| |
| Web URL(s): | https://wssa.net/wp-content/uploads/ilovepdf_merged-26.pdf#page=27
Last checked: 04/19/2024
Requires: PDF Reader
Notes: Item is within a single large file |
|---|
| Publication Type:
| Report |
|---|
| Content Type: | Abstract or summary only |
|---|
| Author(s): | Gurjar, Bholuram;
Torres, Ubaldo;
Bagavathiannan, Muthukumar V.;
Straw, Chase |
|---|
| Author Affiliation: | Gurjar, Torres, and Bagavathiannan: Texas A&M University, College Station, TX; Straw: Texas A&M, College Station, TX |
|---|
| Title: | A machine learning framework for the detection and localization of annual bluegrass (Poa annua) in bermudagrass turf |
|---|
| Section: | WSSA/SWSS student competition posters
Other records with the "WSSA/SWSS student competition posters" Section
|
|---|
| Meeting Info.: | San Antonio, Texas: January 22 - 25, 2024 |
|---|
| Source: | Weed Science Society of America - Southern Weed Science Society Joint Meeting. 2024, p. 23. |
|---|
| Publishing Information: | [United States]: Weed Science Society of America |
|---|
| # of Pages: | 1 |
|---|
| Abstract/Contents: | "Annual bluegrass (Poa annua) is an extremely problematic weed in US turf systems, posing a significant challenge for turfgrass management. Herbicide application is the most popular and economically viable option among other weed control methods in turf systems. However, the widespread use of blanket herbicide applications has harmful effects on the environment, as well as off-target movement of herbicides, reducing the aesthetic look of turfgrass. Additionally, the prolonged use of the same mode of herbicides leads to the development of resistant biotypes. Research on weed detection and site-specific weed management (SSWM) is limited for annual bluegrass, a major weed in turfgrass. To enable precision herbicide applications to annual bluegrass plants we developed a machine learning-based framework for weed detection and localization of this weed present in turfgrass. Drone-based RGB imagery was collected at different growth stages of annual bluegrass in Deer Park, Texas, with the specific objective of developing an annual bluegrass recognition and localization algorithm. The You Only Look Once (YOLO) machine learning model was used for annual bluegrass detection. We compared 12 different architecture variants from YOLO v5, v7, and v8 on lowresolution drone images. The results showed that the YOLOv7-w6 model had the highest detection accuracy (78%), followed by the YOLOv5l model (68%), and the YOLOv8l model (66%). After successfully detecting weeds in the orthophoto, a geotransformation function was developed to map the location of the weeds in the field based on the detected weeds in the image. The output file format of the geotransformation function is a shape file that could be used for site-specific herbicide applications using drones, robots, and GNSS-guided boom sprayers to manage individual weed plants in turfgrass. The accuracy of the weed coordinates depends on the accuracy of the orthophoto georeferencing, with longitude and latitude errors determined to be 5.31 cm and 3.74 cm, respectively. However, this error could be minimized using imagery collected with an RTK-mounted drone. Future developments will include real-time weed detection, site-specific spraying, and testing the model's robustness at different growth stages and with various turf species." |
|---|
| Language: | English |
|---|
| References: | 0 |
|---|
| See Also: | Original verison appears in ASA, CSSA, SSSA International Annual Meeting, 2023, p. 151207, with variant title "Developing a machine-learning based weed detection and localization framework for precision herbicide applications in turf", R=333566. R=333566 |
|---|
| Note: | This item is an abstract only! |
|---|
| ASA/CSSA/SSSA Citation (Crop Science-Like - may be incomplete):
Gurjar, B., U. Torres, M. V. Bagavathiannan, and C. Straw. 2024. A machine learning framework for the detection and localization of annual bluegrass (Poa annua) in bermudagrass turf. Abstr. Annu. Meet. Weed Sci. Soc. Am. p. 23. |
| Fastlink to access this record outside TGIF: https://tic.lib.msu.edu/tgif/flink?recno=336047 |
| If there are problems with this record, send us feedback about record 336047. |
| Choices for finding the above item: |
|---|
| Web URL(s):
https://wssa.net/wp-content/uploads/ilovepdf_merged-26.pdf#page=27
Last checked: 04/19/2024
Requires: PDF Reader
Notes: Item is within a single large file |
| 
MSU catalog number: b2180085 |
| Request through your local library's inter-library loan service (bring or send a copy of this TGIF record) |
