Inshore Ship Detection Based on Level Set Method and Visual Saliency for SAR Images
Abstract
:1. Introduction
2. Related Work
2.1. LBF Model
- It is sensitive to initial contour.Figure 1a,d are the original images with different initialization curves (red square). Figure 1b,c are the results after 300 iterations and 3000 iterations. No matter after how many iterations, level set function with initialization curve 1 cannot converge around the targets. Figure 1e is the result of Figure 1d after 300 iterations. It shows that the level set function with initialization curve 2 can well converge around the targets. By comparison, different initialization curves lead to different results. Therefore, it can be concluded that the LBF model is sensitive to initialization curve.
- It has poor performances for SAR images segmentation.This is because the SAR images contain speckle noise, land architectures and have a low signal-to-noise ratio. Even for segmentation results with a proper initialization (as shown in Figure 1e), it still contains lots of clutters (including speckle noise and land architectures).
2.2. ILCM Method
3. Proposed Method
3.1. Fast Initialization
3.2. Improved LSM
3.3. Adaptive Threshold
3.4. Discrimination
- Traverse the entire result image, search all the closed regions and number them , where 0 ≤ ≤ , denotes the number of closed regions.
- Calculate the area size of each region .
- Set two thresholds of area size according to the image type, the smaller one named , and the larger one named .
- If ≤ or ≥ , is determined as a false alarm target and is removed from the detection result. Otherwise, it can be a target and then move to the next region.
- If all of the regions are tested, we can obtain the final detection result.
4. Experiment Results and Discussion
4.1. Results and Analysis of Fast Initialization
- Down-sampling accelerates the speed of computation. Because the number of pixels in the image is greatly reduced.
- Down-sampling can remove the influence of isolated clutter points. For example, rescale the image into one-quarter of the original image, noise whose size is less than one pixel will not appear in the rescaled image.
4.2. Results and Analysis of Proposed LSM
4.3. Results and Analysis of Adaptive Threshold
- The level set method is an active contour model which aim to identify each region of interest by using a certain region descriptor to guide the motion of the active contour [26]. It is different from the method (like CFAR) which needs a pixel-by-pixel comparison, the result of it is consist of regions, so the level set method is more like a region detector.
- The characteristics of the saliency map. For isolated dark spots in the ship targets, a higher saliency value can be obtained by the ILCM algorithm. Because in the formula (4), is the maximum value in the sub0 region, as long as there is one point with a high gray value in the sub0 region, then the salient value of dark spot become larger. In this way, the isolated dark spot inner the ship target also has a higher intensity in the saliency map.
4.4. Results and Analysis of Discrimination
4.5. Results and Analysis of the Whole Proposed Method
4.5.1. Comparison with Other Two Ship Detection Methods
4.5.2. Quantitative Evaluation
4.5.3. Generalization Ability of the Proposed Method
5. Conclusion
Author Contributions
Funding
Conflicts of Interest
References
- Wang, Q.; Zhu, H.; Wu, W.; Zhao, H.; Yuan, N. Inshore ship detection using high-resolution synthetic aperture radar images based on maximally stable extremal region. J. Appl. Remote Sens. 2015, 9, 095094. [Google Scholar] [CrossRef]
- Zhao, H.; Wang, Q.; Huang, J.; Wu, W.; Yuan, N. Method for inshore ship detection based on feature recognition and adaptive background window. J. Appl. Remote Sens. 2014, 8, 083608. [Google Scholar] [CrossRef]
- Shi, H.; Zhang, Q.; Bian, M.; Wang, H.; Wang, Z.; Chen, L.; Yang, J. A Novel Ship Detection Method Based on Gradient and Integral Feature for Single-Polarization Synthetic Aperture Radar Imagery. Sensors 2018, 18, 563. [Google Scholar] [CrossRef] [PubMed]
- Leng, X.; Ji, K.; Zhou, S.; Xing, X.; Zou, H. An Adaptive Ship Detection Scheme for Spaceborne SAR Imagery. Sensors 2016, 16, 1345. [Google Scholar] [CrossRef] [PubMed]
- Wang, J.; Lu, C.; Jiang, W. Simultaneous Ship Detection and Orientation Estimation in SAR Images Based on Attention Module and Angle Regression. Sensors 2018, 18, 2851. [Google Scholar] [CrossRef] [PubMed]
- An, Q.; Pan, Z.; You, H. Ship Detection in Gaofen-3 SAR Images Based on Sea Clutter Distribution Analysis and Deep Convolutional Neural Network. Sensors 2018, 18, 334. [Google Scholar] [CrossRef] [PubMed]
- Zhai, L.; Li, Y.; Su, Y. Inshore ship detection via saliency and context information in high-resolution SAR images. IEEE Geosci. Remote Sens. Lett. 2016, 13, 1870–1874. [Google Scholar] [CrossRef]
- Yu, L.; Fan, G.; Gong, J.; Havlicek, J.P. Joint Infrared Target Recognition and Segmentation Using a Shape Manifold-Aware Level Set. Sensors 2015, 15, 10118–10145. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Osher, S.; Sethian, J.A. Fronts propagating with curvature-dependent speed: Algorithms based on Hamilton-Jacobi formulations. J. Comput. Phys. 1988, 79, 12–49. [Google Scholar] [CrossRef] [Green Version]
- Peng, D.; Merriman, B.; Osher, S.; Zhao, H.; Kang, M. A PDE-Based Fast Local Level Set Method. J. Comput. Phys. 1999, 155, 410–438. [Google Scholar] [CrossRef] [Green Version]
- Adalsteinsson, D.; Sethian, J.A. The Fast Construction of Extension Velocities in Level Set Methods. J. Comput. Phys. 1999, 148, 2–22. [Google Scholar] [CrossRef] [Green Version]
- Chan, T.; Vese, L. An active contour model without edges. In Scale-Space Theories in Computer Vision; Johansen, M., Olsen, P., Weickert, O.F., Eds.; Springer: Berlin, Germany, 1999; pp. 141–151. [Google Scholar]
- Li, C.; Kao, C.Y.; Gore, J.C.; Ding, Z. Implicit active contours driven by local binary fitting energy. In Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA, 17–22 June 2007; pp. 1199–1206. [Google Scholar]
- Li, C.; Kao, C.Y.; Gore, J.C.; Ding, Z. Minimization of region-scalable fitting energy for image segmentation. IEEE Trans. Image Process. 2008, 17, 1940–1949. [Google Scholar] [PubMed]
- Li, C.; Xu, C.; Gui, C.; Fox, M.D. Distance regularized level set evolution and its application to image segmentation. IEEE Trans. Image Process. 2010, 19, 3243–3254. [Google Scholar] [PubMed]
- Lv, H.; Wang, Z.; Fu, S.; Zhang, C.; Zhai, L.; Liu, X. A robust active contour segmentation based on fractional-order differentiation and fuzzy energy. IEEE Access 2017, 5, 7753–7761. [Google Scholar] [CrossRef]
- Wang, L.; Chen, G.; Shi, D.; Chang, Y.; Chan, S.; Pu, J.; Yang, X. Active contours driven by edge entropy fitting energy for image segmentation. Signal Process. 2018, 149, 27–35. [Google Scholar] [CrossRef]
- Yang, L.; An, W.; Lin, Z. Small Target Detection Based on Visual Saliency Improved by Spatial Distance. Acta Optica Sinica 2015, 35, 0715004. [Google Scholar] [CrossRef]
- Li, A.; Chen, Z. Personalized Visual Saliency: Individuality Affects Image Perception. IEEE Access 2018, 6, 16099–16109. [Google Scholar] [CrossRef]
- Li, X.; Li, D.; Yang, Z. A Patch-Based Saliency Detection Method for Assessing the Visual Privacy Levels of Objects in Photos. IEEE Access 2017, 5, 24332–24343. [Google Scholar] [CrossRef]
- Itti, L.; Koch, C.; Niebur, E. A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 1998, 20, 1254–1259. [Google Scholar] [CrossRef] [Green Version]
- Chen, C.; Li, H.; Wei, Y. A local contrast method for small infrared target detection. IEEE Trans. Geosci. Remote Sens 2014, 52, 574–581. [Google Scholar] [CrossRef]
- Han, J.; Ma, Y.; Zhou, B. A Robust Infrared Small Target Detection Algorithm Based on Human Visual System. IEEE Trans. Geosci. Remote Sens. 2014, 1, 2168–2172. [Google Scholar]
- Nie, T.; He, B.; Bi, G. A Method of Ship Detection under Complex Background. ISPRS Int. J. Geo-Inf. 2017, 6, 159. [Google Scholar] [CrossRef]
- Wang, X.; Chen, C. Ship detection for complex background SAR images based on a multiscale variance weighted image entropy method. IEEE Geosci. Remote Sens. Lett. 2017, 14, 184–187. [Google Scholar] [CrossRef]
- Cheng, M.; Zhang, Z.; Lin, W. BING: Binarized normed gradients for objectless estimation at 300 fps. In Proceedings of the IEEE Conference on Computer Vision & Pattern Recognition (CVPR), Columbus, OH, USA, 24–27 June 2014; pp. 3286–3293. [Google Scholar]
- Otsu, N. A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 1979, 9, 62–66. [Google Scholar] [CrossRef]
- Li, C.; Huang, R.; Ding, Z. A level set method for image segmentation in the presence of intensity inhomogeneities with application to MRI. IEEE Trans. Image Process. 2011, 20, 2007–2016. [Google Scholar] [PubMed]
- Qin, X.; Zhou, S.; Zou, H.; Gao, G. A CFAR Detection Algorithm for Generalized Gamma Distributed Background in High-Resolution SAR Images. IEEE Geosci. Remote Sens. Lett. 2013, 10, 806–810. [Google Scholar]
Image Name | Polarization | Band | Size (pixels) | Resolution |
---|---|---|---|---|
Image 1 | HH | X | 235 × 225 | 1.0 m × 1.0 m |
Image 2 | HH | X | 456 × 407 | 1.0 m × 1.0 m |
Image 3 | VV | X | 200 × 200 | 3.0 m × 3.0 m |
Image | K-CFAR | MVWIE | Proposed Method |
---|---|---|---|
image 1 | 63.2/12.0 1 | 80.5/32.3 | 89.5/4.7 |
image 2 | 69.2/4.5 | 91.1/21.2 | 93.5/1.9 |
image 3 | 82.6/3.9 | 95.7/17.8 | 96.2/1.3 |
Image | K-CFAR | MVWIE | Proposed Method |
---|---|---|---|
image 1 | 6.00 | 9.14 | 11.46 |
image 2 | 10.44 | 41.72 | 45.61 |
image 3 | 4.68 | 9.18 | 9.53 |
Images | Polarization | Band | Size (pixels) | Resolution | Location | Year |
---|---|---|---|---|---|---|
Image 4 | HH | X | 364 × 244 | 3.0 m × 3.0 m | Shanghai, China | 2010 |
Image 5 | VV | X | 357 × 381 | 3.0 m × 3.0 m | Kochi, India | 2008 |
Image 6 | HH | X | 175 × 116 | 1.0 m × 1.0 m | Visakhapatnam, India | 2008 |
Image 7 | VV | X | 331 × 292 | 1.0 m × 1.0 m | Kerch, Russia | 2009 |
© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Xie, T.; Zhang, W.; Yang, L.; Wang, Q.; Huang, J.; Yuan, N. Inshore Ship Detection Based on Level Set Method and Visual Saliency for SAR Images. Sensors 2018, 18, 3877. https://doi.org/10.3390/s18113877
Xie T, Zhang W, Yang L, Wang Q, Huang J, Yuan N. Inshore Ship Detection Based on Level Set Method and Visual Saliency for SAR Images. Sensors. 2018; 18(11):3877. https://doi.org/10.3390/s18113877
Chicago/Turabian StyleXie, Tao, Weike Zhang, Linna Yang, Qingping Wang, Jingjian Huang, and Naichang Yuan. 2018. "Inshore Ship Detection Based on Level Set Method and Visual Saliency for SAR Images" Sensors 18, no. 11: 3877. https://doi.org/10.3390/s18113877
APA StyleXie, T., Zhang, W., Yang, L., Wang, Q., Huang, J., & Yuan, N. (2018). Inshore Ship Detection Based on Level Set Method and Visual Saliency for SAR Images. Sensors, 18(11), 3877. https://doi.org/10.3390/s18113877