Development of an IoT-based Imaging System for Automated In-field Monitoring

The automated monitoring and evaluation system of plant phenotypes is one of the keys to advancing and strengthening crop breeding programs. In this study, improvements to the camera-based sensor system and a previous research weather station primarily assembled from Raspberry Pi products are outlined—a board with dual cameras (RGB and NoIR) that provides high spatial and temporal resolution data. The network connection hardware and power system for the sensors have been upgraded. Previously, the sensors could automatically capture plant images at user-defined time points; thus, an image processing algorithm (edge computing) was developed and installed to extract digital phenotypic traits from images captured after the capturing process. With the development, the new sensor system can be integrated with the internet and is configured with a cloud server to store data online (digital traits and raw images). A real-time monitoring system has been established to visualize the development of traits and plant images over the entire season using time series data. With such a system, plant breeders will be able to monitor multiple trials for timely crop management and decision-making processes, which is also resource-efficient.

Figure 1 AGIcam sensor and weather station. (a) AGIcam installed in the 2021 spring wheat field trial; (b) AGIcam sensor; (c) Weather station.

Figure 2 The IoT framework consists of sensors, cloud services, and monitoring systems.

Source

Click here to read the original text