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
  • [21] ADAPTIVE FUSION-BASED 3D KEYPOINT DETECTION FOR RGB POINT CLOUDS
    Iqbal, Muhammad Zafar
    Bobkov, Dmytro
    Steinbach, Eckehard
    2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2019, : 3711 - 3715
  • [22] Keypoint domain triangular features for fast initial alignment of 3D point clouds
    Quan, Siwen
    Ma, Jie
    ELECTRONICS LETTERS, 2019, 55 (14) : 787 - +
  • [23] Accurate Registration of 3D Point Clouds Based on Keypoint Extraction and Improved Iterative Closest Point Algorithm
    Peng Zhen
    Lu Yuanjian
    Qu Chao
    Zhu Dahu
    LASER & OPTOELECTRONICS PROGRESS, 2020, 57 (06)
  • [24] Fast LoG SIFT Keypoint Detector
    Maharjan, Paras
    Vanfossan, Lyle
    Li, Zhu
    Shen, Jerry Jialie
    2023 IEEE 25TH INTERNATIONAL WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING, MMSP, 2023,
  • [25] VFKD: Voxelized Fractal Keypoint Detector
    Gomez-Donoso, Francisco
    Escalona, Felix
    Cazorla, Miguel
    2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
  • [26] A LOW-DIMENSIONAL FEATURE TRANSFORM FOR KEYPOINT MATCHING AND CLASSIFICATION OF POINT CLOUDS WITHOUT NORMAL COMPUTATION
    Seib, Viktor
    Paulus, Dietrich
    2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2018, : 2949 - 2953
  • [27] A VESSEL KEYPOINT DETECTOR FOR JUNCTION CLASSIFICATION
    Srinidhi, Chetan L.
    Rath, Priyadarshi
    Sivaswamy, Jayanthi
    2017 IEEE 14TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2017), 2017, : 882 - 885
  • [28] SHOT : A Binary Feature Descriptor for Fast and Efficient Keypoint Matching on 3D Point Clouds
    Prakhya, Sai Manoj
    Liu, Bingbing
    Lin, Weisi
    2015 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2015, : 1929 - 1934
  • [29] Impact of Quality and Distance on the Perception of Point Clouds in Mixed Reality
    Nguyen, Minh
    Vats, Shivi
    Van Damme, Sam
    van der Hooft, Jeroen
    Vega, Maria Torres
    Wauters, Tim
    Timmerer, Christian
    Hellwagner, Hermann
    2023 15TH INTERNATIONAL CONFERENCE ON QUALITY OF MULTIMEDIA EXPERIENCE, QOMEX, 2023, : 87 - 90
  • [30] Fast exact shortest distance queries for massive point clouds
    Eriksson, David
    Shellshear, Evan
    GRAPHICAL MODELS, 2016, 84 : 28 - 37