A comprehensive survey of semantic segmentation based on computer vision

Semantic segmentation is a significant and demanding work in computer vision and it has gained more attention worldwide. This article delivers an in-depth analysis of vision-based semantic segmentation approaches for 3D point cloud data. This article investigates the emergence and development of semantic segmentation both domestically and internationally. It also outlines the historical evolution and various branches of semantic segmentation and emphasizing recent advancements driven by deep learning techniques. Despite notable progress, challenges persist, including handling variability in object shapes and sizes, computational costs, and robustness against different conditions. This survey aims to evaluate and synthesize current research, identifying strengths and weaknesses of traditional and modern methods, and highlighting potential future research directions. The study offers valuable information on the implementation and performance of different segmentation approaches by presenting an comprehensive analysis of methodologies, datasets, and evaluation metrics and guiding researchers towards suitable techniques for several applications.