• Laser & Optoelectronics Progress
  • Vol. 56, Issue 14, 141502 (2019)
Zhiqiang Zhang* and Wenhua Shi
Author Affiliations
  • 1General Education Center, Zhengzhou Business University, Gongyi, Henan 451200, China
  • show less
    DOI: 10.3788/LOP56.141502 Cite this Article Set citation alerts
    Zhiqiang Zhang, Wenhua Shi. Research and Implementation of Binocular Distance Measurement System Based on Improved Scale-Invariant Feature Transform Algorithm with Parallel Acceleration[J]. Laser & Optoelectronics Progress, 2019, 56(14): 141502 Copy Citation Text show less
    Principle of binocular distance measurement. Solid lines represent light path of left camera and dotted lines represent light path of right camera
    Fig. 1. Principle of binocular distance measurement. Solid lines represent light path of left camera and dotted lines represent light path of right camera
    Flow chart of program
    Fig. 2. Flow chart of program
    Results of key-point detection
    Fig. 3. Results of key-point detection
    Results of key-point matching
    Fig. 4. Results of key-point matching
    Results of community discovery
    Fig. 5. Results of community discovery
    Results of binocular distance measurement
    Fig. 6. Results of binocular distance measurement
    MethodTime consumption/msComplexityError /%
    n = 11n= 21
    Original Gaussian blur24528990O(n×n×W×H)0
    Mean blur5892437O(n×n×W×H)0.04
    Separation mean blur230435O(2×n×W×H)0.04
    Integral mean blur3234O(W×H)0.04
    Table 1. Comparison of time consumption, complexity, and error for four Gaussian blur calculation methods
    ItemProposedalgorithmPrevious workin Ref. [23]
    Convolution core width31×3119×19
    Image size /(pixel×pixel)640×480640×480
    GPU hardwareGT940MGTX560
    Theoretical floating-pointcomputing power /TFlops11
    Time consumption /ms100634
    Table 2. Comparison of time consumption between proposed SIFT algorithm and previous work
    Zhiqiang Zhang, Wenhua Shi. Research and Implementation of Binocular Distance Measurement System Based on Improved Scale-Invariant Feature Transform Algorithm with Parallel Acceleration[J]. Laser & Optoelectronics Progress, 2019, 56(14): 141502
    Download Citation