Research and Design of a Small Object Detection and Tracking System Based on YOLOv8 and ByteTrack Algorithms

Amidst the rapid evolution of computer vision technologies, the detection and tracking of small objects have gained paramount importance in domains such as video surveillance, autonomous driving, and intelligent transportation systems. Although existing methodologies have achieved notable advancements, enhancing the accuracy of small object detection and tracking remains a formidable challenge. This study leverages the state-of-the-art deep learning model YOLOv8 in conjunction with the multi-object tracking algorithm ByteTrack to design an efficient system for small object recognition and tracking. Through extensive and rigorous testing, we have substantiated the model's efficacy and practicality in complex environments, particularly in handling scenarios with occlusions and dynamic changes. This research not only enriches the understanding of small object tracking technologies but also furnishes robust support for real-world applications.