The visible light camera-based long-range surveillance always suffers from the complex atmosphere. When applying some traditional image enhancement methods, the computational effects behave limited because of their poor environment adaptability. To conquer that problem, a blind image quality (IQ) learning-based multiscale Retinex, i.e. the IQ-learning multiscale Retinex, is proposed. First, a series of typical degenerated images are collected. Second, several blind IQ evaluation metrics are computed for the dataset above. They are the image brightness degree, the image region contrast degree, the image edge blur degree, the image colour quality degree, and the image noise degree. Third, a wavelet transform multi-scale Retinex (WT_MSR) is used to carry out the basic image enhancement. A kind of optimal enhancement is implemented by the subjective evaluation and tuning of multiple optimal control parameters (MOCPs) of WT_MSR for these degenerated dataset. Fourth, the back propagation neural network (BPNN) is used to build a connection between the IQ metrics and the MOCPs. Finally, when a new image is captured, this system will compute its IQ metrics and estimate the MOCPs for the WT_MSR by BPNN; then a kind of optimal enhancement can be realised. Many outdoor applications have shown the effectiveness of proposed method.

References

1. 1)
  - 14. Meylan, L., Susstrunk, S.: ‘High dynamic range image rendering with a Retinex-based adaptive filter’, IEEE Trans. Image Process., 2006, 15, (9), pp. 2820–2830.
2. 2)
  - 17. Gu, K., Zhai, G., Yang, X., et al: ‘Using free energy principle for blind image quality assessment’, IEEE Trans. Multimedia, 2015, 17, (1), pp. 50–63.
3. 3)
  - 15. Li, Y., Sun, J., Meng, X., et al: ‘Face recognition method by combining AMSR with SVM’, Comput. Meas. Control, 2012, 20, (3), pp. 823–825.
4. 4)
  - 12. Jang, I.-S., Lee, T.-H., Ha, H.-G., et al: ‘Adaptive color enhancement based on multi-scaled Retinex using local contrast of the input image’. Proc. Int. Symp. Optomechatronic Technologies, Toronto: Canada, October 2010, pp. 1–6.
5. 5)
  - 13. Lee, C.-H., Shih, J.-L., Lien, C.-C., et al: ‘Adaptive multiscale Retinex for image contrast enhancement’. Proc. Int. Conf. Signal-Image Technology Internet-Based Systems, Kyoto, Japan, December 2013, pp. 43–50.
6. 6)
  - 23. Chen, H., Han, X., Hu, B.: ‘An image retrieval method based on spatial features of colors’. Proc. Int. Symp. Computer Science Computational Technology, Shanghai, China, December 2008, pp. 284–287.
7. 7)
  - 31. Gu, K., Zhai, G., Yang, X., et al: ‘Automatic contrast enhancement technology with saliency preservation’, IEEE Trans. Circuits Syst. Video Technol., 2015, 25, (9), pp. 1480–1494.
8. 8)
  - 30. Wang, L., Yao, X., Meng, Z., et al: ‘An optical coherence tomography attenuation compensation algorithm based on adaptive multi-scale Retinex’, Chin. J. Lasers, 2013, 40, (12), pp. 1204001-1–1204001-6.
9. 9)
  - 20. Gao, C., Panetta, K., Agaian, S.: ‘No reference color image quality measures’. Proc. IEEE Int. Conf. Cybernetics, Lausanne Switzerland, June 2013, pp. 243–248.
10. 10)
  - 24. Nan, D., Bi, D., Zha, Y., et al: ‘A no-reference image quality assessment method based on parameter estimation’, J. Electron. Inf. Technol., 2013, 35, (9), pp. 2066–2072.
11. 11)
  - 18. Liu, H., Cheng, J., Lu, H.: ‘Abnormal change detection of image quality metric series using diffusion process and stopping time theory’. Proc. LNCS Pacific-Rim Conf. Multimedia, Shanghai, China, September 2010, pp. 272–283.
12. 12)
  - 4. He, K., Sun, J., Tang X., : ‘Single image haze removal using dark channel prior’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 33, (12), pp. 2341–2353.
13. 13)
  - 6. Liu, H., Wang, C., Lu, H., et al: ‘Outdoor camera calibration method for a GPS & camera based surveillance system’. Proc. IEEE Int. Conf. Industrial Technology, Vina del Mar, Chile, March 2010, pp. 263–267.
14. 14)
  - 28. Gu, K., Zhai, G., Lin, W., et al: ‘The analysis of image contrast: from quality assessment to automatic enhancement’, IEEE Trans. Cybern., 2016, 46, (1), pp. 284–297.
15. 15)
  - 27. Budiman, F.N., Khan, Y., Malik, N.H., et al: ‘Utilization of artificial neural network for the estimation of size and position metallic particle adhering to spacer in GIS’, IEEE Trans. Dielectr. Electr. Insul., 2013, 20, (6), pp. 2143–2151.
16. 16)
  - 1. Owayjan, M., Freiha, G., Achkar, R., et al: ‘Firoxio: forest fire detection and alerting system’. Proc. IEEE Mediterranean Electrotechnical Conf., Beirut, Lebanon, April 2014, pp. 177–181.
17. 17)
  - 11. Jobson, D.J., Rahman, Z.-U., Woodell, G.A.: ‘Properties and performance of a center/surround Retinex’, IEEE Trans. Image Process., 1997, 6, (3), pp. 451–462.
18. 18)
  - 3. Fattal, R.: ‘Single image dehazing’, ACM Trans. Graph., 2008, 27, (3), pp. 1–9.
19. 19)
  - 29. Mu, C., Wang, J., Yuan, Z., et al: ‘The research of the ATR system based on infrared images and L-M BP neural network’. Proc. Int. Conf. Image Graphics, Qingdao, China, July 2013, pp. 801–805.
20. 20)
  - 26. He, L., Yang, Y.: ‘An improved color image enhancement algorithm based on MSR’. Proc. Int. Symp. Computer Science Computational Technology, Shanghai, China, December 2008, pp. 13–16.
21. 21)
  - 10. Mecocci, A., Molinari, G.: ‘Color recovery in outdoor environments: a novel integrated approach using Retinex, gray world and stretching’. Proc. IEEE Workshop Multimedia Signal Processing, Siena, Italy, September 2004, pp. 75–78.
22. 22)
  - 25. Liu, H., Lu, H.: ‘Imaging air quality evaluation based on noise brightness ratio and Gompertz type diffusion process’. Proc. Int. Congress Image Signal Processing, Yantai, China, October 2010, pp. 2332–2335.
23. 23)
  - 9. Kimmel, R., Elad, M., Shaked, D., et al: ‘A variational framework for Retinex’, Int. J. Comput. Vis., 2003, 52, (1), pp. 7–23.
24. 24)
  - 5. Ancuti, C.O., Ancuti, C., Bekaert, P.: ‘Enhancing by saliency-guided decolorization’. Proc. IEEE Conf. Computer Vision Pattern Recognition, Colorado Springs, USA, June 2011, pp. 257–264.
25. 25)
  - 19. Gu, K., Zhai, G., Yang, X., et al: ‘Hybrid no-reference quality metric for singly and multiple distorted images’, IEEE Trans. Broadcast., 2014, 60, (3), pp. 555–567.
26. 26)
  - 16. Moorthy, A.K., Bovik, A.C.: ‘Blind image quality assessment: from natural scene statistics to perceptual quality’, IEEE Trans. Image Process., 2011, 20, (12), pp. 3350–3364.
27. 27)
  - 21. Gu, K., Wang, S., Zhai, G., et al: ‘Blind quality assessment of tone-mapped images via analysis of information, naturalness, and structure’, IEEE Trans. Multimedia, 2016, 18, (3), pp. 432–443.
28. 28)
  - 8. Land, E.H., McCann, J.J.: ‘Lightness and the Retinex theory’, J. Opt. Soc. Am., 1971, 61, (1), pp. 1–11.
29. 29)
  - 22. Wang, X., Tian, B., Liang, C., et al: ‘Blind image quality assessment for measuring image blur’. Proc. Congress Image Signal Processing, Sanya, Hainan, May 2008, pp. 467–470.
30. 30)
  - 2. Ahmadi, P., Tabandeh, M., Gholampour, I.: ‘Abnormal event detection and localisation in traffic videos based on group sparse topical coding’, IET Image Process., 2016, 10, (3), pp. 235–246.
31. 31)
  - 7. Land, E.H.: ‘The Retinex theory of color vision’, Sci. Am., 1977, 237, pp. 108–128.

Image enhancement for outdoor long-range surveillance using IQ-learning multiscale Retinex

References

Related content