Inshore Ship Detection Based on Level Set Method and Visual Saliency for SAR Images

Xie, Tao; Zhang, Weike; Yang, Linna; Wang, Qingping; Huang, Jingjian; Yuan, Naichang

doi:10.3390/s18113877

Cited by 27 publications

(13 citation statements)

References 28 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to more objectively reflect the adaptability and accuracy of the method. This paper introduced the detection rate J, the false detection rate W of reference [43], and defines the under-detection rate L. The total number of pixels for setting the standard segmentation is S, and the total number of pixels for the segmentation method is M, then:…”

Section: Experiments and Analysis A Imagesmentioning

confidence: 99%

Multi-Scale Adaptive Level Set Segmentation Method Based on Saliency

et al. 2019

View full text Add to dashboard Cite

Image segmentation is an important research of computer vision. Due to the effects of intensity inhomogeneity, target edge and background complex, it is still challenging to achieve effective segmentation of target adaptively. To solve these issues, an image segmentation method based on saliency and level set is proposed in this paper. First, adaptive initial contour of level set is got by wavelet-based feature probability evaluation (WFPE) model, the initial contour is closer to the target contour, which can reduce background interference and evolve faster. Second, in order to realize the best detection of intensity mutation and locate the target edge more accurately, an edge constraint energy term is introduced with multiscale information obtained by wavelet transform. Finally, to improve segmentation adaptability and speed, the region information and edge constraint energy term are merged into the adaptive active contour model, the final evolution curve evolves in coarse scale, and then interpolates to get the final segmentation contour. Experimental results show that the proposed method achieves high efficiency in the following aspects: adaptability to images, speed of evolution, close to human visual perception.

show abstract

Section: Experiments and Analysis A Imagesmentioning

confidence: 99%

Multi-Scale Adaptive Level Set Segmentation Method Based on Saliency

et al. 2019

View full text Add to dashboard Cite

show abstract

“…So far, many traditional SAR ship detection methods have been proposed, e.g., global thresholdbased [36][37][38], constant false alarm ratio (CFAR)-based [39][40][41], generalized likelihood ratio test (GLRT)-based [42][43][44], transformation domain-based [45][46][47], visual saliency-based [48][49][50], super-pixel segmentation-based [51][52][53], and auxiliary feature-based (e.g., ship-wake) [54][55][56], all of which obtained modest results in specific backgrounds, but these methods always extract ship features by hand-designed means, leading to complexity in computation, weakness in generalization, and trouble in manual feature extraction [1,4]. Moreover, as ship wakes do not exist all the time, and their features are not as obvious as ship targets, the research on the detection of ship wakes is not extensive [13].…”

Section: Introductionmentioning

confidence: 99%

LS-SSDD-v1.0: A Deep Learning Dataset Dedicated to Small Ship Detection from Large-Scale Sentinel-1 SAR Images

Zhang

et al. 2020

Remote Sensing

174

View full text Add to dashboard Cite

Ship detection in synthetic aperture radar (SAR) images is becoming a research hotspot. In recent years, as the rise of artificial intelligence, deep learning has almost dominated SAR ship detection community for its higher accuracy, faster speed, less human intervention, etc. However, today, there is still a lack of a reliable deep learning SAR ship detection dataset that can meet the practical migration application of ship detection in large-scene space-borne SAR images. Thus, to solve this problem, this paper releases a Large-Scale SAR Ship Detection Dataset-v1.0 (LS-SSDD-v1.0) from Sentinel-1, for small ship detection under large-scale backgrounds. LS-SSDD-v1.0 contains 15 large-scale SAR images whose ground truths are correctly labeled by SAR experts by drawing support from the Automatic Identification System (AIS) and Google Earth. To facilitate network training, the large-scale images are directly cut into 9000 sub-images without bells and whistles, providing convenience for subsequent detection result presentation in large-scale SAR images. Notably, LS-SSDD-v1.0 has five advantages: (1) large-scale backgrounds, (2) small ship detection, (3) abundant pure backgrounds, (4) fully automatic detection flow, and (5) numerous and standardized research baselines. Last but not least, combined with the advantage of abundant pure backgrounds, we also propose a Pure Background Hybrid Training mechanism (PBHT-mechanism) to suppress false alarms of land in large-scale SAR images. Experimental results of ablation study can verify the effectiveness of the PBHT-mechanism. LS-SSDD-v1.0 can inspire related scholars to make extensive research into SAR ship detection methods with engineering application value, which is conducive to the progress of SAR intelligent interpretation technology. LS-SSDD-v1.0 is available at https://github.com/TianwenZhang0825/LS-SSDD-v1.0-OPEN.

show abstract

“…For example, Xie et al. proposed to combine visual saliency with the level set for inshore ship detection in SAR images [26]. Gao et al.…”

Section: Introductionmentioning

confidence: 99%

A feed‐forward framework integrating saliency and geometry discrimination for shadow detection in SAR images

Zou

et al. 2021

IET Radar Sonar & Navi

View full text Add to dashboard Cite

Shadow has been increasingly a kind of significant aid information for object extraction and scene interpretation in synthetic aperture radar images, which makes SAR shadow detection an important issue. In this paper, we propose a feed‐forward framework integrating saliency and geometry discrimination for shadow detection in SAR images. We firstly develop a global contrast based shadow saliency model to extract suspected shadows. Considering that such suspected regions mostly contain some non‐shadow areas, a discrimination strategy based on geometric relationships between objects and shadows is designed to remove falsely detected areas. Then the remaining regions become the final shadow detection results. Several experiments are carried out on images from two real datasets, Moving and Stationary Target Acquisition Recognition and MiniSAR, to evaluate the performance of our method. From the perspectives of three commonly used metrics, the proposed algorithm comprehensively outperforms two other classic methods, presenting reliable shadow detection ability. Moreover, the detection results of the two classic methods are significantly enhanced in controlling false alarms after the discrimination module is introduced. The results demonstrate that our algorithm is practically applicable to shadow detection in SAR images, and the discrimination strategy can be flexibly extended for related tasks.

show abstract

Inshore Ship Detection Based on Level Set Method and Visual Saliency for SAR Images

Cited by 27 publications

References 28 publications

Multi-Scale Adaptive Level Set Segmentation Method Based on Saliency

Multi-Scale Adaptive Level Set Segmentation Method Based on Saliency

LS-SSDD-v1.0: A Deep Learning Dataset Dedicated to Small Ship Detection from Large-Scale Sentinel-1 SAR Images

A feed‐forward framework integrating saliency and geometry discrimination for shadow detection in SAR images

Contact Info

Product

Resources

About