Chenfeng Lou, Yong Zhang, Jiaqi Yin. Small Target Detection Method Based on Robinson-Guard Filter and Pixel Convergence[J]. Acta Optica Sinica, 2020, 40(15): 1504001
Search by keywords or author
- Acta Optica Sinica
- Vol. 40, Issue 15, 1504001 (2020)
Fig. 1. Belt noise in image shot by linear array sensor
Fig. 2. Belt noise causes max(z) being too high
Fig. 3. Deviation ratio between MC of circle target with radius of R and ideal value
Fig. 4. Targets with minimum MC when 2≤n≤4. (a) MC=0.3536; (b) MC=0.3849; (c) MC=0.3750
Fig. 5. MC of some typical pixels. (a) MC=0.4033; (b) MC=0.6479; (c) MC=0.8000
Fig. 6. Simulated infrared target in guard band
Fig. 7. Window position shift in low SNR condition. (a) Original image; (b) fusion map of original image and shifted window
Fig. 8. Flowchart of proposed method
Fig. 9. Processing of IR images of birds in clouds. (a1)(a2) Original images; (b1)(b2) heat maps of window distribution; (c1)(c2) target probability maps; (d1)(d2) segmentation results
Fig. 10. Three-dimensional projection of normalized |MTPM| in Figs. 9(c1) and 9(c2). (a) Projection of Fig. 9 (c1); (b) projection of Fig. 9 (c2)
Fig. 11. Simulated images and MTPM for different SNR. (a1) Simulated image with RSNR=0.2; (b1) simulated image with RSNR=0.5; (c1) simulated image with RSNR=1; (d1) simulated image with RSNR=3; (a2) MTPM with RSNR=0.2; (b2) MTPM with RSNR=0.5; (c2) MTPM with RSNR=1; (d2) MTPM with RSNR=3
Fig. 12. Comparison of several target detection methods. (a1)(b1)(c1)(d1) Scenes a,b,c,and d; (a2)(b2)(c2)(d2) NIPPS; (a3)(b3)(c3)(d3) RIPT; (a4)(b4)(c4)(d4) MDTDLMS-RDLCM; (a5)(b5)(c5)(d5) proposed method
Fig. 13. ROC curves of different algorithms
|
Table 1. Detection rates of different methods
|
Table 2. False alarms of different methods
|
Table 3. [in Chinese]
Set citation alerts for the article
Please enter your email address