Software Engineering Approaches for TinyML based IoT Embedded Vision: A Systematic Literature Review
This review addresses the need for robust software engineering frameworks to help product developers scale TinyML applications in IoT embedded vision, but it is incremental as it synthesizes existing knowledge rather than introducing new methods.
The paper conducted a systematic literature review to identify key challenges in TinyML-based IoT embedded vision and aggregated state-of-the-art software engineering approaches from computer vision, machine learning, and embedded systems to address these challenges, drawing synergies between expertise from embedded systems and ML developers.
Internet of Things (IoT) has catapulted human ability to control our environments through ubiquitous sensing, communication, computation, and actuation. Over the past few years, IoT has joined forces with Machine Learning (ML) to embed deep intelligence at the far edge. TinyML (Tiny Machine Learning) has enabled the deployment of ML models for embedded vision on extremely lean edge hardware, bringing the power of IoT and ML together. However, TinyML powered embedded vision applications are still in a nascent stage, and they are just starting to scale to widespread real-world IoT deployment. To harness the true potential of IoT and ML, it is necessary to provide product developers with robust, easy-to-use software engineering (SE) frameworks and best practices that are customized for the unique challenges faced in TinyML engineering. Through this systematic literature review, we aggregated the key challenges reported by TinyML developers and identified state-of-art SE approaches in large-scale Computer Vision, Machine Learning, and Embedded Systems that can help address key challenges in TinyML based IoT embedded vision. In summary, our study draws synergies between SE expertise that embedded systems developers and ML developers have independently developed to help address the unique challenges in the engineering of TinyML based IoT embedded vision.