From 2d to 3d: Evolution of Object Detection Algorithms and Their Impact on Traffic Systems

Target detection is a fundamental research area in computer vision, with wide applications in pedestrian detection, vehicle recognition, and autonomous driving. For autonomous systems to navigate and engage with their surroundings safely, they must be able to detect and classify objects accurately in real-time. The development of deep learning technology has led to a rapid evolution in object detection techniques. This paper reviews the evolution of 2D object detection algorithms, ranging from deep learning-based techniques to conventional machine vision approaches. Additionally, it talks about how 3D object identification systems have advanced and how they are used in traffic situations. The study also examines the difficulties that object detection algorithms are currently facing and suggests possible avenues for further investigation. This study seeks to deliver an extensive review of the development and present landscape of object detection technologies, helping researchers better understand the key technical pathways, identify existing challenges, and explore innovative approaches for advancing the field further. It is hoped that this review can serve as a reference and inspiration for subsequent research and practical applications.