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

Laser & Optoelectronics Progress, Volume. 56, Issue 8, 081501(2019)

Road Scene Depth Estimation Based on Deep Convolutional Neural Networks

Jianzhong Yuan1, Wujie Zhou1,2、*, Ting Pan1, and Pengli Gu1
Author Affiliations
  • 1 School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou, Zhejiang 310023, China
  • 2 College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, Zhejiang 310027, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (7)
    Equations (0)
    References (44)
    Cited By (4)
    Tools
    Paper Information
    Topics
    Figures & Tables(7)
    Structural diagram of neural network

    Fig. 1. Structural diagram of neural network

    Download full size
    Two types of network blocks. (a) Identity_block; (b) Conv_block

    Fig. 2. Two types of network blocks. (a) Identity_block; (b) Conv_block

    Download full size
    Schematic of N-layer Dense_block

    Fig. 3. Schematic of N-layer Dense_block

    Download full size
    Schematic of TransitionUp

    Fig. 4. Schematic of TransitionUp

    Download full size
    Experimental results. (a) RGB image; (b) ground truth; (c) depth prediction map

    Fig. 5. Experimental results. (a) RGB image; (b) ground truth; (c) depth prediction map

    Download full size

    • Table 1. Depth estimation results on KITTI dataset

      View table

      Table 1. Depth estimation results on KITTI dataset

      MethodAccuracy (higher is better)Error (lower is better)
      δ<1.25δ<1.252δ<1.253RrmsRlog_rmsElg
      Ref. [24]0.4880.9470.9722.64400.2720.167
      Ref. [41]0.6740.9430.9722.46180.2430.126
      Ref. [42]0.6400.9470.9792.51930.2470.134
      Ref. [43]0.6340.9160.9452.82460.3050.127
      Ref. [44]0.5660.9450.9702.65070.2640.145
      Proposed0.7170.9470.9742.42250.2340.111

    • Table 2. Depth estimation results of slice experiment

      View table

      Table 2. Depth estimation results of slice experiment

      MethodAccuracy (higher is better)Error (lower is better)
      δ<1.25δ<1.252δ<1.253RrmsRlog_rmsElg
      Proposed0.7170.9470.9742.42250.2340.111
      Proposed10.6960.9410.9712.38770.2420.124
      Proposed20.6780.9460.9742.4120.2370.122
    Tools

    Get Citation

    Copy Citation Text

    Jianzhong Yuan, Wujie Zhou, Ting Pan, Pengli Gu. Road Scene Depth Estimation Based on Deep Convolutional Neural Networks[J]. Laser & Optoelectronics Progress, 2019, 56(8): 081501

    Download Citation

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

    Category: Machine Vision

    Received: Nov. 2, 2018

    Accepted: Nov. 22, 2018

    Published Online: Jul. 26, 2019

    The Author Email: Wujie Zhou (wujiezhou@163.com)

    DOI:10.3788/LOP56.081501

    Topics

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