３次元点群情報を基づく物体認識及び３次元地図生成

抄録

This paper describes a 3D mapping method with object recognition result by using a wheeled mobile robot. The object recognition is realized by using a deep learning neural network called PointPillars. By comparing the recognition results between two continuous frames, the object ID can be matched and for those which are recognized in both frames, and ID will be changed for the others. The recognized objects with determined ID will be reflected to the 3D map.