Full TGIF Record # 333544
Item 1 of 1
Web URL(s):https://scisoc.confex.com/scisoc/2023am/meetingapp.cgi/Paper/152514
    Last checked: 12/07/2023
Publication Type:
i
Report
Content Type:Abstract or Summary only
Author(s):Petelewicz, Pawel; Zhou, Qiyu; Schiavon, Marco; Schumann, Arnold; Boyd, Nathan S.
Author Affiliation:Petelewicz: Presenting Author and Agronomy, University of Florida, Gainesville, FL; Zhou: North Carolina State University, Raleigh, NC; Schiavon: Environmental Horticulture, University of Florida, Davie, FL; Schumann: Citrus Research and Education Center, University of Florida, Lake Alfred, FL; Boyd: Gulf Coast Research and Education Center, University of Florida, Wimauma, FL
Title:Simulation-based nozzle density optimization for maximized efficacy of a machine-vision weed control system for applications in turfgrass settings
Section:Turf pest management poster: diseases, insects, weeds II
Other records with the "Turf pest management poster: diseases, insects, weeds II" Section

C05 turfgrass science
Other records with the "C05 turfgrass science" Section

521
Other records with the "521" Section
Meeting Info.:St. Louis, Missouri: October 29-November 1, 2023
Source:ASA, CSSA, SSSA International Annual Meeting. 2023, p. 152514.
Publishing Information:[Madison, Wisconsin]: [American Society of Agronomy, Crop Science Society of America, and Soil Science Society of America]
# of Pages:1
Abstract/Contents:"Precise spray application technologies have the capacity to drastically reduce herbicide inputs. To be successful we need to optimize the performance of both the machine vision (MV) based weed detection and actuator efficiency. This study assessed 1) the performance of spotted spurge [Chamaesyce maculata (L.) Small] recognition in 'Latitude 36' bermudagrass (Cynodon spp.) turf canopy using the You Only Look Once (YOLOv3) 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 YOLOv3 model was trained and validated with a dataset of 1,191 images. The simulation design consisted of 4 grid matrix regimes (3 Œ 3, 6 Œ 6, 12 Œ 12, and 24 Œ 24) demonstrating respectively: 3, 6, 12, and 24 non-overlapping nozzles covering the 50 cm band width. Simulated efficiency testing was conducted using 50 images containing predictions (labels) generated with the newly trained YOLO model and, by applying each of the grid matrixes to individual images and manually collecting efficacy data. Our model resulted in prediction accuracy as indicated by the F1 Score of 0.62 precision of 0.65 and recall value of 0.60. Increase in nozzle density provided improved actuators precision along with higher predicted herbicide use efficiency. There was no statistically significant difference between 24- and 12-nozzle scenario; thus, the optimal actuators efficacy and herbicide savings (>80%) would occur by increasing nozzle density from standard 1 covering 50-cm band to 12 (providing ~5% false hits ratio, 18% area under simulated application)."
Language:English
References:0
See Also:See also related item "Simulation-based nozzel density optimization for maximized efficacy of a machine vision-based weed control system for applications in turfgrass settings" Weed Technology, 38(1) January/February 2024, p. [1-9], R=337896. R=337896

See also related item "Simulation-based nozzle density optimization for maximized efficacy of machine-vision based weed control system for applications in turfgrass settings" Proceedings of the Southern Weed Science Society 76th Annual Meeting, Vol. 76, p. 185, R=333863. R=333863

See also related item "Database development workflow and comparison of different annotation methods for weed detection in turfgrass systems" Weed Science Society of America - Southern Weed Science Society Joint Meeting, 2024, p. 205-206, R=336048. R=336048
Note:This item is an abstract only!
ASA/CSSA/SSSA Citation (Crop Science-Like - may be incomplete):
Petelewicz, P., Q. Zhou, M. Schiavon, A. Schumann, and N. S. Boyd. 2023. Simulation-based nozzle density optimization for maximized efficacy of a machine-vision weed control system for applications in turfgrass settings. Agron. Abr. p. 152514.
Fastlink to access this record outside TGIF: https://tic.msu.edu/tgif/flink?recno=333544
If there are problems with this record, send us feedback about record 333544.
Choices for finding the above item:
Web URL(s):
https://scisoc.confex.com/scisoc/2023am/meetingapp.cgi/Paper/152514
    Last checked: 12/07/2023
Request through your local library's inter-library loan service (bring or send a copy of this TGIF record)