• Laser & Optoelectronics Progress
  • Vol. 58, Issue 12, 1212002 (2021)
Hongsheng Cui and Tao Jiang*
Author Affiliations
  • School of Automation, University of Science and Technology Beijing, Beijing 100083, China
  • show less
    DOI: 10.3788/LOP202158.1212002 Cite this Article Set citation alerts
    Hongsheng Cui, Tao Jiang. Laser Dazzler with Automatic Focal Length Adjustment for Pedestrians[J]. Laser & Optoelectronics Progress, 2021, 58(12): 1212002 Copy Citation Text show less
    Schematic of laser components
    Fig. 1. Schematic of laser components
    Laser component structure diagram
    Fig. 2. Laser component structure diagram
    Haar features applied to pedestrian
    Fig. 3. Haar features applied to pedestrian
    Rectangular feature
    Fig. 4. Rectangular feature
    Schematic of integral graph calculation
    Fig. 5. Schematic of integral graph calculation
    Haar eigenvalue calculation diagram
    Fig. 6. Haar eigenvalue calculation diagram
    Training flowchart of Gentle Adaboost classifier
    Fig. 7. Training flowchart of Gentle Adaboost classifier
    Pedestrian detection test results
    Fig. 8. Pedestrian detection test results
    Diagram of DSP pedestrian detection hardware circuit structure
    Fig. 9. Diagram of DSP pedestrian detection hardware circuit structure
    Diagram of STM32 circuit structure
    Fig. 10. Diagram of STM32 circuit structure
    Automatic focusing control circuit board
    Fig. 11. Automatic focusing control circuit board
    Flow of pedestrian detection program based on DSP
    Fig. 12. Flow of pedestrian detection program based on DSP
    Schematic of STM32 focusing program
    Fig. 13. Schematic of STM32 focusing program
    Test results of single person with different sizes
    Fig. 14. Test results of single person with different sizes
    Test results of multi persons
    Fig. 15. Test results of multi persons
    TargetDetection rate /%False detection rate /%Remarks
    Pedestrians in the image88.69.3200 images
    Pedestrians in the video87.210.15 minutes video
    Table 1. Opencv pedestrian detection test results
    ItemSpeed beforeoptimization /msSpeed afteroptimization /msRemark
    Detection time46568512 frame/s
    Table 2. Comparison of detection speed before and after optimization
    Pedestrian height /pixelLens presetRemarks
    ≥201For a single pedestrian, the pedestrian height is calculated as the size of a single pedestrian. When there are multiple pedestrians, the pedestrian height is calculated based on the largest of the multiple sizes.
    ≥402
    ≥603
    ≥804
    ≥905
    Table 3. Comparison table of target size and lens preset position
    Hongsheng Cui, Tao Jiang. Laser Dazzler with Automatic Focal Length Adjustment for Pedestrians[J]. Laser & Optoelectronics Progress, 2021, 58(12): 1212002
    Download Citation