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
  • [41] PIU-Net: Generation of Virtual Panoramic Views from Colored Point Clouds
    Adam, Michael Georg
    Steinbach, Eckehard
    VISAPP: PROCEEDINGS OF THE 16TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS - VOL. 4: VISAPP, 2021, : 269 - 276
  • [42] Fuzzy logic and histogram of normal orientation-based 3D keypoint detection for point clouds
    Iqbal M.Z.
    Bobkov D.
    Steinbach E.
    Pattern Recognition Letters, 2020, 136 : 40 - 47
  • [43] THE COLORED EDGE OF NOCTILUCENT CLOUDS
    AVASTE, OA
    GADSDEN, M
    GRECHKO, GM
    JOURNAL OF ATMOSPHERIC AND TERRESTRIAL PHYSICS, 1988, 50 (07): : 591 - &
  • [44] JoKDNet: A joint keypoint detection and description network for large-scale outdoor TLS point clouds registration
    Wang, Yuan
    Yang, Bisheng
    Chen, Yiping
    Liang, Fuxun
    Dong, Zhen
    INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2021, 104
  • [45] Automatic markerless registration of point clouds with semantic-keypoint-based 4-points congruent sets
    Ge, Xuming
    ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2017, 130 : 344 - 357
  • [46] Novel scale-invariant keypoint detector
    Wen, Ming
    Li, Ying
    Zhuo, Qing
    Wang, Wenyuan
    OPTICAL ENGINEERING, 2008, 47 (05)
  • [47] On Approximate Geodesic-Distance Queries amid Deforming Point Clouds
    Agarwal, Pankaj K.
    Efrat, Alon
    Sharathkumar, R.
    Yu, Hai
    ALGORITHMIC FOUNDATIONS OF ROBOTICS VIII, 2010, 57 : 351 - +
  • [48] Metricizing the Euclidean Space Toward Desired Distance Relations in Point Clouds
    Rass, Stefan
    Konig, Sandra
    Ahmad, Shahzad
    Goman, Maksim
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2024, 19 : 7304 - 7319
  • [49] Power Line Simulation for Safety Distance Detection Using Point Clouds
    Zhang, Sai Chang
    Liu, Jun Zheng
    Niu, Zheng
    Gao, Shuai
    Xu, Hai Zhi
    Pei, Jie
    IEEE ACCESS, 2020, 8 (08): : 165409 - 165418
  • [50] Registration of HRSI and LiDAR Point Clouds Based on Distance Transformation Model
    Zhang Y.
    Hong W.
    Wan Y.
    Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University, 2023, 48 (03): : 339 - 348