Exploring Quantized CNN Deployment on Microcontrollers for Object Detection in a PAN
Matthew Bailey, Joseph Clark, Rolland Muzeya
TinyML is a growing field that focuses on developing deep learning models suitable for ultra-low-power devices such as microcontrollers (MCU). Traditional computer vision models use computationally expensive convolutional neural networks (CNNs), making even the quantized forms of these models difficult to deploy on microcontrollers. We present our efforts in designing a multi-node TinyML system for the detection of multiple objects. To accomplish this objective, we experimented with using camera modules with the ESPCAM and the NANO BLE 33 embedded devices. We further explored using embedded devices' systems with one MCU per node and systems with multiple MCUs per node. The goal of our effort is to develop a system that performs object detection and notifies the user about the presence of an object within a personal area network (PAN). When compared to a traditional network-based object-detection system, our proposed system provides the following advantages. First, our system is simple and cost-effective to deploy as it is completely based on a PAN and does not need Wi-Fi or Internet connectivity. Secondly, our system processes data inside the PAN, hence ensuring the privacy of surveillance data.
Matthew Bailey is a senior CIS major with a minor in cybersecurity, and emphasis in networking and software development. He has presented at the SC Upstate Research Symposium previously for work with machine learning, and he has held a position in the IT Department of Lander since 2020. After graduation, Matthew plans to enter the software development or IT fields, while furthering his education on computing.
Joseph Clark graduated from Fort Mill High School in Fort Mill, SC, in 2014. After high school, Joseph joined the United States Marine Corps and served for five years. Joseph is a double major in Mathematics and Computer Information Systems. His achievements include serving as a teaching assistant for Math 121, working as a peer tutor, and presenting undergraduate research in mathematics and computer information systems at multiple locations during his time at Lander.
Rolland Muzeya graduated from Mazowe Boys High School in Harare, Zimbabwe. He is a junior Computer Information Systems major with a minor in Mathematics. His achievements include working as a computer repair technician on campus, and will be a Software Engineering intern at BlackRock in the summer of 2023.