Stereo vision controlled variable rate sprayer for specialty crops: Part II. Sprayer development and performance evaluation

Authors: ROMAN, CARLA - The Ohio State University; Jeon, Hongyoung; Zhu, Heping; CAMPOS, JAVIER - The Ohio State University; OZKAN, ERDAL - The Ohio State University

Submitted to: Journal of the ASABE
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/1/2023
Publication Date: 9/1/2023
Citation: Roman, C., Jeon, H., Zhu, H., Campos, J., Ozkan, E. 2023. Stereo vision controlled variable rate sprayer for specialty crops: Part II. Sprayer development and performance evaluation. Journal of the ASABE. 66(5): 1005-1017. https://doi.org/10.13031/ja.15578.
DOI: https://doi.org/10.13031/ja.15578

Interpretive Summary: Stereo vision has great potential to transition agricultural applications to data-driven systems as it can acquire image data along with 3-dimentional(D) data simultaneously. A real time variable rate sprayer using stereo vision as its target detection sensor was developed and tested for performance in an apple orchard. The variable rate sprayer adjusted its spray outputs 10 times per second to recognized tree canopies while determining spray volumes every 200 ms. The performance of the variable rate sprayer was compared to a conventional sprayer for spray accuracy, uniformity, and volume. The outcomes from this research highlight advantages of variable rate spray applications and demonstrate the potential of stereo vision applications. Furthermore, research outcomes demonstrate the potential of stereo vision-based agricultural research and applications which expedite development of decision support systems using stereo vision data for US growers.

Technical Abstract: A real time variable rate sprayer controlled by stereo vision was developed to increase spray application accuracy and reduce the use of crop protection products. The sprayer was designed to detect tree canopy and calculate its volume using depth images from the stereo vision and discharge corresponding spray volumes every 200 ms through the embedded software in the graphical user interface. The sprayer was evaluated in an apple orchard at different travel speeds (3.2 to 8.0 km h-1) for its performance in detecting canopy and measuring its volume. In addition, spray volume, deposition and coverage of the variable rate application of the sprayer were evaluated against a constant rate spray application. Test results showed that the sprayer detected visually similar tree canopy during the evaluation although its canopy volume measurements were deviated from manually measured canopy volume from 0.11 to 0.83 m3 due to lateral position changes of the sprayer. The sprayer controlled duty cycles of pulse width modulated valves to spray intended volume accurately for detected canopy (0.073 to 0.083 L m-3) and only used the spray volumes of 19.5% to 26.7% compared to conventional constant rate spray application (338 L ha-1). The conventional spray application generally had more spray deposition and coverage in tree canopy than the variable rate sprayer as expected since its spray volume was approximately 3.7 times higher. However, the conventional spray application had statistically different deposition means (p=0.05) by tree sizes though the depositions of the variable rate spray application were statistically the same regardless of tree sizes. The stereo vision controlled sprayer offers a cost-effective real-time variable rate spray option for growers with the potentials of performing other tasks by using image process algorithms while applying crop protection products.