Researching

Journals
  • Advanced Photonics
  • Photonics Insights
  • Advanced Photonics Nexus
  • Photonics Research
  • Advanced Imaging
  • View All Journals
  • Chinese Optics Letters
  • High Power Laser Science and Engineering
    • Articles
  • Optics
  • Physics
  • Geography
  • View All Subjects
    • Conferences
  • CIOP
  • HPLSE
  • AP
  • View All Events
    • News
    About CLP
    Search by keywords or author
    Journals >Laser & Optoelectronics Progress >Volume 55 >Issue 11 >Page 111505 > Article
    • Laser & Optoelectronics Progress
    • Vol. 55, Issue 11, 111505 (2018)
    Multi-Shaped Targets Recognition and Point Clouds Acquisition Algorithm in Complex Environment
    Mingyou Chen1, Yunchao Tang2, Xiangjun Zou1、*, Kuangyu Huang1, Wenxian Feng2, and Po Zhang1
    Author Affiliations
  • 1 Collage of Engineering, South China Agricultural University, Guangzhou, Guangdong 510642, China
  • 2 School of Civil and Transportation Engineering, Guangdong University of Technology, Guangzhou, Guangdong 510006, China
    • show less
    DOI: 10.3788/LOP55.111505 Cite this Article Set citation alerts
    Mingyou Chen, Yunchao Tang, Xiangjun Zou, Kuangyu Huang, Wenxian Feng, Po Zhang. Multi-Shaped Targets Recognition and Point Clouds Acquisition Algorithm in Complex Environment[J]. Laser & Optoelectronics Progress, 2018, 55(11): 111505 Copy Citation Text show less
    Workflow of algorithm
    Fig. 1. Workflow of algorithm
    Download full size
    Schematic of RPCA scene sample training. (a) One of the scene samples; (b) target sample; (c) training process
    Fig. 2. Schematic of RPCA scene sample training. (a) One of the scene samples; (b) target sample; (c) training process
    Download full size
    Schematic diagram of RPCA in image segmentation. (a) Image to be segmented; (b) high-rank noises (targets)
    Fig. 3. Schematic diagram of RPCA in image segmentation. (a) Image to be segmented; (b) high-rank noises (targets)
    Download full size
    Effect of morphology operation. (a) Adaptive thresholding segmentation to high-rank noises; (b) morphology operation; (c) corresponding pixels in original image
    Fig. 4. Effect of morphology operation. (a) Adaptive thresholding segmentation to high-rank noises; (b) morphology operation; (c) corresponding pixels in original image
    Download full size
    Improved k-means clustering process
    Fig. 5. Improved k-means clustering process
    Download full size
    Schematic of SVM classification. (a) Input regions; (b) output targets with label 1; (c) output targets with label 0; (d) training and classification progress
    Fig. 6. Schematic of SVM classification. (a) Input regions; (b) output targets with label 1; (c) output targets with label 0; (d) training and classification progress
    Download full size
    Schematic of epipolar line rectification
    Fig. 7. Schematic of epipolar line rectification
    Download full size
    Template searching matching point through epipolar line
    Fig. 8. Template searching matching point through epipolar line
    Download full size
    Positioning of right image objects. (a) Targets labeled 1; (b) targets labeled 0
    Fig. 9. Positioning of right image objects. (a) Targets labeled 1; (b) targets labeled 0
    Download full size
    Relationship between new and old coordinates
    Fig. 10. Relationship between new and old coordinates
    Download full size
    Illustration of advanced pass through denoising
    Fig. 11. Illustration of advanced pass through denoising
    Download full size
    Schematic of radium filtering
    Fig. 12. Schematic of radium filtering
    Download full size
    Contrast before and after denoising. (a) Original point clouds; (b) denoised point clouds
    Fig. 13. Contrast before and after denoising. (a) Original point clouds; (b) denoised point clouds
    Download full size
    Experimental platform
    Fig. 14. Experimental platform
    Download full size
    Schematic of location effect of different algorithms in complex environment. (a)-(d) Messy background with identical color; (e) stacked targets with weak light; (f) messy background with nonlinear light
    Fig. 15. Schematic of location effect of different algorithms in complex environment. (a)-(d) Messy background with identical color; (e) stacked targets with weak light; (f) messy background with nonlinear light
    Download full size
    Data of algorithm efficiency. (a) Contrast of calculation quantity; (b) contrast of running time
    Fig. 16. Data of algorithm efficiency. (a) Contrast of calculation quantity; (b) contrast of running time
    Download full size
    Experimental data of algorithm error. (a) Cylinder measuring error; (b) square measuring error; (c) gear measuring error
    Fig. 17. Experimental data of algorithm error. (a) Cylinder measuring error; (b) square measuring error; (c) gear measuring error
    Download full size
    SceneNumber of targetsNumber of recognized targetsCorrect rate /%
    Fig. 15(a)4646100
    Fig. 15(b)525096.2
    Fig. 15(c)212095.2
    Fig. 15(d)5050100
    Fig. 15(e)504692.0
    Fig. 15(f)504488.0
    Table 1. Recognizing rate of new targets
    Abstract
    Get PDF(in Chinese)
    Figures&Tables (18)
    Equations (0)
    References (20)
    Cited By (6)
    Get Citation
    Copy Citation Text
    Mingyou Chen, Yunchao Tang, Xiangjun Zou, Kuangyu Huang, Wenxian Feng, Po Zhang. Multi-Shaped Targets Recognition and Point Clouds Acquisition Algorithm in Complex Environment[J]. Laser & Optoelectronics Progress, 2018, 55(11): 111505
    Download Citation
    Set citation alerts for the article
    Tools
    Share
    Set citation alerts for the article
    Save the article for my favorites
    Paper Information
    Recommended Topics
    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology