Superpixel Boundary-Based Edge Description Algorithm for SAR Image Segmentation

Shang, Ronghua; Lin, Junkai; Jiao, Licheng; Yang, Xiaohui; Li, Yangyang

doi:10.1109/jstars.2020.2987653

Cited by 23 publications

(16 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we demonstrate the performance of our method using two simulated and two real SAR datasets. Five representative methods, including the SLIC-pixel similarity ratio (PSR) [12], the edge-aware superpixel generation (EA) [11], the edge-dominated local clustering (ED) [13], the Fisher vector (FV)-based adaptive superpixel segmentation (FVASS) [16], and the superpixel segmentation method of superpixel boundary-based edge description algorithm (Sp-SpBED) [17] are selected for comparison. Note that the EA and ED methods both consider the edge information for superpixel generation but without considering the SAR image homogeneity.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

“…Wang et al [16] developed a superpixel segmentation approach and extended its application on ship target detection for marine SAR images, which incorporated a Fisher vector to improve low contrast between the ship targets and sea clutter, increasing the discrimination accuracy. Shang et al [17] proposed to use the SLIC algorithm to generate superpixels, and then used strong SAR image edges Superpixel Generation for SAR Imagery Based on Fast DBSCAN Clustering with Edge Penalty Liang Zhang, ShengTao Lu, Canbin Hu, Deliang Xiang, Member, IEEE, Tao Liu, and Yi Su, Senior Member, IEEE I as constraints to calculate the neighborhood weighted mean of each superpixel to achieve the superpixel smoothing. In recent years, there have been proposed some superpixel generation methods based on deep learning models.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Superpixel Generation for SAR Imagery Based on Fast DBSCAN Clustering With Edge Penalty

Zhang

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

In this paper, we propose an adaptive superpixel generation algorithm for synthetic aperture radar (SAR) imagery, which is implemented based on fast Density Based Spatial Clustering of Applications with Noise (DBSCAN) clustering and superpixel merging with edge penalty. The superpixel generation algorithm consists of two stages, i.e., fast pixel clustering and superpixel merging. In the clustering stage, we define a new adaptive pixel dissimilarity measure for SAR image and then optimize the DBSCAN strategy, which considers the edge information and can achieve rapid clustering. In the merging stage, based on the initial superpixels, a new superpixel dissimilarity measure is defined, which can merge the small local superpixels into their neighborhood superpixels, making the final superpixel segmentation results compact and regular. Experimental results on two simulated and two real SAR images demonstrate that our method outperforms the state-of-the-art superpixel generation methods in terms of both efficiency and accuracy. The superpixel segmentation accuracy of our method is 5%-10% higher and the time cost is 10%-40% lower than other methods. Since the superpixel segmentation result can be used as a preprocessing stage for the SAR data interpretation applications, superpixel-based and pixel-based classification results with two real SAR images are also used for comparison, which can validate the advantages of our proposed method.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Superpixel Generation for SAR Imagery Based on Fast DBSCAN Clustering With Edge Penalty

Zhang

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The main idea of the region proposal algorithm (RPA) (Taghizadeh and Chalechale, 2020) is that it can inspect the image to define the regions, where an object is most likely to be located. (Szegedy et al, 2017) This can be achieved by using superpixel algorithm (Shang et al, 2020) for over-segmenting the input image. The RPA is considered to be more efficient than the traditional object detection techniques, i.e., image pyramids and sliding windows for some reasons as: i) the count of generated ROIs is few, ii) it is faster than exhaustively examining every scale/location of the input image, and iii) the amount of accuracy lost is minimal.…”

Section: Region Proposal Algorithm For Roi Generationmentioning

confidence: 99%

Towards a Reliable and Sensitive Deep Learning Based Approach for Multi-Ship Detection in SAR Imagery

Elshafey

2021

IJG

View full text Add to dashboard Cite

Synthetic Aperture Radar (SAR) images show promising results in monitoring maritime activities. Recently, Deep learning-based object detection techniques have impressive results in most detection applications but unfortunately there are challenging problems such as difficulty of detecting multiple ships, especially inshore ones. In this paper, a three-step ship detection process is described and a reliable and sensitive hybrid deep learning model is proposed as an efficient classifier in the middle step. The proposed model combines the finetuned Inception-Resnet-V2 model and the Long Short Term Memory model in two different approaches: parallel approach and cascaded approach. In experiments, the region proposal algorithm and the Non-Maxima suppression algorithm are applied in the first and last step in the three-step detection process. The comparative results show that the proposed approach in cascaded form outperforms the competitive recent state-of-the-art approaches by enhancement up to 16.3%, 16.5%, and 18.9% in terms of recall, precision and mean average precision, respectively. Moreover, the proposed approach shows high relative sensitivity for challenged cases of both inshore and offshore scenes by enhancement ratios up to 81.88% and 24.58%, respectively in recall perspective.

show abstract

“…Yue et al [5] propose a classification method, which achieves a pixel accuracy (PA) of 95.79%, whereas Luo et al [6] achieve an overall accuracy of 95.17%. Other recently proposed method typically reaches an accuracy of above 90% [7][8][9][10][11][12][13].…”

mentioning

confidence: 99%

Analysis of feasibility and advantages of multi‐source image registration using regional features

Zeng

Zhu

et al. 2021

Electronics Letters

View full text Add to dashboard Cite

Automatic registration of multi-source remote sensing data is a challenging task due to the high non-linearity of radiometric differences among various data. Feature extraction is a key enabling technique in registration algorithm design. In this letter, we prove the feasibility of using extracted regional features for multi-source image registration. In particular, regional features can be extracted through pixel-level image classification, and existing off-the-shelf algorithms can be directly adopted. Experiment results demonstrate the robustness of the regionalfeature-based registration method.

show abstract

Superpixel Boundary-Based Edge Description Algorithm for SAR Image Segmentation

Cited by 23 publications

References 38 publications

Superpixel Generation for SAR Imagery Based on Fast DBSCAN Clustering With Edge Penalty

Superpixel Generation for SAR Imagery Based on Fast DBSCAN Clustering With Edge Penalty

Towards a Reliable and Sensitive Deep Learning Based Approach for Multi-Ship Detection in SAR Imagery

Analysis of feasibility and advantages of multi‐source image registration using regional features

Contact Info

Product

Resources

About