Irregular Change Detection in Sparse Bi-Temporal Point Clouds using Learned Place Recognition Descriptors and Point-to-Voxel Comparison

被引:0
|
作者
Stathoulopoulos, Nikolaos [1 ]
Koval, Anton [1 ]
Nikolakopoulos, George [1 ]
机构
[1] Lulea Univ Technol, Dept Comp Elect & Space Engn, Robot & AI Grp, S-97187 Lulea, Sweden
基金
欧盟地平线“2020”;
关键词
D O I
10.1109/IROS55552.2023.10342248
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Change detection and irregular object extraction in 3D point clouds is a challenging task that is of high importance not only for autonomous navigation but also for updating existing digital twin models of various industrial environments. This article proposes an innovative approach for change detection in 3D point clouds using deep learned place recognition descriptors and irregular object extraction based on voxel-to-point comparison. The proposed method first aligns the bi-temporal point clouds using a map-merging algorithm in order to establish a common coordinate frame. Then, it utilizes deep learning techniques to extract robust and discriminative features from the 3D point cloud scans, which are used to detect changes between consecutive point cloud frames and therefore find the changed areas. Finally, the altered areas are sampled and compared between the two time instances to extract any obstructions that caused the area to change. The proposed method was successfully evaluated in real-world field experiments, where it was able to detect different types of changes in 3D point clouds, such as object or muck-pile addition and displacement, showcasing the effectiveness of the approach. The results of this study demonstrate important implications for various applications, including safety and security monitoring in construction sites, mapping and exploration and suggests potential future research directions in this field.
引用
收藏
页码:8077 / 8083
页数:7
相关论文
共 6 条
  • [1] Building Change Detection from Bi-Temporal Dense-Matching Point Clouds and Aerial Images
    Pang, Shiyan
    Hu, Xiangyun
    Cai, Zhongliang
    Gong, Jinqi
    Zhang, Mi
    SENSORS, 2018, 18 (04)
  • [2] Point Cloud Descriptors for Place Recognition using Sparse Visual Information
    Cieslewski, Titus
    Elena, Stumm Y.
    Gawel, Abel
    Bosse, Mike
    Lynen, Simon
    Siegwart, Roland
    2016 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2016, : 4830 - 4836
  • [3] Use of Bi-Temporal ALS Point Clouds for Tree Removal Detection on Private Property in Raciborz, Poland
    Przewozna, Patrycja
    Hawrylo, Pawel
    Zieba-Kulawik, Karolina
    Inglot, Adam
    Maczka, Krzysztof
    Wezyk, Piotr
    Matczak, Piotr
    REMOTE SENSING, 2021, 13 (04) : 1 - 21
  • [4] Assessment of approaches for monitoring forest structure dynamics using bi-temporal digital aerial photogrammetry point clouds
    Fu, Xiaoyao
    Zhang, Zhengnan
    Cao, Lin
    Coops, Nicholas C.
    Goodbody, Tristan R. H.
    Liu, Hao
    Shen, Xin
    Wu, Xiangqian
    REMOTE SENSING OF ENVIRONMENT, 2021, 255
  • [5] Change detection of mountain birch using multi-temporal ALS point clouds
    Nystrom, Mattias
    Holmgren, Johan
    Olsson, Hakan
    REMOTE SENSING LETTERS, 2013, 4 (02) : 190 - 199
  • [6] Change detection of trees in urban areas using mutil-temporal airborne lidar point clouds
    Xiao, Wen
    Xu, Sudan
    Elberink, Sander Oude
    Vosselman, George
    REMOTE SENSING OF THE OCEAN, SEA ICE, COASTAL WATERS, AND LARGE WATER REGIONS 2012, 2012, 8532