SYSTEM AND METHOD FOR CLUSTERING LiDAR POINT CLOUD BY USING ARTIFICIAL INTELLIGENCE

An artificial intelligence (AI)-based system configured to perform clustering of light detection and ranging (LiDAR) point cloud data, the system comprising:

• at least one processor;
• and
• at least one memory storing computer program instructions that, based on being executed by the at least one processor, perform operations of object recognition for recognizing an object in a surrounding environment based on point cloud data obtained from at least one LiDAR sensor, the operations comprising:
• obtaining point cloud data from at least one LiDAR sensor;
• determining a plurality of classes respectively corresponding to a plurality of objects detected in the point cloud data;
• executing class merging for the plurality of classes to obtain a plurality of seed classes, wherein a number of the plurality of seed classes is smaller than a number of the plurality of classes;
• generating a seed point list composed of a plurality of seed points respectively corresponding to the plurality of seed classes;
• selecting a clustering scheme for the point cloud data and generating a data structure for the selected clustering scheme;
• determining a clustering priority for the plurality of seed classes;
• and
• segmenting the point cloud data to which the data structure is applied, depending on the clustering priority, and applying the selected clustering scheme to the segmented point cloud data to generate a plurality of clusters.