New directions in weed research and management using 3-D imaging

Authors: DOBBS, APRIL - North Carolina A&t State University; BAGAVATHIANNAN, MUTHUKUMAR - Texas A&M University; GINN, DANIEL - Texas A&M University; Mirsky, Steven; REBERG-HORTON, CHRIS - North Carolina State University; LEON, RAMON - North Carolina State University

Submitted to: Weed Science
Publication Type: Review Article
Publication Acceptance Date: 9/27/2022
Publication Date: 10/21/2022
Citation: Dobbs, A.M., Bagavathiannan, M.V., Ginn, D., Mirsky, S.B., Reberg-Horton, C.S., Leon, R.G. 2022. New directions in weed research and management using 3-D imaging. Weed Science. 70:641-647. https://doi.org/10.1017/wsc.2022.59.
DOI: https://doi.org/10.1017/wsc.2022.59

Interpretive Summary: Weed management and weed research could greatly benefit from three-dimensional (3-D) imaging technology, which would more effectively map weed populations in a field and support crop development studies than traditional two-dimensional (2-D) techniques. 2-D techniques don't accurately quantify plant size, biomass, or canopy structure due to the lack of depth information and other issues. This paper outlines a way to mitigate the challenges presented by 2-D techniques through the use of 3-D imaging captured by inexpensive and easily-available cameras. 3-D imaging will allow for accurate mapping of weeds in a field, allowing farmers to target and "spot spray" weeds rather than applying herbicides uniformly across a field. It will also allow farmers to recognize and remove weed escapes before they can add to the soil weed seed bank, slowing the development of herbicide resistance. As this technology continues its rapid evolution, it will provide simple, efficient, and low-cost tools for growers and researchers alike, expanding our knowledge about effective weed management strategies in our collective effort to protect crops, reduce herbicide use, slow the rate of herbicide resistance evolution, and improve environmental health.

Technical Abstract: Three-dimensional imaging technology offers great potential for weed management and weed research. Until now, most imaging techniques for mapping weed populations and crop development have used conventional 2-D methods. However, 2-D approaches fall short in quantifying plant size, biomass, and canopy structure because of lack of depth information, and vulnerability to occlusion, shadows, overlap, and variations in light. To mitigate these challenges, 3-D imaging techniques are being developed to create accurate 3-D plant models from point clouds generated from RGB images, which can be obtained using inexpensive commercially-available cameras. Three-dimensional imaging will allow growers to create spatio-temporal maps of weed populations in the field and target weed patches for site-specific weed management, including automated precision weed control. This technology will also help growers monitor cover crop performance for weed suppression and detect late-season weed escapes for timely control, thereby reducing seed bank persistence and slowing the evolution of herbicide resistance. In addition to its many applications in weed management, 3-D imaging has great potential for weed research, from understanding weed-crop competition, to modeling weed community dynamics. As this technology continues its rapid evolution, it will provide simple, efficient, and low-cost tools for growers and researchers alike and expand our knowledge about effective weed management strategies in our collective effort to protect crops, reduce herbicide use, slow the rate of herbicide resistance evolution, and improve environmental health.