Investigation of depth camera potentials for variable-rate sprayers

Authors: Jeon, Hongyoung; Zhu, Heping

Submitted to: American Society of Agricultural and Biological Engineers
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/13/2022
Publication Date: 2/21/2023
Citation: Jeon, H., Zhu, H. 2023. Investigation of depth camera potentials for variable-rate sprayers. American Society of Agricultural and Biological Engineers. 66(1):115-126. https://doi.org/10.13031/ja.15070.
DOI: https://doi.org/10.13031/ja.15070

Interpretive Summary: Using high quality and resolution of agronomic data in specialty crop production is critical for US growers to make sensible decisions to reduce their production inputs while maximizing the outputs from their production. However, current practice of collecting agronomic data such as plant size and growth data is mainly labor-intensive manual process due to lack of instrument availability. Low-cost stereo vision sensor was identified, and its performance was evaluated in collecting agronomic data such as canopy size and color data of specialty crops. This study outcomes showed the stereo vision sensor possessed great potential to collect forementioned data with reasonable acquisition rate (5 images per second) with reasonable measurement accuracy (2.8 % to 15.8% of measurement errors) under outdoor conditions. The information from this study will be useful for researchers and growers who need to collect forementioned data of specialty crops.

Technical Abstract: A commercial depth camera was tested as a mean of detecting the canopy of ornamental and tree crops. A custom-designed graphic user interface was developed to control the depth camera and save RGB and IR images and depth data to a local computer. Indoor evaluations showed that measurements could be influenced by the temperature and illumination; however, the influence was minimal because its relative error was less than 1% and the maximum variation between the average measurements was 14 mm. The depth camera was able to detect a target with its width as narrow as 20-mm with detection rates from 31% to 72%, and the rates went up 72% to 89% when the target width increased to 40 mm. The depth camera showed acceptable performance in detecting canopy contour changes and had measurement errors of 2.8% to 15.3% while detecting the distances to outdoor crabapple and oak trees. In addition, the depth camera detected canopy in various outdoor conditions from sunrise to sunset with reasonable accuracy (less than 10% of relative errors). In terms of the measurement stability, the depth camera detected crabapple canopy with less than 6% variations under various illuminations between sunrise and sunset. The results from the evaluations suggested that the performance of the depth camera was adequate for canopy detections under outdoor conditions for future variable rate applications in ornamental and tree crop production.