Investigation and analysis of an ultrasonic sensor for specific yield assessment and greenhouse features identification

The spectrum of an ultrasonic return echo from plants has been shown to contain useful information. The research reported in this paper focused on developing an ultrasonic sensing system and analyzing the ultrasonic classification features that would ultimately be used as the basis for a yield estimation robotic system. An algorithm was also developed for prediction of fruit mass per plant based on the ultrasonic echo return from a plant. The ultrasonic sensor system was tested in lab and pepper greenhouse environments and on single pepper plants, single leaves and fruit. The results showed the potential of ultrasonic sensors for such a robot in classifying plants and greenhouse infrastructures such as walls. It showed the robot’s ability to detect hidden plant rows and fruits as well as making an estimation of the fruit mass in single plants. A multi-linear regression model developed for estimating the energy level was found to be highly significant with R² of 0.64 and 0.84 for 28–32 and 20–28 kHz ranges respectively. This estimated model was used to derive a prediction method for fruit mass per plant that yielded an R² of 0.34.