Volume 18, Issue 3 (12-2021)
JSDP 2021, 18(3): 147-160 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Mahmoodzadeh A. Marine Target Detection in Noisy Infrared Images using a Hybrid Recognition Algorithm. JSDP 2021; 18 (3) :147-160
URL: http://jsdp.rcisp.ac.ir/article-1-1061-en.html
URL: http://jsdp.rcisp.ac.ir/article-1-1061-en.html
Department of Electrical Engineering, Shiraz Branch, Islamic Azad University
Abstract: (1612 Views)
Maritime transportation system is a vital part of the world conveyance. The surveillance in maritime industry and detecting marine targets have a great impact on military and commercial applications. Daily increase in maritime zone encourages the researchers to develop intelligent surveillance approaches in the maritime transportation. The sensing methods generally include visual and infrared cameras, sensors, and radars. Cameras are widely used since they capture high resolution images than sensors and traditional radars. Also, applying complex pattern recognition techniques and decision-making processes to the camera images provides more accurate detection results. Due to the clutters, dust, and weather changes in the sea including the rainfall, snowfall, and heavy fog, the image quality taken by the visual cameras is drastically deteriorated. Also, detecting the sea targets -specially the small ones- and similarly the sea-sky horizon line becomes more challenging. In such situations, the infrared images reveal higher performance and accuracy in comparison with visible images. The sea-sky horizon line detection of noisy infrared images in small target detection algorithms with high intensity and low SNR is of great importance in maritime surveillance. Determining the horizon line simplifies the target detection by restricting the search area for the targets in the image. This task decreases the computation time and mistakes in the detection.
This paper presents a method for detecting marine targets in noisy infrared images. The proposed method includes two steps of detecting the sea-sky horizon line and finding the targets. In the first step, the two-dimensional gradient of the image is computed, from which it is observed that the most variations are appeared at the edge points. With respect to this remark, the maximum of each column of the gradient image is found and the obtained values for all columns and corresponding rows’ numbers are kept in a set, namely the maximum pixels set. Then, to find the sea-sky horizon line, on the first and the last 75 pixels in the mentioned set, a straight line is fitted along the image width. Afterwards, to search for the objects, a region of interest is selected around the detected line. Restricting the search region increases the speed of the proposed method and decreases the number of false alarms. In the second step, this region is partitioned into some separate blocks; from each, multiple features are extracted. These features are fed into multiple classifiers whose outputs are given to a decision-making algorithm based on the interval type-II fuzzy fusion system. This system decides to which class (target or background) that block belongs. Finally, the objects are found by integrating the target blocks and removing the unwanted ones.
To evaluate the proposed method, first an image dataset was generated using an infrared camera with medium wavelength in different situations. This was done due to no access to a complete infrared sea image bank. Sea infrared images were commonly corrupted by a combination of noises including the salt-and-pepper, Gaussian noise or electronic noises due to the detector of camera image supply. In order to attenuate these noises, a 3×3 median filter was applied to the raw image. Afterwards, to increase the image contrast, the histogram equalization method was performed. Finally, the proposed approach was run to find the marine targets in the enhanced image. The results demonstrated that the sea-sky horizon line was detected with low computational complexity and high accuracy while targets were also found with desirable detection rates.
This paper presents a method for detecting marine targets in noisy infrared images. The proposed method includes two steps of detecting the sea-sky horizon line and finding the targets. In the first step, the two-dimensional gradient of the image is computed, from which it is observed that the most variations are appeared at the edge points. With respect to this remark, the maximum of each column of the gradient image is found and the obtained values for all columns and corresponding rows’ numbers are kept in a set, namely the maximum pixels set. Then, to find the sea-sky horizon line, on the first and the last 75 pixels in the mentioned set, a straight line is fitted along the image width. Afterwards, to search for the objects, a region of interest is selected around the detected line. Restricting the search region increases the speed of the proposed method and decreases the number of false alarms. In the second step, this region is partitioned into some separate blocks; from each, multiple features are extracted. These features are fed into multiple classifiers whose outputs are given to a decision-making algorithm based on the interval type-II fuzzy fusion system. This system decides to which class (target or background) that block belongs. Finally, the objects are found by integrating the target blocks and removing the unwanted ones.
To evaluate the proposed method, first an image dataset was generated using an infrared camera with medium wavelength in different situations. This was done due to no access to a complete infrared sea image bank. Sea infrared images were commonly corrupted by a combination of noises including the salt-and-pepper, Gaussian noise or electronic noises due to the detector of camera image supply. In order to attenuate these noises, a 3×3 median filter was applied to the raw image. Afterwards, to increase the image contrast, the histogram equalization method was performed. Finally, the proposed approach was run to find the marine targets in the enhanced image. The results demonstrated that the sea-sky horizon line was detected with low computational complexity and high accuracy while targets were also found with desirable detection rates.
Keywords: Targets detection, Sea-sky horizon line detection, Feature extraction, Classifier, fuzzy inference system
Type of Study: Research |
Subject:
Paper
Received: 2019/08/18 | Accepted: 2021/05/10 | Published: 2022/01/20 | ePublished: 2022/01/20
Received: 2019/08/18 | Accepted: 2021/05/10 | Published: 2022/01/20 | ePublished: 2022/01/20
References
1. [1] Jiao J, Lu H, Wang Z, Zhang W, Qi L. "L0 Gradient Smoothing and Bimodal Histogram Analysis: A Robust Method for Sea-sky-line Detection", InProceedings of the ACM Multi-media Asia, 2019 Dec 15, pp. 1-6 [DOI:10.1145/3338533.3366554]
2. [2] Li F, Zhang J, Sun W, Jin J, Li L, Dai Y, "Sea-sky line detection using gray variation differences in the time domain for unmanned surface vehicles", Signal, Image and Video Processing, no.8, pp.1-8, 2020. [DOI:10.1007/s11760-020-01733-0]
3. [3] B. Wang, Y. Su and L. Wan, "A sea-sky line detection method for unmanned surface vehicles based on gradient saliency," Sensors, vol. 16, no. 4, pp. 543, 2016. [DOI:10.3390/s16040543] [PMID] [PMCID]
4. [4] I. Lipschutz, E. Gershikov and B. Milgrom, "New methods for horizon line detection in infrared and visible sea images," Int. J. Comput. Eng. Res, vol. 3, no. 3, pp. 1197-1215, 2013.
5. [5] Zhu M, Liu B, Wang M, Lu Y. Design and Analysis of Switch Median Filters for Salt and Pepper Noise. InAdvances in Graphic Communication, Printing and Packaging 2019 (pp. 220-226). Springer, Singapore. [DOI:10.1007/978-981-13-3663-8_31]
6. [6] Abdallah MB, Malek J, Azar AT, Belmabrouk H, Monreal JE, Krissian K, "Adaptive noise-reducing anisotropic diffusion filter", Neural Computing and Applications, vol.1;27(5), pp.1273-300. 2016 [DOI:10.1007/s00521-015-1933-9]
7. [7] Z. C. Wang, "A bilateral filtering based image de-noising algorithm for night time infrared monitoring images," in International Con-ference on Computational Science and Compu-tational Intelligence, pp. 199-203, 2014.
8. [8] Bartyzel K. Adaptive kuwahara filter. Signal, Image and Video Processing. 2016 Apr 1;10(4):663-70. [DOI:10.1007/s11760-015-0791-3]
9. [9] Z. Liu, C. Sun, X. Bai and F. Zhou, "Infrared ship target image smoothing based on adaptive mean shift," International Conference on Digital lmage Computing: Techniques and Applications, Nov201, pp.425-27.
10. [10] L. Dong, D. Ma, G. Qin, T. Zhang,W. Xu, "Infrared target detection in backlighting maritime environment based on visual attention model", Infrared Physics & Technology, no,1, pp. 193-200, 2019. [DOI:10.1016/j.infrared.2019.04.018]
11. [11] W.Yang, H. Li, J. Liu, S. Xie, J. Luo , "A sea-sky-line detection method based on Gaussian mixture models and image texture features", International Journal of Advanced Robotic Systems,2019 Dec ;16(6):1729881419892116. [DOI:10.1177/1729881419892116]
12. [12] X. Bai, F. Zhou, Y. Xie, T. Jin, "Adaptive morphological method for clutter elimination to enhance and detect infrared small target," International Conference on Internet Comput-ing in Science and Engineering, pp. 47 - 52, 2008. [DOI:10.1109/ICICSE.2008.28]
13. [13] X. Chen and Y. Wang, "Detection of low contrast targets based on lifting scheme wavelet transform," International Conference on Mechatronics and Automation, pp. 4349 - 4354, 2009.
14. [14] X. Bai and F. Zhou, "Analysis of new top-hat transformation and the application for infrared dim small target detection," Pattern Recog-nition, pp. 2145-2156, 2010. [DOI:10.1016/j.patcog.2009.12.023]
15. [15] X. Kong, L. Liu, Y. Qian and M. Cui, "Automatic detection of sea-sky horizon line and small targets in maritime infrared imagery," Infrared Physics & Technology, pp. 185-199, 2016. [DOI:10.1016/j.infrared.2016.01.016]
16. [16] H. Deng, X. Sun, and X. Zhou, "A multiscale fuzzy metric for detectingsmall infrared targets against chaotic cloudy/sea-sky backgrounds," IEEE Trans. Cybern., vol. 49, no. 5, pp. 1694-1707, May 2019. [DOI:10.1109/TCYB.2018.2810832] [PMID]
17. [17] L. Zhang, L. Peng, T. Zhang, S. Cao, and Z. Peng, "Infrared small tar-get detection via non-convex rank approximation minimization jointl2,1norm," Remote Sens., vol. 10, no. 11, p. 1821, 2018. [DOI:10.3390/rs10111821]
18. [18] P. Du and A. Hamdulla, "Infrared moving small-target detection usingspatial-temporal local difference measure," IEEE Geosci. Remote Sens.Lett., vol. 17, no. 10, pp. 1817-1821, Oct. 2020 [DOI:10.1109/LGRS.2019.2954715]
19. [19] S. Kim, "Analysis of small infrared target features and learning-based false detection removal for infrared search and track," Pattern Analysis and Applications, vol. 17, no. 4, pp. 883-900, 2014. [DOI:10.1007/s10044-013-0361-7]
20. [20] Scherreik MD, Rigling BD. Open set recognition for automatic target classification with rejection. IEEE Transactions on Aerospace and Electronic Systems. 2016 May 26;52(2):632-42. [DOI:10.1109/TAES.2015.150027]
21. [21] R.O. Duda, P.E. Hart, and D.G. Stork, Pattern classification, John Wiley & Sons, 2012.
22. [22] J. Gou, H. Ma, w. Ou, S. Zeng, Y. Rao, H. Yang , A generalized mean distance-based k-nearest neighbor classifier. Expert Systems with Applications. 2019 Jan 1;115:356-72. [DOI:10.1016/j.eswa.2018.08.021]
23. [23] M. Bilal, MS. Hanif, "High performance real-time pedestrian detection using light weight features and fast cascaded kernel SVM classification", Journal of Signal Processing Systems, vol.19, pp.117-29, 2019. [DOI:10.1007/s11265-018-1374-7]
24. [24] M. Khishe, A. Safari , "Classification of sonar targets using an MLP neural network trained by dragonfly algorithm", Wireless Personal Communication, vol.1, pp.2241-60, 2019. [DOI:10.1007/s11277-019-06520-w]
25. [25] Z. Liu, X. Bai, C. Sun, F. Zhou, Y. Li , "Multi-modal ship target image smoothing based on adaptive mean shift", IEEE Access, vol. 18;6, pp. 12573-86, 2018. [DOI:10.1109/ACCESS.2018.2794141]
26. [26] W. Xiao, A. Zaforemska, M. Smigaj, Y. Wang, R. Gaulton, "Mean shift segmentation assessment for individual forest tree delineation from airborne lidar data", Remote Sensing, vol. 11(11), pp.1263, 2019. [DOI:10.3390/rs11111263]
27. [27] P. Melin , E.Ontiveros-Robles ,CI. Gonzalez, JR. Castro, O. Castillo, "An approach for parameterized shadowed type-2 fuzzy membership functions applied in control applications", Soft Computing, vol.1, no-.23(11), pp.3887-901, 2019. [DOI:10.1007/s00500-018-3503-4]
28. [28] V. Gandhi, V. Mendiratta, S. Thakur, Ms. Choudhry, "Morphological Operations For denoising of White Gaussian Noise Corrupted MR Images", In2020 International Con-ference on Electronics and Sustainable Co-mmunication Systems (ICESC), 2020 Jul 2 ,pp. 228-234. [DOI:10.1109/ICESC48915.2020.9155936] [PMID]
29. [29] L. Ltti, C. Koch and E. Niebur, "A model of saliency-based visual attention for rapid scene analysis," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, pp. 1254 - 1259, 1998. [DOI:10.1109/34.730558]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
