Centroid Distance Keypoint Detector for Colored Point Clouds

被引:7
|
作者
Teng, Hanzhe [1 ]
Chatziparaschis, Dimitrios [1 ]
Kan, Xinyue [1 ]
Roy-Chowdhury, Amit K. [1 ]
Karydis, Konstantinos [1 ]
机构
[1] Univ Calif Riverside, Riverside, CA 92521 USA
来源
2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV) | 2023年
关键词
D O I
10.1109/WACV56688.2023.00125
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Keypoint detection serves as the basis for many computer vision and robotics applications. Despite the fact that colored point clouds can be readily obtained, most existing keypoint detectors extract only geometry-salient keypoints, which can impede the overall performance of systems that intend to (or have the potential to) leverage color information. To promote advances in such systems, we propose an efficient multi-modal keypoint detector that can extract both geometry-salient and color-salient keypoints in colored point clouds. The proposed CEntroid Distance (CED) keypoint detector comprises an intuitive and effective saliency measure, the centroid distance, that can be used in both 3D space and color space, and a multi-modal non-maximum suppression algorithm that can select keypoints with high saliency in two or more modalities. The proposed saliency measure leverages directly the distribution of points in a local neighborhood and does not require normal estimation or eigenvalue decomposition. We evaluate the proposed method in terms of repeatability and computational efficiency (i.e. running time) against state-of-the-art keypoint detectors on both synthetic and real-world datasets. Results demonstrate that our proposed CED keypoint detector requires minimal computational time while attaining high repeatability. To showcase one of the potential applications of the proposed method, we further investigate the task of colored point cloud registration. Results suggest that our proposed CED detector outperforms state-of-the-art handcrafted and learning-based keypoint detectors in the evaluated scenes. The C++ implementation of the proposed method is made publicly available at https://github.com/UCR-Robotics/CED_Detector.
引用
收藏
页码:1196 / 1205
页数:10
相关论文
共 50 条
  • [1] Shape binary patterns: an efficient local descriptor and keypoint detector for point clouds
    Romero-Gonzalez, Cristina
    Garcia-Varea, Ismael
    Martinez-Gomez, Jesus
    MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (03) : 3577 - 3601
  • [2] Shape binary patterns: an efficient local descriptor and keypoint detector for point clouds
    Cristina Romero-González
    Ismael García-Varea
    Jesus Martínez-Gómez
    Multimedia Tools and Applications, 2022, 81 : 3577 - 3601
  • [3] SKD: Keypoint Detection for Point Clouds Using Saliency Estimation
    Tinchev, Georgi
    Penate-Sanchez, Adrian
    Fallon, Maurice
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (02) : 3785 - 3792
  • [4] Concept drift detector based on centroid distance analysis
    Klikowski, Jakub
    2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
  • [5] Keypoint based autonomous registration of terrestrial laser point-clouds
    Barnea, Shahar
    Filin, Sagi
    ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2008, 63 (01) : 19 - 35
  • [6] A Supervoxel Segmentation Method with Adaptive Centroid Initialization for Point Clouds
    Puligandla, V. Anirudh
    Loncaric, Sven
    IEEE Access, 2022, 10 : 98525 - 98534
  • [7] A Supervoxel Segmentation Method With Adaptive Centroid Initialization for Point Clouds
    Puligandla, V. Anirudh
    Loncaric, Sven
    IEEE ACCESS, 2022, 10 : 98525 - 98534
  • [8] FINDING A GOOD FEATURE DETECTOR-DESCRIPTOR COMBINATION FOR THE 2D KEYPOINT-BASED REGISTRATION OF TLS POINT CLOUDS
    Urban, S.
    Weinmann, M.
    ISPRS GEOSPATIAL WEEK 2015, 2015, II-3 (W5): : 121 - 128
  • [9] Fast and Robust Keypoint Detection in Unstructured 3-D Point Clouds
    Garstka, Jens
    Peters, Gabriele
    ICIMCO 2015 PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS, VOL. 2, 2015, : 131 - 140
  • [10] Centroid Detection Using Optical Mask and Single Point Detector
    Li, Zhaocong
    Wu, Xiaosong
    Huang, Linhai
    Gu, Naiting
    IEEE PHOTONICS TECHNOLOGY LETTERS, 2024, 36 (22) : 1337 - 1340