Multiple Inspection Object Detection Algorithm Based on Hough Transform

Bibo Tian; Yunmeng Liu; Lei Ding

doi:10.3788/LOP240496

Laser & Optoelectronics Progress, Volume. 61, Issue 18, 1837016(2024)

Multiple Inspection Object Detection Algorithm Based on Hough Transform

Bibo Tian^1,2,3, Yunmeng Liu^1,3、**, and Lei Ding^1,2,3、*

¹Key Laboratory of Infrared System Detection and Imaging Technology, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China

²School of Information Science and Technology, ShanghaiTech University, Shanghai 201210, China

³Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(10)

Fig. 1. Straight line extraction diagram of traditional Hough transform algorithm

Download full size

Fig. 2. Peak extraction of the polar coordinate domain with traditional Hough transform algorithm

Download full size

Fig. 3. Flowchart of object detection with improved algorithms

Download full size

Fig. 4. Flow chart of the fast star map matching algorithm

Download full size

Fig. 5. Flow chart of multiple inspection object detection algorithm based on Hough transform

Download full size

Fig. 6. Comparison of the effect of straight line extraction before and after the improvement of the algorithm. (a) Traditional Hough algorithm; (b) proposed algorithm

Download full size

Fig. 7. Star map taken by the outfield CCD camera

Download full size

Table 1. Comparison of algorithm performance
View table
Table 1. Comparison of algorithm performance
Algorithm Accuracy /% False alarm rate /% Time /s
Traditional Hough algorithm 56.8 27.1 3.8932
Traditional Hough algorithm（improve quantification precision） 60.4 25.2 11.3472
Proposed algorithm 92.3 6.8 3.6146

Table 2. Comparison of algorithm performance under different star numbers

View table

Table 2. Comparison of algorithm performance under different star numbers

Star number /（frame×frame）	Traditional Hough algorithm		Proposed algorithm
Star number /（frame×frame）	Accuracy /%	False alarm rate /%	Accuracy /%	False alarm rate /%
5×5	100	0	100	0
10×5	86.0	2.5	100	0
20×5	62.0	18.7	99.2	0.7
30×5	58.7	29.3	98.3	1.3

Table 3. Performance of proposed algorithm under different signal-to-noise ratios
View table
Table 3. Performance of proposed algorithm under different signal-to-noise ratios
SNR Accuracy /% False alarm rate /%
1.5 95.0 4.9
2 96.8 2.8
3 98.1 1.6
4 99.3 0.5
5 100 0

Tools

Get Citation

Copy Citation Text

Bibo Tian, Yunmeng Liu, Lei Ding. Multiple Inspection Object Detection Algorithm Based on Hough Transform[J]. Laser & Optoelectronics Progress, 2024, 61(18): 1837016

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites