Date of Award

6-2020

Degree Name

MS in Electrical Engineering

Department

Electrical Engineering

College

College of Engineering

Advisor

Dr. Jane Zhang

Advisor Department

Electrical Engineering

Advisor College

College of Engineering

Abstract

Smart agriculture is an increasingly popular field in which the technology of wireless sensor networks (WSN) has played a large role. Significant research has been done at Cal Poly and elsewhere to develop a computer vision (CV) and machine learning (ML) pipeline to monitor crops and accurately predict crop yield numbers. By autonomously providing farmers with this data, both time and money are saved. During the past development of a prediction pipeline, the primary focuses were CV and ML processing while a lack of attention was given to the collection of quality image data. This lack of focus in previous research presented itself as incomplete and inefficient processing models. This thesis work attempts to solve this image acquisition problem through the initial development and design of an Internet of Things (IoT) prototype network to collect consistent image data with no human interaction. The system is developed with the goals of being low-power, low-cost, autonomous, and scalable. The proposed IoT network nodes are based on the ESP32 SoC and communicate over-the-air with the gateway node via Bluetooth Low Energy (BLE). In addition to BLE, the gateway node periodically uplinks image data via Wi-Fi to a cloud server to ensure the accessibility of collected data. This research develops all functionality of the network, comprehensively characterizes the power consumption of IoT nodes, and provides battery life estimates for sensor nodes. The sensor node developed consumes a peak current of 150mA in its active state and sleeps at 162µA in its standby state. Node-to-node BLE data transmission throughput of 220kbps and node-tocloud Wi-Fi data transmission throughput of 709.5kbps is achieved. Sensor node device lifetime is estimated to be 682 days on a 6600mAh LiPo battery while acquiring five images per day. This network can be utilized by any application that requires a wireless sensor network (WSN), high data rates, low power consumption, short range communication, and large amounts of data to be transmitted at low frequency intervals.

Share

COinS