- Research
- Open Access

# Target detection in complex scene of SAR image based on existence probability

- Shuo Liu
^{1}, - Zongjie Cao
^{1}Email author, - Honggang Wu
^{2}, - Yiming Pi
^{1}and - Haiyi Yang
^{1}

**2016**:114

https://doi.org/10.1186/s13634-016-0413-4

© The Author(s). 2016

**Received:**30 April 2016**Accepted:**27 October 2016**Published:**8 November 2016

## Abstract

This study proposes a target detection approach based on the target existence probability in complex scenes of a synthetic aperture radar image. Superpixels are the basic unit throughout the approach and are labelled into each classified scene by a texture feature. The original and predicted saliency depth values for each scene are derived through self-information of all the labelled superpixels in each scene. Thereafter, the target existence probability is estimated based on the comparison of two saliency depth values. Lastly, an improved visual attention algorithm, in which the scenes of the saliency map are endowed with different weights related to the existence probabilities, derives the target detection result. This algorithm enhances the attention for the scene that contains the target. Hence, the proposed approach is self-adapting for complex scenes and the algorithm is substantially suitable for different detection missions as well (e.g. vehicle, ship or aircraft detection in the related scenes of road, harbour or airport, respectively). Experimental results on various data show the effectiveness of the proposed method.

## Keywords

- Target detection
- SAR image
- Self-information
- Superpixel
- Complex scene

## 1 Introduction

Target detection in complex scenes, such as urban areas, airports or harbours, is a challenge in the area of synthetic aperture radar (SAR) image interpretation. Instead of a single scene, such as grassland, farmland or sea, the target detection performance in complex scenes is degraded by using conventional methods. In these complex scenes, the clutter produced by the background may be similar with the targets and are detected as false alarms. For example, the strong reflections of urban building considerably affect vehicle detection. Moreover, the echo waves from various backgrounds overlap and induce strong coherent speckles [1].

To date, many algorithms are adaptive for detecting a specific target in a complex scene by exploring the region of interest (ROI). For these specific target detections (e.g. ship, vehicle and aircraft detections) in a complex scene, the algorithms obtain the ROIs (e.g. ocean, road and airport) by utilising a preprocess module [2–10]. In [2–5], ROIs are obtained by combining the region mask, which is derived using geographic information system (GIS) data and image data. However, the performances of the GIS data-based algorithms are profoundly influenced by the accuracy of the GIS information. These data often suffer from systematic or random positional errors; hence, the region axes have to be realigned to the image [11]. Wang et al. used the Markov random field (MRF) algorithm to extract the ocean scene and detect ships [6]. In [7], the authors achieve the elimination of land areas by filtering the divided sub-image based on the rate of high-intensity pixels. In [8], the SAR image is segmented into N sub-images or regions that comprise high, median or low backscatters based on the k-means programme. The pixels of the targets are detected by the thresholds of the different regions. For these segmentation- or classification-based algorithms, ROI and its characteristics are defined by human experience. That is, the type of target and the possible scenes where the targets exist are predefined before detection. This way, only one algorithm suits one type of target; hence, the range of application and efficiency of the algorithm are unsatisfying.

This study proposes an existence probability-based approach for the SAR image target detection in a complex scene. The existence probability takes the advantage of saliency depth (SD) value to represent the probability that targets exist in a scene. Prior to the estimation of these probabilities, a preprocessing module exists to obtain scenes and arrange the labels of superpixels. Accordingly, an improved visual attention detection algorithm achieves the detection result. The proposed algorithm is self-adapting for complex scenes and for different types of target in the SAR image target detection. The results of the simulated and real SAR data experiments verify the performance of the proposed algorithm.

## 2 Methodology

### 2.1 Preprocessing module

The estimation and detection modules are processed in superpixel elements. Therefore, the generation of superpixels is achieved in the preprocessing module. Compared with a pixel, a superpixel has substantial statistical characteristic, which is the basis for calculating the saliency depth value. Furthermore, the observed object in the visual attention model is replaced by the superpixel from the pixel; hence, the single salient pixels are contained into the un-salient superpixel. In the current study, the superpixels are generated by the simple linear iterative clustering (SLIC) method [12] because they process with limited computational effort and the superpixels adhere to the boundaries well.

In the preprocessing module, each scene that has an approximate background is extracted using the classification algorithm. A dense texture feature extracted through a morphological operation [13], which has been proven suitable for remote-sensing image classification, is opted. Six morphological operations are used in the extraction of features, including opening, closing, opening and closing by reconstruction and opening and closing by top-hat. Meanwhile, the structural elements in the morphological operation comprise square or diamond shapes, and the scales are set at 3 or 7, respectively.

### 2.2 Estimation module

The existence probability of the target is estimated through an SD value of each classified scene, thereby presenting the possibility that a single scene contains the targets. After extracting the outlier information in the scene, the estimation measures original and predicted saliencies. The original SD value of the scene means the existence probability of the scene with potential targets, whereas the predicted SD value derived after excluding the outliers means the probability without targets. Thereafter, a comparison between the two SD values shows the existence probability of the targets.

#### 2.2.1 Self-information of the superpixel

In a relatively homogeneous scene, the intensity distributions of the entire scene are similar to that of most of the superpixels in the scene. In addition, for an SAR image that needs detection, the number of target pixels is limited and the distribution of the target is different from the scene. Therefore, the target superpixels are discriminated by measuring the similarity of distributions between the scene and the superpixels.

*x*with probability

*p*(

*x*), the self-information function is as follows:

Variable sp is the superpixel, variable *s* is the scene and the “|” symbol stands for conditional. After all, the similarity between the superpixel and the scene *S*(sp,*s*) is inversely proportional to its self-information *I*(*sp*|*s*).

The first and second factors indicate the texture and Gaussian distribution components, respectively. The texture in one superpixel was assumed homogenous based on the SLIC algorithm. Therefore, the texture component in (3) can be regard as constant, and then, the pixels in the superpixel could be considered iid.

*I*, which contains

*i*types of scene

*s*

_{ i }, the conditional probability of each superpixel for each scene is calculated by the probabilities of its contained pixels. In addition, the conditional probability of each pixel could be represented by the histogram of the scene, such as

*P*(

**SP**

_{ ij }(

*r*)|

*s*

_{ i }) =

*P*(

*l*|

*s*

_{ i };

**SP**

_{ ij }(

*r*) =

*l*). The variable

**SP**

_{ ij }is the

*j*-th superpixel in scene

*s*

_{ i }, and the variable

**SP**

_{ ij }(

*r*) is the

*r*-th pixel in superpixel

**SP**

_{ ij }. Variable

*l*is the intensity value. Therefore, the pixels with the same intensity have equal probability, the amount of pixels with intensity

*l*equals to

*P*(

*l*|

**SP**

_{ ij }) ⋅

*R*and variable

*R*is the number of pixels in

**SP**

_{ ij }. After accumulating the same probability, the total conditional probability of superpixel is transformed as (4).

Variable *P*(**SP**
_{
ij
}) is the probability of superpixel **SP**
_{
ij
}. The probability is equal to the accumulation of the conditional probability of each pixel **SP**
_{
ij
}(*r*) in the superpixel.

Variable *t* is a constant that is experimentally set as [2,3]; thus, the number of outliers are sufficient to represent the salient level of *s*
_{
i
}; variables *μ*
_{
i
} and *δ*
_{
i
} are the mean and variance, respectively, that are calculated over all the self-information values of the superpixels in *s*
_{
i
}.

#### 2.2.2 SD-value-based existence probability

*q*is the number of the detected outliers and variable

*i*is the types of the scene and threshold Th

_{ i }= t •

*δ*

_{ i }+

*μ*

_{ i }. The SAR image shown in Fig. 2a is tested, and the types of the scenes are

*i*= [1,2,3,4] which correspond to grass, road, tree and shadow, respectively. Each scene is a collection of superpixels that have the same classification label. The SD value of a scene is based on the self-information of these superpixels. The distributions in each scene are shown in Fig. 3. The SD values are calculated as follows: Dep

_{1}≈ 105.1536, Dep

_{2}≈ 26.2686, Dep

_{3}≈ 12.9632 and Dep

_{4}≈ 11.0291. Two targets are located in the grass scene; hence, the SD value of grass is the largest amongst the four scenes. The other scenes have close values because of different thresholds.

Variable *D*
_{
i
} is the new SD value after excluding the outliers in scene *s*
_{
i
}, and *α* is a constant predictive coefficient. The difference between the original and predicted SD value interprets the existence probability of the targets in a scene. When the original value is outstanding beyond the predicted value, the scene is supposed to contain targets. Lastly, the scenes that lack targets are censored, whereas the rates between the differences of the scene with the targets are assigned as weights of the saliency map in the next detection module.

### 2.3 Detection module

Following the idea of saliency in the estimation module, an improved superpixel-based visual attention model is proposed for the SAR image target detection. The proposed model is based on the Itti visual attention model [14], which is commonly used for the salient object detection in an optical image. The structure of the proposed model is shown in the red box of Fig. 1.

*I*with a size of

*m*×

*n*can be decomposed as follows:

*Σ*is a diagonal matrix that comprises eigenvalues and zeros. By retaining the different numbers of the eigenvalue, the low-rank approximate image

*I*(

*p*) that was formed by a different matrix

*Σ*(

*p*) is computed as follows:

The variable *k*
_{
p
} is the number of residual eigenvalue in the matrix *Σ*(*p*). The initial value of the variables are set as follows: *I*(1) = *I*, *Σ*(1) = *Σ* and *k*
_{1} = Rank(*I*). The variable *f* is the degree of the low-rank approximation, which is experimentally set as [0.3, 0.7].

The second improvement is the important information-enhancing component. In the Itti model, after the Gaussian pyramid model, a centre-surround difference component based on the subtraction between the different resolution images extracts the difference, thereby indicating the value in the saliency map. However, the pixels around the targets in the result of the image subtraction are insufficient to be detected. In the SVD-based pyramid, with the increasing layer of the pyramid, the image information is decreasing, whereas the principle component (e.g. the target region) is retained. The important information is enhanced by adding different layers of the SVD pyramid.

*S*

_{ ij }is computed by averaging the saliency of each pixel

*S*

_{ ij }(

*r*) in

**SP**

_{ ij }.

In (13), the saliency of the isolated pixels is averaged into its surrounding, whereas the target superpixels or scene superpixels are homogeneous and have limited influence.

Generally, the saliency map of the proposed model is weighted by the existence probability. The saliency of the high existence probability scene is enhanced whilst the others are depressed; thus, the weighted map reorders the priority of the visual attention detection. With the improved visual attention model, the target detection module is suitable for the SAR image target detection.

## 3 Experimental results

Figure 4b shows the distributions of the self-information value belonging to the five scenes without the targets. Figure 4e, h, k, n show the distributions of the scene with the following targets: grass, bush, road and both bush and road scenes, respectively, and the self-information values of the targets are marked by the red dotted circle in the four figures. By comparing Fig. 4e, h, k, n with Fig. 4b, we can find that the self-information value of the targets are all larger than the self-information value of the backgrounds. Figure 4c shows the original and predicted SD values of all scenes. The colours of the predicted values are displayed in the legend alongside the figures, and the original values are identical cyan coloured. From Fig. 4f, only the original SD value of the grass scene is beyond the predicted value, thereby satisfying the fact in Fig. 4d that the targets are added in the grass scene. A similar situation is shown in Fig. 4i, l, o. Particularly, Fig. 4c shows that no target exists; thus, all original values are lower than the predicted values. By contrast, Fig. 4o shows that two groups of targets appear at the bush and road scenes and the corresponding original values are larger than the predictions. Hence, the existence of targets can make the SD value larger, and the module achieves correct results no matter the target situation or situation where the targets are located in multi-scenes.

^{−3}, 1.5 × 10

^{−3}, 3.2 × 10

^{−3}and 3.9 × 10

^{−3}for Fig. 5b from top to bottom, respectively. This result is due to large intensity contrast and fuzzy edge between the two scenes, as well as the CFAR method that is sensitive to light pixels in the dark background. In the visual attention method results, false alarms occur in the crown area of the tree scene. This result is due to the strong intensity value crown that deduces high saliency, and the false alarm rates are about 1.5 × 10

^{−2}, 1.8 × 10

^{−2}, 1.6 × 10

^{−2}and 1.9 × 10

^{−2}for Fig. 5c from top to bottom, respectively. However, the false alarms caused by the edges or strong intensity areas are filtered out using the proposed method, and the false alarm rates are reduced to less than 1 × 10

^{−3}(Fig. 5c). The edges or strong intensity areas have high saliency, whereas the scenes which they belong to have a lower SD value than the predicted one. Therefore, the existence probability of the targets is low in the scene; hence, these areas are barely considered targets. In summary, the experiments proved that maintaining an acceptable false alarm rate in the complex scenes for the two detection methods is difficult and the proposed approach is suitable for the target detection in complex scenes of the SAR images.

*M*

_{ENL}. Figure 6 shows an original image, a noised image and their detection results of three algorithms, which are the proposed algorithm, CA–CFAR detector based on Rayleigh distribution [16] and AC–CFAR detector based on G

^{0}distribution [15]. In Fig. 6a,

*M*

_{ENL}≈ 2.9, and for Fig. 6f,

*M*

_{ENL}≈ 1.5. Figure 6b, g show the saliency depth value. With the increased noise, the predicted SD values of the grass scene that contains targets are reduced but still higher than the original SD values. The proposed approach remains similar in performance, as shown in Fig. 6c, h, besides some edge pixels of targets were missed. By the results of the CA–CFAR method in Fig. 6d, i, target pixels significantly decrease on the constant false alarm ratio condition. For the AC–CFAR approach, a comparison of Fig. 6e, j suggests that numerous false alarm pixels are emerging and several target pixels are disappearing.

## 4 Conclusions

In this study, the target detection in the complex scene SAR image was focused by estimating the existence probability of the target in each scene. A texture-based classification is used to obtain the scenes firstly. Thereafter, the SD value based on information theory is used to estimate the existence probability. Lastly, an improved visual attention detection module is used to derive the detection result. The proposed method is a superpixel-based approach that maximises the extensive statistical features provided by the superpixel in the estimation module and decreases the false alarm rate in the detection module. By the target existence probability, the focus of visual attention is changed to the scene that contains the target superpixels with high possibility. With these benefits, the proposed approach is suitable for target detection in the complex scene SAR image and is extensively used for different target detection missions.

## Declarations

### Competing interests

The authors declare that they have no competing interests.

**Open Access**This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

## Authors’ Affiliations

## References

- F Argenti, A Lapini, T Bianchi, L Alparone, A tutorial on speckle reduction in synthetic aperture radar images. Geosci Remote Sens Magazine IEEE
**1**(3), 6–35 (2013)View ArticleGoogle Scholar - L Eikvil, L Aurdal, H Koren, Classification-based vehicle detection in high-resolution satellite images. ISPRS J Photogramm Remote Sens
**64**(1), 65–72 (2009)View ArticleGoogle Scholar - L. Xie, L. Wei, Research on vehicle detection in high resolution satellite images”, in Proc. IEEE Int. Conf. on Intelligent Systems, 2013, pp. 279–283.Google Scholar
- J. Leitloff, S. Hinz, U. Stilla, Vehicle queue detection in satellite images of urban areas, in Proc. URS’ 05, pp. 14–16, Mar. 2005Google Scholar
- D. Pastina, F. Fico and P. Lombardo, Detection of ship targets in COSMO-SkyMed SAR images, in Proc. IEEE Radar conf., 2011, pp. 928–933.Google Scholar
- Q Wang et al., Inshore ship detection using high-resolution synthetic aperture radar images based on maximally stable extremal region. J Appl Remote Sens
**9**(1), 1931–3195 (2015)Google Scholar - M Amoon, A Bozorgi, G Rezai-rad, New method for ship detection in synthetic aperture radar imagery based on the human visual attention system. J Appl Remote Sens
**7**, 071599–071599 (2013)View ArticleGoogle Scholar - M Liao, C Wang, Using SAR images to detect ships from sea clutter. IEEE Geosci Remote Sens Lett
**5**(2), 194–198 (2008)View ArticleGoogle Scholar - X Wen, L Shao, X Yu, W Fang, A rapid learning algorithm for vehicle classification. Inform Sci
**295**(1), 395–406 (2015)View ArticleGoogle Scholar - Zhili Zhou, Yunlong Wang, Q.M. Jonathan Wu, Ching-Nung Yang, Xingming Sun, Effective and efficient global context verification for image copy detection, IEEE Transactions on Information Forensics and Security, 2016.Google Scholar
- J Leitloff, S Hinz, U Stilla, Vehicle detection in very high resolution satellite images of city areas. IEEE Trans Geosci Remote Sens
**48**(7), 2795–2806 (2010)View ArticleGoogle Scholar - R Achanta, A Shaji, K Smith, SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Ana Mach Intell
**34**(11), 2274–2282 (2012)View ArticleGoogle Scholar - J. Feng, Z. Cao, Y. Pi, Amplitude and texture feature based SAR image classification with a two-stage approach, in Proc. IEEE Int. Conf. on RADAR, pp. 0360–0364, 2014.Google Scholar
- L Itti, C Koch, E Niebur, A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Pattern Analysis Machine Intell
**20**(11), 1254–1259 (1998)View ArticleGoogle Scholar - G Gao et al., An adaptive and fast CFAR algorithm based on automatic censoring for target detection in high-resolution SAR images. IEEE Trans Geosci Remote Sens
**47**(6), 1685–1697 (2009)View ArticleGoogle Scholar - LM Novak, The automatic target-recognition system in SAIP. Lincoln Lab J
**10**(2), 187–202 (1997)Google Scholar