Path Segmentation from Point Cloud Data for Autonomous Navigation

Autonomous vehicles require in-depth knowledge of their surroundings, making path segmentation and object detection crucial for determining the feasible region planning. Uniform characteristics a road portion can be denoted by segmentations. Currently, techniques mostly depend on quality camera images under different lighting conditions. However, Light Detection Ranging (LiDAR) sensors provide extremely precise 3D geometry information about leading to increased accuracy with memory consumption computational overhead. This paper introduces novel methodology which combines LiDAR data detection, bridging gap between Point Clouds (PCs). The assignment semantic labels points is essential in various fields, including remote sensing, autonomous vehicles, computer vision. research discusses how select most relevant geometric features planning improve navigation. An automatic framework Semantic Segmentation (SS) introduced, consisting four processes: selecting neighborhoods, extracting classification features, features. aim make components usable end users without specialized considering simplicity, effectiveness, reproducibility. Through an extensive evaluation feature selection methods, classifiers, benchmark datasets, outcomes show that appropriate neighborhoods significantly develops segmentation. Additionally, right subsets reduce computation time, usage, enhance results.