Skip to main content
ARS Home » Midwest Area » Wooster, Ohio » Application Technology Research » Research » Publications at this Location » Publication #381030

Research Project: Coordinated Precision Application Technologies for Sustainable Pest Management and Crop Protection

Location: Application Technology Research

Title: Improved canopy characterization with laser scanning sensor for greenhouse spray applications

item NAIR, UCHIT - The Ohio State University
item LING, PETER - The Ohio State University
item Zhu, Heping

Submitted to: Journal of the ASABE
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 8/23/2021
Publication Date: 12/20/2021
Citation: Nair, U., Ling, P., Zhu, H. 2021. Improved canopy characterization with laser scanning sensor for greenhouse spray applications. Journal of the ASABE. 64(6):2125-2136.

Interpretive Summary: Chemicals are used in greenhouses to maintain plant yield, and quality by combating insects, weeds, and plant pathogens, but excessive use can have a detrimental effect on the environment and worker safety. The intelligent spray technology is needed in greenhouses to control spray rates as a function of the canopy volume to reduce pesticide waste. Laser sensors have been successfully integrated into orchard sprayers to characterize canopy structures for precision pesticide applications. However, compared to orchards, canopy characterization inside a greenhouse can be challenging due to multiple constraints of the tightly packed high-value plants. In this research, a ‘super resolution’ algorithm was developed and tested for processing sets of point cloud data collected from a high-speed indoor-use laser sensor. Plant canopy characterization was improved through the algorithm by isolating individual targets from the dataset, removing distortion, and estimating the occluded portion of the plant canopies. The point cloud data processing algorithm for the laser sensor increased the range of accurate measurements and reduced time in mapping large areas. It was later integrated into an experimental variable-rate intelligent spray system for field evaluations in a commercial greenhouse. Furthermore, the algorithm would have great potentials to be used in other applications such as plant phenotyping, plant health monitoring, and plant nutrition and inventory managements.

Technical Abstract: Laser-guided intelligent spray technology for greenhouse applications requires sensors that can accurately measure plant dimensions. This study proposed a new method to overcome current limitations by introducing a processing algorithm that manipulates the noisy dataset and determines the optimal sensor height to produce better measurement of the canopy width. The processing involves a combination of registration, clustering and mirroring algorithms. The registration algorithm aligns multiple scans of the same scene to improve resolution. The clustering algorithm isolates individual plant canopies from the dataset to enable further processing. The mirroring algorithm is used to resolve the problems of distortion and occlusion and predict the missing information in the dataset. The performance of the processing algorithm was evaluated by calculating the root mean square error (RMSE) in the canopy width measurements. The processing algorithm reduced RMSE values by 46% and the largest improvements were seen for objects placed beyond 1.5 m from the sensor. The sensor height was observed to be inversely proportional to the RMSE values. The average RMSE of the processing algorithm was 25 mm when the laser sensor was at the height of 1 m. Another experimental setup was used to test the limits of the relation between sensor height and the algorithm performance while using objects that were more representative of plant canopy shapes. The overall average RMSE was reduced by increasing sensor height, but the performance levelled off and was even reduced beyond the recommended ‘optimal sensor height’. The processing algorithm introduced has the potential to not only improve spray efficiencies but also in plant phenotyping applications.