Road edge detection based on combined deep learning and spatial statistics of LiDAR data
Dragan Kukolj, Igor Marinović, Sandra Nemet
Abstract
Mobile laser scanning data can be used for effective extraction of road edge information, which is important in the domain of road maintenance and intelligent transportation. This paper proposes a road edge detection method that combines a deep learning and spatial statistics of point cloud data. Semantic segmentation using a deep neural network enables the effective extraction of point cloud fragments recognized as road. The process continues with the spatial statistical analysis of voxel features of data organized into a 3D voxel grid. Filtered voxels are clustered into spatially proximate clusters of similar shape, i.e. straight or curved edges.
Topics & Concepts
Point cloudVoxelComputer scienceArtificial intelligenceSegmentationEnhanced Data Rates for GSM EvolutionGridDeep learningLidarSpatial analysisPattern recognition (psychology)Artificial neural networkDomain (mathematical analysis)GeographyData miningComputer visionRemote sensingMathematicsGeodesyMathematical analysisRemote Sensing and LiDAR ApplicationsAutomated Road and Building Extraction3D Surveying and Cultural Heritage