Image-Based Analysis of Water Content Change in Tomato Cultivation

Water-stress cultivation is becoming widely used for deliberately reducing the amount of irrigation and increasing the sugar content of fruits. Deliberately reducing the amount of irrigation requires experience and intuition of skilled farmers, so it is difficult for new farmers to conduct water-stress cultivation. Therefore, New farmers need techniques to easily conduct such cultivation. Under these circumstances, the importance of an irrigation-control system for automating irrigation should be discussed. To control irrigation, we must determine the changes in plant states. In this study, we clarified how much the body-water content of plants changes due to irrigation and designed a model for representing the body-water content of plants and their response to irrigation using a hidden Markov model. In this paper, we discuss whether this model can be used for irrigation control. Such technology for new farmers should be low in cost, so plant reaction to irrigation is measured using optical flow on the basis of leaf wilt. Based on the displacement vectors obtained from optical flow, we estimated the body-water content of plants and evaluated whether it is possible to determine the irrigation amount with our model. The results from experiments conducted on the cultivation of tomato plants revealed that the displacement vectors obtained from optical flow under specific conditions reflects the change in body-water content.