia Rumali, Kirstin E. Bett, Hema S. N. Duddu, Imran Ahmed, William van der Kamp, and Karsten Nielsen
- Subjects
Ground truth ,010504 meteorology & atmospheric sciences ,business.industry ,Computer science ,Pattern recognition ,02 engineering and technology ,Image segmentation ,Blob detection ,01 natural sciences ,Plot (graphics) ,Random walker algorithm ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Segmentation ,Artificial intelligence ,Precision and recall ,Cluster analysis ,business ,0105 earth and related environmental sciences - Abstract
Unmanned Aerial Vehicles (UAVs) paired with image detection and segmentation techniques can be used to extract plant phenotype information of individual breeding or research plots. Each plot contains plants of a single genetic line. Breeders are interested in selecting lines with preferred phenotypes (physical traits) that increase crop yield or resilience. Automated detection and segmentation of plots would enable automatic monitoring and quantification of plot phenotypes, allowing a faster selection process that requires much fewer person-hours compared with manual assessment. A detection algorithm based on Laplacian of Gaussian (LoG) blob detection and a segmentation algorithm based on a combination of unsupervised clustering and random walker image segmentation are proposed to detect and segment lentil plots from multi-spectral aerial images. Our algorithm detects and segments lentil plots from normalized difference vegetative index (NDVI) images. The detection algorithm exhibited an average precision and recall of 96.3% and 97.2% respectively. The average Dice similarity coefficient between a detected segmented plot and its ground truth was 0.906.
- Published
- 2019
- Full Text
- View/download PDF