Object-Based Classification of PolSAR Images Based on Spatial and Semantic Features

Zou, Bin; Xu, Xiaofang; Zhang, Lamei

doi:10.1109/jstars.2020.2968966

Cited by 24 publications

(9 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods try to establish an accurate and effective description of the polarimetric features of land cover. Although these methods can preserve detailed information of images and have obtained good results for the low-resolution PolSAR images, they often generate the salt-and-pepper-like result with high-resolution images because of the highintraclass and lowinterclass variability of image pixels [7]. Also, these conventional methods cannot deal with single-pol SAR images.…”

Section: B Related Workmentioning

confidence: 99%

“…In (7), the r corresponds to the input sample stride, which is equivalent to convolving the input x with upsampled filters produced by inserting r − 1 zeros between two consecutive filter values along each spatial dimension [35]. In a DCNN, the size of field-of-view (FOV) can roughly indicates how much we use context information.…”

Section: B Encoder-decoder Network For Sar Image Semantic Segmentationmentioning

confidence: 99%

“…Conventionally, singlepixel-based land cover classification of PolSAR images takes a single pixel as a processing unit, where the polarimetric scattering mechanism and target decomposition theorems could be used to extract physically plausible features of the pixel [5], [6]. However, PolSAR feature extraction with traditional methods is often limited to the intrapixel regime [7]. In recent years, with the rapid development of deep learning method, region-level land cover classification of PolSAR images have emerged, which takes one image patch as input and utilizes convolutional neural networks (CNNs) to extract high-level features and classify the terrain surface [8], [9].…”

mentioning

confidence: 99%

See 2 more Smart Citations

Object-Level Semantic Segmentation on the High-Resolution Gaofen-3 FUSAR-Map Dataset

Shi

Chen

et al. 2021

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

View full text Add to dashboard Cite

Land cover classification with SAR images mainly focuses on the utilization of fully polarimetric SAR (PolSAR) images. The conventional task of PolSAR classification is single-pixel-based region-level classification using polarimetric target decomposition. In recent years, a large number of high-resolution SAR images have become available, most of which are single-polarization. This article explores the potential of object-level semantic segmentation of high-resolution single-pol SAR images, in particular tailored for the Gaofen-3 (GF-3) sensor. First, a well-annotated GF-3 segmentation dataset "FUSAR-Map" is presented for SAR semantic segmentation. It is based on four data sources: GF-3 single-pol SAR images, Google Earth optical remote sensing images, Google Earth digital maps, and building footprint vector data. It consists of 610 high-resolution GF-3 single-pol SAR images with the size of 1024 × 1024. Second, an encoder-decoder network based on transfer learning is employed to implement semantic segmentation of GF-3 SAR images. For the FUSAR-Map dataset, an optical image pretrained deep convolution neural network (DCNN) is fine-tuned with the SAR training dataset. Experiments on the FUSAR-Map dataset demonstrate the feasibility of object-level semantic segmentation with high-resolution GF-3 single-pol SAR images. Also, our algorithm obtains fourth place about the PolSAR image semantic segmentation on the "2020 Gaofen Challenge on Automated High-Resolution Earth Observation Image Interpretation." The new dataset and the encoder-decoder network are intended as the benchmark data and baseline algorithm for further development of semantic segmentation with high-resolution SAR images. The FUSAR-Map and our algorithm are available at github.com/fudanxu/FUSAR-Map/.

show abstract

Section: B Related Workmentioning

confidence: 99%

Section: B Encoder-decoder Network For Sar Image Semantic Segmentationmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Object-Level Semantic Segmentation on the High-Resolution Gaofen-3 FUSAR-Map Dataset

Shi

Chen

et al. 2021

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

View full text Add to dashboard Cite

show abstract

“…Mundhenk et al [8] also presented a neural network called ResCeption with Inception styled layers to count cars in one pass. Object based image classification (OBIC) by construction of object adjacent graph has been introduced for satellite images [20].…”

Section: B Cnn Models For Aerial Object Detectionmentioning

confidence: 99%

Multisized Object Detection Using Spaceborne Optical Imagery

Haroon

Shahzad

Fraz

2020

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

View full text Add to dashboard Cite

This paper addresses the highly challenging problem of vehicle detection from high resolution remote sensing imagery by introducing a novel medium size annotated dataset named Satellite Imagery Multi-vehicles Dataset (SIMD) along with an adapted single pass deep multi-scale object detection framework with the aim to detect multi sized/type objects for catering above-ground perspective of vehicles. The dataset images are acquired from multiple locations in the EU/US regions available in the public Google Earth satellite imagery. Specifically, it comprises 5,000 images of resolution 1024 x 768 and collectively contains 45,096 objects in 15 different classes of vehicles including cars, trucks, buses, long vehicles, various types of aircrafts and boats. In the proposed architecture, we demonstrate the relevant modifications needed to translate the state-of-the-art object detection frameworks to solve the object detection problem from remote sensing imagery. The proposed architecture has been evaluated on SIMD and a public dataset VEDAI. The comparative analysis has been performed with existing off-theshelf single-shot object detection models including YOLO and YOLT yielding superior performance measured with standard evaluation strategies. To ignite further research in this domain, the introduced SIMD dataset and the corresponding architecture is publicly available at this link: http://vision.seecs.edu.pk/simd.

show abstract

“…Thus, more target scattering characteristics can be provided for image classification. In recent years, PolSAR system have been widely used in image classification [1], target recognition [2], land cover mapping and so forth. Existing PolSAR image classification methods including unsupervised and supervised methods have been widely put foreword.…”

Section: Introductionmentioning

confidence: 99%

Riemannian Nearest-Regularized Subspace Classification for Polarimetric SAR images

Shi¹,

Huang²

2022

Preprint

View full text Add to dashboard Cite

As a representation learning method, nearest regularized subspace (NRS) algorithm is an effective tool to obtain both accuracy and speed for PolSAR image classification. However, existing NRS methods use the polarimetric feature vector but the PolSAR original covariance matrix (known as Hermitian positive definite (HPD) matrix) as the input. Without considering the matrix structure, existing NRS-based methods cannot learn correlation among channels. How to utilize the original covariance matrix to NRS method is a key problem. To address this limit, a Riemannian NRS method is proposed, which consider the HPD matrices endow in the Riemannian space. Firstly, to utilize the PolSAR original data, a Riemannian NRS method(RNRS) is proposed by constructing HPD dictionary and HPD distance metric. Secondly, a new Tikhonov regularization term is designed to reduce the differences within the same class. Finally, the optimal method is developed and the first-order derivation is inferred. During the experimental test, only T matrix is used in the proposed method, while multiple of features are utilized for compared methods. Experimental results demonstrate the proposed method can outperform the state-of-art algorithms even using less features.

show abstract

Object-Based Classification of PolSAR Images Based on Spatial and Semantic Features

Cited by 24 publications

References 38 publications

Object-Level Semantic Segmentation on the High-Resolution Gaofen-3 FUSAR-Map Dataset

Object-Level Semantic Segmentation on the High-Resolution Gaofen-3 FUSAR-Map Dataset

Multisized Object Detection Using Spaceborne Optical Imagery

Riemannian Nearest-Regularized Subspace Classification for Polarimetric SAR images

Contact Info

Product

Resources

About