| dc.contributor.author | Sapkota, Ranjan | |
| dc.description.abstract | Currently, a blanket application of herbicides across the field without considering the spatial distribution of weeds is the most used method to control weeds in corn. Unmanned aerial systems (UASs) can provide high spatial resolution imagery, which can be used to map weeds across a field with a high spatial and temporal resolution during early growing season to support site-specific weed control (SSWC). The proposed approach assumes that plants growing outside the corn rows are weeds that need to be controlled. For that, we are proposing the use of “Pixel Intensity Projection” (PIP) algorithm for the detection of corn rows on UAS imagery. After being identified, corn rows were then removed from the imagery and the remaining vegetation fraction was assumed to be weeds. A weed prescription map based on the remaining vegetation fraction was created and implemented through a commercial sprayer field weed control. | en_US |
| dc.publisher | North Dakota State University | en_US |
| dc.rights | NDSU policy 190.6.2 | en_US |
| dc.title | Using UAS Imagery and Computer Vision to Support Site-Specific Weed Control in Corn | en_US |
| dc.type | Thesis | en_US |
| dc.date.accessioned | 2023-12-20T19:03:46Z | |
| dc.date.available | 2023-12-20T19:03:46Z | |
| dc.date.issued | 2022 | |
| dc.identifier.uri | https://hdl.handle.net/10365/33405 | |
| dc.rights.uri | https://www.ndsu.edu/fileadmin/policy/190.pdf | en_US |
| ndsu.degree | Master of Science (MS) | en_US |
| ndsu.college | Engineering | en_US |
| ndsu.department | Agricultural and Biosystems Engineering | en_US |
| ndsu.program | Agricultural and Biosystems Engineering | en_US |
| ndsu.advisor | Flores, Paulo | |
