Creating Predictive Weed Emergence Models Using Repeat Photography and Image Analysis
Open Access
- 15 May 2020
- Vol. 9 (5), 635
- https://doi.org/10.3390/plants9050635
Abstract
Weed emergence models have the potential to be important tools for automating weed control actions; however, producing the necessary data (e.g., seedling counts) is time consuming and tedious. If similar weed emergence models could be created by deriving emergence data from images rather than physical counts, the amount of generated data could be increased to create more robust models. In this research, repeat RGB images taken throughout the emergence period of Raphanus raphanistrum L. and Senna obtusifolia (L.) Irwin and Barneby underwent pixel-based spectral classification. Relative cumulative pixels generated by the weed of interest over time were used to model emergence patterns. The models that were derived from cumulative pixel data were validated with the relative emergence of true seedling counts. The cumulative pixel model for R. raphanistrum and S. obtusifolia accounted for 92% of the variation in relative emergence of true counts. The results demonstrate that a simple image analysis approach based on time-dependent changes in weed cover can be used to generate weed emergence predictive models equivalent to those produced based on seedling counts. This process will help researchers working on weed emergence models, providing a new low-cost and technologically simple tool for data collection.Keywords
Funding Information
- Economic Research Service (2017-6505-26807, 2018-70006-28933, 2019-68012-29818)
This publication has 23 references indexed in Scilit:
- Remote detection of invasive plants: a review of spectral, textural and phenological approachesBiological Invasions, 2013
- Regional‐scale phenology modeling based on meteorological records and remote sensing observationsPublished by American Geophysical Union (AGU) ,2012
- Color Thresholding Method for Image Segmentation of Natural ImagesInternational Journal of Image, Graphics and Signal Processing(ijigsp), 2012
- Using digital repeat photography and eddy covariance data to model grassland phenology and photosynthetic CO2 uptakeAgricultural and Forest Meteorology, 2011
- Predicting weed emergence for eight annual species in the northeastern United StatesWeed Science, 2004
- A Review on Remote Sensing of Weeds in AgriculturePrecision Agriculture, 2004
- A mechanistic growth and development model of common ragweedWeed Science, 2001
- Modeling seedling emergenceField Crops Research, 2000
- WEED DETECTION USING COLOR MACHINE VISIONTransactions of the ASAE, 2000
- Colour vision: Putting it in contextCurrent Biology, 1996