| |
| Web URL(s): | https://www.swss.ws/wp-content/uploads/2023_SWSS_Proceedings_Final-002.pdf#page=265
Last checked: 01/05/2024
Requires: PDF Reader
Notes: Item is within a single large file |
|---|
| Publication Type:
| Report |
|---|
| Content Type: | Abstract or summary only |
|---|
| Author(s): | Petelewicz, P.;
Zhou, Q.;
Schiavon, M.;
Schumann, A. W.;
Boyd, N. |
|---|
| Author Affiliation: | Petelewicz: University of Florida, Gainesville, FL; Zhou: North Carolina State University, Raleigh, NC; Schiavon: University of Florida, Davie, FL; Schumann: University of Florida, Lake Alfred, FL; Boyd; University of Florida/Gulf Coast Research and Education Center, Balm, FL |
|---|
| Title: | Simulation-based nozzle density optimization for maximized efficacy of machine-vision based weed control system for applications in turfgrss settings |
|---|
| Section: | 2023 meeting abstract
Other records with the "2023 meeting abstract" Section
|
|---|
| Meeting Info.: | January 23-26, 2023 |
|---|
| Source: | Proceedings of the Southern Weed Science Society 76th Annual Meeting. Vol. 76, 2023, p. 185. |
|---|
| Publishing Information: | Baton Rouge, LA: Southern Weed Science Society |
|---|
| # of Pages: | 1 |
|---|
| Abstract/Contents: | "Precise application technologies have the capacity to drastically diminish herbicide inputs, thereby reduce their environmental burden. A key to the success using such systems requires the best possible performance of all its components including the machine vision (MV) based weed detection and spraying sections. This study assessed 1) the performance of spotted spurge [Chamaesyce maculata (L.) Small] recognition in 'Latitude 36' bermudagrass (Cynodon Rich.) turf canopy using You Only Look Once (YOLO) real-time multi-object detection algorithm, and 2) the impact of various nozzle densities on the model efficiency and projected herbicide savings under simulated conditions. The YOLO model was trained with a dataset of 710 images and evaluated on a dataset of 581 testing images. The simulation design consisted of 4 grid matrix regimes (3 Π3, 6 Π6, 12 Π12, and 24 Π24) demonstrating respectively: 3, 6, 12, and 24 non-overlapping nozzles with the same specifications, producing a perfect spray pattern, and equally distributed on the spraying boom to cover a total of 50 cm bandwidth within the same time interval. Simulated efficiency testing was conducted using 50 images containing predictions (labels) generated with newly trained YOLO model, by applying each of grid matrixes to individual images and manually collecting efficacy data. Our model resulted in exquisite accuracy. When subjected to simulation, the lowest nozzle density (3-nozzle scenario) resulted in the largest application area (41%) required to ensure herbicide deposition to all weeds detected within images, thus providing the lowest probable savings. As presumed, the least area required for satisfactory target weed coverage (13%), thereby greatest predicted herbicide use efficiency, was achieved with the highest simulated nozzle density (24-nozzle scenario). However, it was not different when compared to 12-nozzle scenario (18% area under simulated herbicide application). Considering various economic and logistic factors, the optimal savings would occur by increasing nozzle density from standard 1 covering 50-cm band to 12 assuming each individual nozzle covers approx. 5-cm band." |
|---|
| Language: | English |
|---|
| References: | 0 |
|---|
| See Also: | See also related item "Simulation-based nozzle density optimization for maximized efficacy of a machine-vision weed control system for applications in turfgrass settings" ASA, CSSA, SSSA International Annual Meeting, 2022, p. 152514, R=333544. R=333544 |
|---|
| Note: | This item is an abstract only! |
|---|
| ASA/CSSA/SSSA Citation (Crop Science-Like - may be incomplete):
Petelewicz, P., Q. Zhou, M. Schiavon, A. W. Schumann, and N. Boyd. 2023. Simulation-based nozzle density optimization for maximized efficacy of machine-vision based weed control system for applications in turfgrss settings. South. Weed Sci. Soc. Proc. 76:p. 185. |
| Fastlink to access this record outside TGIF: https://tic.lib.msu.edu/tgif/flink?recno=333863 |
| If there are problems with this record, send us feedback about record 333863. |
| Choices for finding the above item: |
|---|
| Web URL(s):
https://www.swss.ws/wp-content/uploads/2023_SWSS_Proceedings_Final-002.pdf#page=265
Last checked: 01/05/2024
Requires: PDF Reader
Notes: Item is within a single large file |
| 
MSU catalog number: b2207931 |
| Request through your local library's inter-library loan service (bring or send a copy of this TGIF record) |
