Ground object recognition and segmentation from aerial image‐based 3D point cloud. (23rd July 2019)

• Record Type: Journal Article
• Authors: Ogura, Katsuya; Yamada, Yuma; Kajita, Shugo; Yamaguchi, Hirozumi; Higashino, Teruo; Takai, Mineo
• Other Names: Pang Shaoning guestEditor.; Zhang Xuyun guestEditor.; Ikeda Kazushi guestEditor.; Puthal Deepak guestEditor.; Li Jianxin guestEditor.; Sarrafzahed Abdolhossein guestEditor.
• Is Part Of: Computational intelligence. Volume 35:Number 3(2019)
• Page Start: 625
• Page End: 642
• Publication Date: 2019-07-23
• Subjects: drone -- outdoor recognition -- point cloud -- segmentation -- 3D objects; Artificial intelligence -- Periodicals; Computational linguistics -- Periodicals; 006.3
• DOI: 10.1111/coin.12232
• Languages: English
• ISSNs: 0824-7935

Abstract

Abstract: Several attempts have been made to grasp three‐dimensional (3D) ground shape from a 3D point cloud generated by aerial vehicles, which help fast situation recognition. However, identifying such objects on the ground from a 3D point cloud, which consists of 3D coordinates and color information, is not straightforward due to the gap between the low‐level point information (coordinates and colors) and high‐level context information (objects). In this paper, we propose a ground object recognition and segmentation method from a geo‐referenced point cloud. Basically, we rely on some existing tools to generate such a point cloud from aerial images, and our method tries to give semantics to each set of clustered points. In our method, firstly, such points that correspond to the ground surface are removed using the elevation data from the Geographical Survey Institute. Next, we apply an interpoint distance‐based clustering and color‐based clustering. Then, such clusters that share some regions are merged to correctly identify a cluster that corresponds to a single object. We have evaluated our method in several experiments in real fields. We have confirmed that our method can remove the ground surface within 20 cm error and can recognize most of the objects.