Remote Crop Sensing with IoT and AI on the Edge

The current work in this paper inspired by the concepts of Edge Computing, Machine Learning, Computer Vision and Internet of Things (IoT). This synergy is used for monitoring apple orchard yield and more specific the detection and information extraction for apple harvesting purposes in the agriculture field. The above concept utilizes the means for a low power information relay using LoRaWAN (Low Power Wide Area Network) protocol designed to connect battery operated "things" with the internet in regional or global topology. Image acquisition and data are processed on a battery driven edge device away from the grid and on site. The proposition implementing a full YoloV4 framework in a single board computer (SBC) equipped with a proper camera and by using custom-trained weights seems to be a feasible solution. The performance of the proposed approach for good apple detection is up to 66.89% for complex dense environments. These preliminary results reveal the feasibility of this edge computing approach utilizing Artificial Intelligence and IoT technologies.