Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Acta Optica Sinica, Volume. 37, Issue 12, 1215003(2017)

Depth Estimation from Monocular Infrared Video Based on Bi-Recursive Convolutional Neural Network

Shouchuan Wu1, Haitao Zhao1、*, and Shaoyuan Sun2
Author Affiliations
  • 1 School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China
  • 2 School of Information Science and Technology, Donghua University, Shanghai 201620, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (8)
    Equations (0)
    References (22)
    Cited By (7)
    Tools
    Paper Information
    Topics
    Figures & Tables(8)
    Mechanism of bi-recursive convolution

    Fig. 1. Mechanism of bi-recursive convolution

    Download full size
    Diagram for BrCNN

    Fig. 2. Diagram for BrCNN

    Download full size
    Effect of dividing ground truth depth of infrared video into different depth levels. (a) Infrared video; (b) ground truth; (c) 10 layers; (d) 20 layers; (e) 30 layers

    Fig. 3. Effect of dividing ground truth depth of infrared video into different depth levels. (a) Infrared video; (b) ground truth; (c) 10 layers; (d) 20 layers; (e) 30 layers

    Download full size
    Output of different bi-recursive convolutional layers. (a) Infrared video; (b) output of the first bi-recursive convolutional layer; (c) output of the second bi-recursive convolutional layer; (d) output of the third bi-recursive convolutional layer

    Fig. 4. Output of different bi-recursive convolutional layers. (a) Infrared video; (b) output of the first bi-recursive convolutional layer; (c) output of the second bi-recursive convolutional layer; (d) output of the third bi-recursive convolutional layer

    Download full size
    Depth estimation results of different models. (a) Infrared video; (b) ground truth depth; (c) depth estimated by BrCNN; (d) depth estimated by AlexNet; (e) depth estimated by VGG16; (f) depth estimated by Res34

    Fig. 5. Depth estimation results of different models. (a) Infrared video; (b) ground truth depth; (c) depth estimated by BrCNN; (d) depth estimated by AlexNet; (e) depth estimated by VGG16; (f) depth estimated by Res34

    Download full size
    (a) Mean relative error of BrCNN and VGG16 model; (b) 2-norm of difference between adjacent frames

    Fig. 6. (a) Mean relative error of BrCNN and VGG16 model; (b) 2-norm of difference between adjacent frames

    Download full size
    Depth estimation results of larger 2-norm between frame differences. (a) Continuous three frames of infrared video; (b) estimation results of BrCNN

    Fig. 7. Depth estimation results of larger 2-norm between frame differences. (a) Continuous three frames of infrared video; (b) estimation results of BrCNN

    Download full size

    • Table 1. Comparison of depth estimation results between BrCNN model and other classical network models

      View table

      Table 1. Comparison of depth estimation results between BrCNN model and other classical network models

      MethodAccuracyError
      ζ<1.25ζ<1.252ζ<1.253MRERMSELE
      BrCNN0.7620.9010.9560.21410.2010.083
      AlexNet[12]0.7370.8730.9080.25810.7970.090
      VGG16[13]0.7190.8680.9120.27410.8420.093
      Res34[14]0.7210.8700.9210.27510.7820.089
    Tools

    Get Citation

    Copy Citation Text

    Shouchuan Wu, Haitao Zhao, Shaoyuan Sun. Depth Estimation from Monocular Infrared Video Based on Bi-Recursive Convolutional Neural Network[J]. Acta Optica Sinica, 2017, 37(12): 1215003

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Set citation alerts for article
    Save article for my favorites
    Paper Information

    Category: Machine Vision

    Received: Jun. 21, 2017

    Accepted: --

    Published Online: Sep. 6, 2018

    The Author Email: Zhao Haitao (haitaozhao@ecust.edu.cn)

    DOI:10.3788/AOS201737.1215003

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology