Laser & Optoelectronics Progress, Volume. 55, Issue 6, 061010(2018)

Depth Estimation of Single Infrared Image Based on Interframe Information Extraction

Tingting Gu1、1; , Haitao Zhao1、1; , and Shaoyuan Sun2、2;
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

    In view of lacking of the texture information and the edge information in the infrared image, the accuracy of depth estimation is hard to be improved. We propose a deep neural network to estimate the depth of infrared images. The network combines a two-dimensional (2D) residual neural network and a three-dimensional(3D) convolution neural network. The traditional methods of estimating the depth of a single infrared image omits the interframe information and is prone to fuzzy or even missing object contour. The 2D and 3D network inputs are added dense optical flow and the frame before and after the image, respectively. Secondly, the feature map extracted from the 3D convolutional network is further connected to the feature maps of the 2D residual network. Unlike the fully connected layer of the traditional neural network, fully convolutional layer breaks through the size constraints of the input. The experimental results show that the accuracy of the proposed infrared image depth estimation method is improved, and the object contour estimated is clear and complete.

    Tools

    Get Citation

    Copy Citation Text

    Tingting Gu, Haitao Zhao, Shaoyuan Sun. Depth Estimation of Single Infrared Image Based on Interframe Information Extraction[J]. Laser & Optoelectronics Progress, 2018, 55(6): 061010

    Download Citation

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

    Category: Image Processing

    Received: Nov. 21, 2017

    Accepted: --

    Published Online: Sep. 11, 2018

    The Author Email: Gu Tingting (18751973506@163.com)

    DOI:10.3788/LOP55.061010

    Topics