Scholarlink

Potholes pose a significant threat to road safety, leading to accidents, infrastructure degradation, and increased maintenance costs. This paper presents an efficient approach for detecting and visualizing potholes by integrating LiDAR point cloud data with Google Earth through GPS georeferencing. A YDLIDAR G2 sensor is employed to collect spatial data, which is transformed from polar to Cartesian coordinates and mapped onto GPS locations using Python-based processing. The methodology follows a structured workflow: data acquisition, coordinate transformation, georeferencing, and visualization in Google Earth, facilitating precise pothole localization. The proposed technique is compared with Martin Isenburg’s streaming pipeline method for large-scale LiDAR visualization, highlighting distinctions in computational efficiency and real-time application. The results demonstrate accurate mapping of road anomalies, enabling municipalities to optimize maintenance strategies. This study underscores the potential of LiDAR-based Road surface analysis for infrastructure monitoring, with future applications in real-time assessment and autonomous navigation.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

LiDAR-GPS Integrated System for Real-Time Pothole Detection and Visualization Using Google Earth

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Vishal B. Pattanashetty,
  • Prakash Pawar

摘要

Potholes pose a significant threat to road safety, leading to accidents, infrastructure degradation, and increased maintenance costs. This paper presents an efficient approach for detecting and visualizing potholes by integrating LiDAR point cloud data with Google Earth through GPS georeferencing. A YDLIDAR G2 sensor is employed to collect spatial data, which is transformed from polar to Cartesian coordinates and mapped onto GPS locations using Python-based processing. The methodology follows a structured workflow: data acquisition, coordinate transformation, georeferencing, and visualization in Google Earth, facilitating precise pothole localization. The proposed technique is compared with Martin Isenburg’s streaming pipeline method for large-scale LiDAR visualization, highlighting distinctions in computational efficiency and real-time application. The results demonstrate accurate mapping of road anomalies, enabling municipalities to optimize maintenance strategies. This study underscores the potential of LiDAR-based Road surface analysis for infrastructure monitoring, with future applications in real-time assessment and autonomous navigation.