Comparative Review of Object Detection Algorithms in Small Single-Board Computers

Abstract

Object detection is a crucial task in computer vision with a wide range of applications. However, deploying object detection algorithms on small single-board computers (SBCs) poses unique challenges. In this review article, we present an in-depth comparative analysis of object detection algorithms tailored for small SBCs. We have conducted an extensive literature review on existing research in object detection algorithms and evaluated the performance of different approaches on benchmark datasets. Our review encompasses cutting-edge deep learning methods, which are YOLO, SSD, and Faster R-CNN. We delve into the challenges and limitations of implementing these algorithms on small SBCs and offer recommendations for optimizing their performance in such environments. Our analysis aims to shed light on the strengths and weaknesses of various object detection algorithms for small SBCs, ultimately guiding practitioners in making informed decisions and identifying potential avenues for future research in this domain.