LiDAR exhibits high non-ground point ratios and uneven density distributions when obtaining point-cloud data in areas with steep terrains and dense vegetation coverage.Classical filtering algorithms cannot readily obtain accurate point-cloud filtering results.In point-cloud filtering using deep learning,issues such as insufficient information utilization and inadequate feature extraction persist.Therefore,this study proposes a point-cloud filtering network that integrates multidimensional features and global contextual information(MGINet).It establishes a framework for multidimensional feature extraction and global information fusion to enhance the accuracy of point-cloud filtering in complex mountainous regions.MGINet begins by designing a local cross-feature fusion module,which combines normal vectors with spatial geometric structures to extract high-dimensional diverse features,thereby preserving the local spatial structure features of the point cloud.Subsequently,a global-context aggregation module is introduced to capture global contextual information,thus enhancing the generality of the features through cross-coding.Finally,experimental testing on both public and actual datasets from complex mountainous areas shows that MGINet outperforms classical algorithms in terms of point-cloud filtering accuracy.
LiDAR datapoint cloud filteringfeature fusionglobal contextual information
NETL
NSTL
万方数据
