A Median Regularized Level Set for Hierarchical Segmentation of SAR Images

Braga, Alan M.; Marques, Régis C. P.; Rodrigues, Francisco Alixandre Ávila; Medeiros, Fátima N. S. de

doi:10.1109/lgrs.2017.2702062

Cited by 45 publications

(24 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Remote sensing image processing is a hot issue, which includes many types of tasks, such as image segmentation and object detection. Many scholars have proposed many methods, for example, in [1][2][3][4], researchers have proposed a series of machine learning-based image segmentation methods to improve SAR remote sensing image segmentation. In this paper, we mainly study the object detection of optical remote sensing image based on deep learning.…”

Section: Introductionmentioning

confidence: 99%

RADet: Refine Feature Pyramid Network and Multi-Layer Attention Network for Arbitrary-Oriented Object Detection of Remote Sensing Images

et al. 2020

View full text Add to dashboard Cite

Object detection has made significant progress in many real-world scenes. Despite this remarkable progress, the common use case of detection in remote sensing images remains challenging even for leading object detectors, due to the complex background, objects with arbitrary orientation, and large difference in scale of objects. In this paper, we propose a novel rotation detector for remote sensing images, mainly inspired by Mask R-CNN, namely RADet. RADet can obtain the rotation bounding box of objects with shape mask predicted by the mask branch, which is a novel, simple and effective way to get the rotation bounding box of objects. Specifically, a refine feature pyramid network is devised with an improved building block constructing top-down feature maps, to solve the problem of large difference in scales. Meanwhile, the position attention network and the channel attention network are jointly explored by modeling the spatial position dependence between global pixels and highlighting the object feature, for detecting small object surrounded by complex background. Extensive experiments on two remote sensing public datasets, DOTA and NWPUVHR -10, show our method to outperform existing leading object detectors in remote sensing field.Remote Sens. 2020, 12, 389 2 of 20 for each region of interest (RoI). Then, the features are used to achieve category-specific classification and regression for the corresponding proposals. Finally, the final detection result is obtained through post-processing, such as non-maximum suppression. Faster R-CNN is a classical two-stage object detector, which is composed of Region Proposal Networks (RPN) and a detection network consists of classifiers and regressors, and can detect objects quickly and accurately in an end-to-end manner. Based on Faster R-CNN, more improved two-stage object detectors such as Region-based Fully Convolutional Networks (R-FCN) [7] and Mask R-CNN [8] were proposed. To further improve the efficiency of the object detector, Joseph Redmon et al. proposed a single stage target detector based on regression, called YOLO [9]. For the simple structure, You Only Look Once (YOLO) is extremely fast, but its accuracy is lower than that of the two-stage detector. Based on YOLO, YOLO v3 [10] and YOLO 9000 [11] were proposed successively. To trade off the detection speed and accuracy, Single Shot MultiBox Detector (SSD) [12] was proposed, whose speed and accuracy were between YOLO series algorithm and R-CNN series algorithm.

show abstract

Section: Introductionmentioning

confidence: 99%

RADet: Refine Feature Pyramid Network and Multi-Layer Attention Network for Arbitrary-Oriented Object Detection of Remote Sensing Images

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Offshore and inland river ship detection has been studied on both synthetic aperture radar (SAR) and optical remote sensing imagery. Some alternative methods of machine learning approaches have also been proposed [2][3][4][5]. However, the classic ship detection methods based on SAR images will cause a high segmentation [30], image registration [31,32].…”

Section: Introductionmentioning

confidence: 99%

A Coarse-to-Fine Network for Ship Detection in Optical Remote Sensing Images

Gong

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

With the increasing resolution of optical remote sensing images, ship detection in optical remote sensing images has attracted a lot of research interests. The current ship detection methods usually adopt the coarse-to-fine detection strategy, which firstly extracts low-level and manual features, and then performs multi-step training. Inadequacies of this strategy are that it would produce complex calculation, false detection on land and difficulty in detecting the small size ship. Aiming at these problems, a sea-land separation algorithm that combines gradient information and gray information is applied to avoid false alarms on land, the feature pyramid network (FPN) is used to achieve small ship detection, and a multi-scale detection strategy is proposed to achieve ship detection with different degrees of refinement. Then the feature extraction structure is adopted to fuse different hierarchical features to improve the representation ability of features. Finally, we propose a new coarse-to-fine ship detection network (CF-SDN) that directly achieves an end-to-end mapping from image pixels to bounding boxes with confidences. A coarse-to-fine detection strategy is applied to improve the classification ability of the network. Experimental results on optical remote sensing image set indicate that the proposed method outperforms the other excellent detection algorithms and achieves good detection performance on images including some small-sized ships and dense ships near the port.

show abstract

“…The other provides an effective method for uniting spatial information, texture information, and semantic information in feature detection [24,25], but may complicate the algorithms. Instead of processing the image with individual pixels directly, the object-based method segments the original image into independent objects in which the pixels are addressed as the same land cover in the following processes [26] using different segmentation algorithms [27][28][29][30]. The object-based method has been proved effective for shadow extraction and removal in remote sensing imagery after considerable research.…”

Section: Introductionmentioning

confidence: 99%

Object-Based Shadow Index via Illumination Intensity from High Resolution Satellite Images over Urban Areas

Zhou

Sun

2020

Sensors

View full text Add to dashboard Cite

For multi-spectral remote sensing imagery, accurate shadow extraction is of great significance for overcoming the information loss caused by high buildings and the solar incidence angle in urban remote sensing. However, diverse solar illumination conditions, similarities between shadows, and other dark land features bring uncertainties and deviations to shadow extraction processes and results. In this paper, we classify shadows as either strong or weak based on the ratio between ambient light intensity and direct light intensity, and use the fractal net evolution approach (FNEA), which is a multi-scale segmentation method based on spectral and shape heterogeneity, to reduce the interference of salt and pepper noise and relieve the error of misdiagnosing land covers with high reflectivity in shaded regions as unshaded ones. Subsequently, an object-based shadow index (OSI) is presented according to the illumination intensities of different reflectance features, as well as using the normalized difference water index (NDWI) and near infrared (NIR) band to highlight shadows and eliminate water body interference. The data from three high-spatial-resolution satellites—WorldView-2 (WV-2), WorldView-3 (WV-3), and GaoFen-2 (GF-2)—were used to test the methods and verify the robustness of the OSI. The results show that the OSI index performed well regarding both strong and weak shadows with the user accuracy and the producer accuracy both above 90%, while the four other existing indexes that were tested were not effective at diverse solar illumination conditions. In addition, all the disturbances from water body were excluded well when using the OSI, except for the GF-2 data in weak shadows.

show abstract

A Median Regularized Level Set for Hierarchical Segmentation of SAR Images

Cited by 45 publications

References 26 publications

RADet: Refine Feature Pyramid Network and Multi-Layer Attention Network for Arbitrary-Oriented Object Detection of Remote Sensing Images

RADet: Refine Feature Pyramid Network and Multi-Layer Attention Network for Arbitrary-Oriented Object Detection of Remote Sensing Images

A Coarse-to-Fine Network for Ship Detection in Optical Remote Sensing Images

Object-Based Shadow Index via Illumination Intensity from High Resolution Satellite Images over Urban Areas

Contact Info

Product

Resources

About