EDGE BASED 3D INDOOR CORRIDOR MODELING USING A SINGLE IMAGE

被引:1
|
作者
Jahromi, Ali Baligh [1 ]
Sohn, Gunho [1 ]
机构
[1] York Univ, Dept Earth Space Sci & Engn, GeoICT Lab, 4700 Keele St, Toronto, ON M3J 1P3, Canada
来源
ISPRS GEOSPATIAL WEEK 2015 | 2015年 / II-3卷 / W5期
关键词
Indoor Model Reconstruction; Geometric Reasoning; Hypothesis-Verification; Scene Layout Parameterization; RECOVERY;
D O I
10.5194/isprsannals-II-3-W5-417-2015
中图分类号
P9 [自然地理学];
学科分类号
0705 ; 070501 ;
摘要
Reconstruction of spatial layout of indoor scenes from a single image is inherently an ambiguous problem. However, indoor scenes are usually comprised of orthogonal planes. The regularity of planar configuration (scene layout) is often recognizable, which provides valuable information for understanding the indoor scenes. Most of the current methods define the scene layout as a single cubic primitive. This domain-specific knowledge is often not valid in many indoors where multiple corridors are linked each other. In this paper, we aim to address this problem by hypothesizing-verifying multiple cubic primitives representing the indoor scene layout. This method utilizes middle-level perceptual organization, and relies on finding the ground-wall and ceiling-wall boundaries using detected line segments and the orthogonal vanishing points. A comprehensive interpretation of these edge relations is often hindered due to shadows and occlusions. To handle this problem, the proposed method introduces virtual rays which aid in the creation of a physically valid cubic structure by using orthogonal vanishing points. The straight line segments are extracted from the single image and the orthogonal vanishing points are estimated by employing the RANSAC approach. Many scene layout hypotheses are created through intersecting random line segments and virtual rays of vanishing points. The created hypotheses are evaluated by a geometric reasoning-based objective function to find the best fitting hypothesis to the image. The best model hypothesis offered with the highest score is then converted to a 3D model. The proposed method is fully automatic and no human intervention is necessary to obtain an approximate 3D reconstruction.
引用
收藏
页码:417 / 424
页数:8
相关论文
共 50 条
  • [1] 3D Hallway Modeling Using A Single Image
    Olmschenk, Greg
    Zhu, Zhigang
    [J]. 2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2014, : 158 - +
  • [2] GEOMETRIC CONTEXT AND ORIENTATION MAP COMBINATION FOR INDOOR CORRIDOR MODELING USING A SINGLE IMAGE
    Jahromi, Ali Baligh
    Sohn, Gunho
    [J]. XXIII ISPRS CONGRESS, COMMISSION IV, 2016, 41 (B4): : 295 - 302
  • [3] 3D Reconstruction of Indoor Scenes using a Single RGB-D Image
    Bokaris, Panagiotis-Alexandros
    Muselet, Damien
    Tremeau, Alain
    [J]. PROCEEDINGS OF THE 12TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISIGRAPP 2017), VOL 6, 2017, : 394 - 401
  • [4] Indoor 3D Mapping Technique Based on 3D Image Transformation Using Kinect Sensor
    Tuvshinjargal, Doopalam
    Kang, Byeongju
    Chong, Kil To
    Lee, Deok Jin
    [J]. ADVANCED SCIENCE LETTERS, 2015, 21 (10) : 3014 - 3018
  • [5] 3D Object Modeling and Segmentation Using Image Edge Points in Cluttered Environments
    Tomono, Masahiro
    [J]. JOURNAL OF ROBOTICS AND MECHATRONICS, 2009, 21 (06) : 672 - 679
  • [6] Single Image 3D Without a Single 3D Image
    Fouhey, David F.
    Hussain, Wajahat
    Gupta, Abhinav
    Hebert, Martial
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 1053 - 1061
  • [7] Indoor scene modeling from a single image using normal inference and edge features
    Liu, Mingming
    Guo, Yanwen
    Wang, Jun
    [J]. VISUAL COMPUTER, 2017, 33 (10): : 1227 - 1240
  • [8] Indoor scene modeling from a single image using normal inference and edge features
    Mingming Liu
    Yanwen Guo
    Jun Wang
    [J]. The Visual Computer, 2017, 33 : 1227 - 1240
  • [9] Simple 3D Reconstruction of Single Indoor Image with Perspective Cues
    Huang, Jingyuan
    Cowan, Bill
    [J]. 2009 CANADIAN CONFERENCE ON COMPUTER AND ROBOT VISION, 2009, : 140 - 147
  • [10] 3D facial expression modeling based on facial landmarks in single image
    Lv, Chenlei
    Wu, Zhongke
    Wang, Xingce
    Zhou, Mingquan
    [J]. NEUROCOMPUTING, 2019, 355 : 155 - 167