A Method of Restoring Fuzzy Remote Sensing Image Based on Dark Pixel Prior

Remote sensing image deblurring is a long-term and challenging inverse problem. Among them, the ability to find the correct image prior is the key to recovering high-quality and clear images. Therefore, in order to recover high-quality clear images, this paper has found a new and effective image prior: The dark pixel a priori in remote sensing images and a fuzzy remote sensing image restoration method based on dark pixel prior is proposed. Since the dark pixels in the clear remote sensing image will increase the pixel value of the dark pixels in the blurred remote sensing image due to the weighted balance with the bright pixels around it, the sparsity of the dark pixels in the blurred remote sensing image is reduced. Therefore, by using this nonsparse feature of dark pixels in fuzzy remote sensing images, fuzzy remote sensing images and clear remote sensing images can be effectively distinguished, thus realizing the restoration of fuzzy remote sensing images. The experimental results show that the proposed method has obvious effects on the restoration effect and time.

Download Full-text

MILL: Channel Attention–based Deep Multiple Instance Learning for Landslide Recognition

ACM Transactions on Multimedia Computing Communications and Applications ◽

10.1145/3454009 ◽

2021 ◽

Vol 17 (2s) ◽

pp. 1-11

Author(s):

Xiaochuan Tang ◽

Mingzhe Liu ◽

Hao Zhong ◽

Yuanzhen Ju ◽

Weile Li ◽

...

Keyword(s):

Neural Network ◽

Remote Sensing ◽

Large Scale ◽

Remote Sensing Image ◽

Disaster Risk ◽

Multiple Instance Learning ◽

Remote Sensing Images ◽

Loess Area ◽

Remote Sensing Image Classification ◽

Natural Disaster Risk

Landslide recognition is widely used in natural disaster risk management. Traditional landslide recognition is mainly conducted by geologists, which is accurate but inefficient. This article introduces multiple instance learning (MIL) to perform automatic landslide recognition. An end-to-end deep convolutional neural network is proposed, referred to as Multiple Instance Learning–based Landslide classification (MILL). First, MILL uses a large-scale remote sensing image classification dataset to build pre-train networks for landslide feature extraction. Second, MILL extracts instances and assign instance labels without pixel-level annotations. Third, MILL uses a new channel attention–based MIL pooling function to map instance-level labels to bag-level label. We apply MIL to detect landslides in a loess area. Experimental results demonstrate that MILL is effective in identifying landslides in remote sensing images.

Download Full-text

Remote Sensing Image Retrieval with Gabor-CA-ResNet and Split-Based Deep Feature Transform Network

Remote Sensing ◽

10.3390/rs13050869 ◽

2021 ◽

Vol 13 (5) ◽

pp. 869

Author(s):

Zheng Zhuo ◽

Zhong Zhou

Keyword(s):

Remote Sensing ◽

Image Retrieval ◽

State Of The Art ◽

Remote Sensing Image ◽

Storage Space ◽

Remote Sensing Images ◽

Retrieval Method ◽

Organization Management ◽

Deep Feature ◽

Feature Transform

In recent years, the amount of remote sensing imagery data has increased exponentially. The ability to quickly and effectively find the required images from massive remote sensing archives is the key to the organization, management, and sharing of remote sensing image information. This paper proposes a high-resolution remote sensing image retrieval method with Gabor-CA-ResNet and a split-based deep feature transform network. The main contributions include two points. (1) For the complex texture, diverse scales, and special viewing angles of remote sensing images, A Gabor-CA-ResNet network taking ResNet as the backbone network is proposed by using Gabor to represent the spatial-frequency structure of images, channel attention (CA) mechanism to obtain stronger representative and discriminative deep features. (2) A split-based deep feature transform network is designed to divide the features extracted by the Gabor-CA-ResNet network into several segments and transform them separately for reducing the dimensionality and the storage space of deep features significantly. The experimental results on UCM, WHU-RS, RSSCN7, and AID datasets show that, compared with the state-of-the-art methods, our method can obtain competitive performance, especially for remote sensing images with rare targets and complex textures.

Download Full-text

Research on Remote Sensing Image Matching with Special Texture Background

Symmetry ◽

10.3390/sym13081380 ◽

2021 ◽

Vol 13 (8) ◽

pp. 1380

Author(s):

Sen Wang ◽

Xiaoming Sun ◽

Pengfei Liu ◽

Kaige Xu ◽

Weifeng Zhang ◽

...

Keyword(s):

Remote Sensing ◽

Remote Sensing Image ◽

Geometric Distortion ◽

Reference Image ◽

Remote Sensing Images ◽

Scale Invariant ◽

Sift Algorithm ◽

Speeded Up Robust Features ◽

Adaptive Quantization ◽

Texture Background

The purpose of image registration is to find the symmetry between the reference image and the image to be registered. In order to improve the registration effect of unmanned aerial vehicle (UAV) remote sensing imagery with a special texture background, this paper proposes an improved scale-invariant feature transform (SIFT) algorithm by combining image color and exposure information based on adaptive quantization strategy (AQCE-SIFT). By using the color and exposure information of the image, this method can enhance the contrast between the textures of the image with a special texture background, which allows easier feature extraction. The algorithm descriptor was constructed through an adaptive quantization strategy, so that remote sensing images with large geometric distortion or affine changes have a higher correct matching rate during registration. The experimental results showed that the AQCE-SIFT algorithm proposed in this paper was more reasonable in the distribution of the extracted feature points compared with the traditional SIFT algorithm. In the case of 0 degree, 30 degree, and 60 degree image geometric distortion, when the remote sensing image had a texture scarcity region, the number of matching points increased by 21.3%, 45.5%, and 28.6%, respectively and the correct matching rate increased by 0%, 6.0%, and 52.4%, respectively. When the remote sensing image had a large number of similar repetitive regions of texture, the number of matching points increased by 30.4%, 30.9%, and −11.1%, respectively and the correct matching rate increased by 1.2%, 0.8%, and 20.8% respectively. When processing remote sensing images with special texture backgrounds, the AQCE-SIFT algorithm also has more advantages than the existing common algorithms such as color SIFT (CSIFT), gradient location and orientation histogram (GLOH), and speeded-up robust features (SURF) in searching for the symmetry of features between images.

Download Full-text

A Public Dataset for Fine-Grained Ship Classification in Optical Remote Sensing Images

Remote Sensing ◽

10.3390/rs13040747 ◽

2021 ◽

Vol 13 (4) ◽

pp. 747

Author(s):

Yanghua Di ◽

Zhiguo Jiang ◽

Haopeng Zhang

Keyword(s):

Remote Sensing ◽

Image Data ◽

Remote Sensing Image ◽

Google Earth ◽

Optical Remote Sensing ◽

Remote Sensing Images ◽

Visual Categorization ◽

Class Differences ◽

Fine Grained ◽

Ship Classification

Fine-grained visual categorization (FGVC) is an important and challenging problem due to large intra-class differences and small inter-class differences caused by deformation, illumination, angles, etc. Although major advances have been achieved in natural images in the past few years due to the release of popular datasets such as the CUB-200-2011, Stanford Cars and Aircraft datasets, fine-grained ship classification in remote sensing images has been rarely studied because of relative scarcity of publicly available datasets. In this paper, we investigate a large amount of remote sensing image data of sea ships and determine most common 42 categories for fine-grained visual categorization. Based our previous DSCR dataset, a dataset for ship classification in remote sensing images, we collect more remote sensing images containing warships and civilian ships of various scales from Google Earth and other popular remote sensing image datasets including DOTA, HRSC2016, NWPU VHR-10, We call our dataset FGSCR-42, meaning a dataset for Fine-Grained Ship Classification in Remote sensing images with 42 categories. The whole dataset of FGSCR-42 contains 9320 images of most common types of ships. We evaluate popular object classification algorithms and fine-grained visual categorization algorithms to build a benchmark. Our FGSCR-42 dataset is publicly available at our webpages.

Download Full-text

Hybrid Collaborative Representation for Remote-Sensing Image Scene Classification

Remote Sensing ◽

10.3390/rs10121934 ◽

2018 ◽

Vol 10 (12) ◽

pp. 1934 ◽

Cited By ~ 11

Author(s):

Bao-Di Liu ◽

Wen-Yang Xie ◽

Jie Meng ◽

Ye Li ◽

Yanjiang Wang

Keyword(s):

Remote Sensing ◽

Test Sample ◽

Remote Sensing Image ◽

Image Features ◽

Superior Performance ◽

Collaborative Representation ◽

Great Success ◽

Specific Class ◽

Remote Sensing Images ◽

Training Samples

In recent years, the collaborative representation-based classification (CRC) method has achieved great success in visual recognition by directly utilizing training images as dictionary bases. However, it describes a test sample with all training samples to extract shared attributes and does not consider the representation of the test sample with the training samples in a specific class to extract the class-specific attributes. For remote-sensing images, both the shared attributes and class-specific attributes are important for classification. In this paper, we propose a hybrid collaborative representation-based classification approach. The proposed method is capable of improving the performance of classifying remote-sensing images by embedding the class-specific collaborative representation to conventional collaborative representation-based classification. Moreover, we extend the proposed method to arbitrary kernel space to explore the nonlinear characteristics hidden in remote-sensing image features to further enhance classification performance. Extensive experiments on several benchmark remote-sensing image datasets were conducted and clearly demonstrate the superior performance of our proposed algorithm to state-of-the-art approaches.

Download Full-text

Efficient Patch-Wise Semantic Segmentation for Large-Scale Remote Sensing Images

Sensors ◽

10.3390/s18103232 ◽

2018 ◽

Vol 18 (10) ◽

pp. 3232 ◽

Cited By ~ 17

Author(s):

Yan Liu ◽

Qirui Ren ◽

Jiahui Geng ◽

Meng Ding ◽

Jiangyun Li

Keyword(s):

Remote Sensing ◽

High Resolution ◽

Large Scale ◽

Semantic Segmentation ◽

Remote Sensing Image ◽

Training Data ◽

Land Resources ◽

Remote Sensing Images ◽

Training Strategy ◽

The Impact

Efficient and accurate semantic segmentation is the key technique for automatic remote sensing image analysis. While there have been many segmentation methods based on traditional hand-craft feature extractors, it is still challenging to process high-resolution and large-scale remote sensing images. In this work, a novel patch-wise semantic segmentation method with a new training strategy based on fully convolutional networks is presented to segment common land resources. First, to handle the high-resolution image, the images are split as local patches and then a patch-wise network is built. Second, training data is preprocessed in several ways to meet the specific characteristics of remote sensing images, i.e., color imbalance, object rotation variations and lens distortion. Third, a multi-scale training strategy is developed to solve the severe scale variation problem. In addition, the impact of conditional random field (CRF) is studied to improve the precision. The proposed method was evaluated on a dataset collected from a capital city in West China with the Gaofen-2 satellite. The dataset contains ten common land resources (Grassland, Road, etc.). The experimental results show that the proposed algorithm achieves 54.96% in terms of mean intersection over union (MIoU) and outperforms other state-of-the-art methods in remote sensing image segmentation.

Download Full-text

Performance Evaluation of Single-Label and Multi-Label Remote Sensing Image Retrieval Using a Dense Labeling Dataset

Remote Sensing ◽

10.3390/rs10060964 ◽

2018 ◽

Vol 10 (6) ◽

pp. 964 ◽

Cited By ~ 34

Author(s):

Zhenfeng Shao ◽

Ke Yang ◽

Weixun Zhou

Keyword(s):

Remote Sensing ◽

Performance Evaluation ◽

Deep Learning ◽

Image Retrieval ◽

Semantic Segmentation ◽

Semantic Content ◽

Remote Sensing Image ◽

Remote Sensing Images ◽

Benchmark Datasets ◽

Feature Based

Benchmark datasets are essential for developing and evaluating remote sensing image retrieval (RSIR) approaches. However, most of the existing datasets are single-labeled, with each image in these datasets being annotated by a single label representing the most significant semantic content of the image. This is sufficient for simple problems, such as distinguishing between a building and a beach, but multiple labels and sometimes even dense (pixel) labels are required for more complex problems, such as RSIR and semantic segmentation.We therefore extended the existing multi-labeled dataset collected for multi-label RSIR and presented a dense labeling remote sensing dataset termed "DLRSD". DLRSD contained a total of 17 classes, and the pixels of each image were assigned with 17 pre-defined labels. We used DLRSD to evaluate the performance of RSIR methods ranging from traditional handcrafted feature-based methods to deep learning-based ones. More specifically, we evaluated the performances of RSIR methods from both single-label and multi-label perspectives. These results demonstrated the advantages of multiple labels over single labels for interpreting complex remote sensing images. DLRSD provided the literature a benchmark for RSIR and other pixel-based problems such as semantic segmentation.

Download Full-text

Remote Sensing Image Mosaic Algorithm

Key Engineering Materials ◽

10.4028/www.scientific.net/kem.500.716 ◽

2012 ◽

Vol 500 ◽

pp. 716-721

Author(s):

Yi Ding Wang ◽

Shuai Qin

Keyword(s):

Remote Sensing ◽

High Resolution ◽

Hot Spot ◽

Remote Sensing Image ◽

Processing Algorithm ◽

Geometric Features ◽

Image Mosaic ◽

Post Processing ◽

Remote Sensing Images ◽

Image Pixels

In the field of remote sensing, the acquirement of higher resolution of remote sensing images has become a hot spot issue with widely use of high resolution of remote sensing images. This paper focus on the characteristics of high resolution remote sensing images, on the basis of fully considerate of the correlation between geometric features and image pixels, bring forward a fusion of image mosaic processing algorithm. With this algorithm, the surface features can be well preserved after the processing of mosaic the remote sensing images, and the overlapping area can transit naturally, it will be better for the post-processing, analysis and application.

Download Full-text

MRA-SNet: Siamese Networks of Multiscale Residual and Attention for Change Detection in High-Resolution Remote Sensing Images

Remote Sensing ◽

10.3390/rs13224528 ◽

2021 ◽

Vol 13 (22) ◽

pp. 4528

Author(s):

Xin Yang ◽

Lei Hu ◽

Yongmei Zhang ◽

Yunqing Li

Keyword(s):

Remote Sensing ◽

High Resolution ◽

Change Detection ◽

Remote Sensing Image ◽

Image Features ◽

Remote Sensing Images ◽

The Rich ◽

The Difference ◽

Basic Network ◽

And Performance

Remote sensing image change detection (CD) is an important task in remote sensing image analysis and is essential for an accurate understanding of changes in the Earth’s surface. The technology of deep learning (DL) is becoming increasingly popular in solving CD tasks for remote sensing images. Most existing CD methods based on DL tend to use ordinary convolutional blocks to extract and compare remote sensing image features, which cannot fully extract the rich features of high-resolution (HR) remote sensing images. In addition, most of the existing methods lack robustness to pseudochange information processing. To overcome the above problems, in this article, we propose a new method, namely MRA-SNet, for CD in remote sensing images. Utilizing the UNet network as the basic network, the method uses the Siamese network to extract the features of bitemporal images in the encoder separately and perform the difference connection to better generate difference maps. Meanwhile, we replace the ordinary convolution blocks with Multi-Res blocks to extract spatial and spectral features of different scales in remote sensing images. Residual connections are used to extract additional detailed features. To better highlight the change region features and suppress the irrelevant region features, we introduced the Attention Gates module before the skip connection between the encoder and the decoder. Experimental results on a public dataset of remote sensing image CD show that our proposed method outperforms other state-of-the-art (SOTA) CD methods in terms of evaluation metrics and performance.

Download Full-text

Understanding Urban Growth in Beijing-Tianjin-Hebei Region over the Past 100 Years Using Old Maps and Landsat Data

Remote Sensing ◽

10.3390/rs13163264 ◽

2021 ◽

Vol 13 (16) ◽

pp. 3264 ◽

Cited By ~ 1

Author(s):

Shuang Li ◽

Zhongqiu Sun ◽

Yafei Wang ◽

Yuxia Wang

Keyword(s):

Remote Sensing ◽

Urban Area ◽

Spatial Data ◽

Urban Expansion ◽

Remote Sensing Images ◽

The Past ◽

Old Maps ◽

The World ◽

The City

Studying urban expansion from a longer-term perspective is of great significance to obtain an in-depth understanding of the process of urbanization. Remote sensing data are mostly selected to investigate the long-term expansion of cities. In this study, we selected the world-class urban agglomeration of Beijing-Tianjin-Hebei (BTH) as the study area, and then discussed how to make full use of multi-source, multi-category, and multi-temporal spatial data (old maps and remote sensing images) to study long-term urbanization. Through this study, we addressed three questions: (1) How much has the urban area in BTH expanded in the past 100 years? (2) How did the urban area expand in the past century? (3) What factors or important historical events have changed the development of cities with different functions? By comprehensively using urban spatial data, such as old maps and remote sensing images, geo-referencing them, and extracting built-up area information, a long-term series of urban built-up areas in the BTH region can be obtained. Results show the following: (1) There was clear evidence of dramatic urban expansion in this area, and the total built-up area had increased by 55.585 times, from 126.181 km2 to 7013.832 km2. (2) Continuous outward expansion has always been the main trend, while the compactness of the built-up land within the city is constantly decreasing and the complexity of the city boundary is increasing. (3) Cities in BTH were mostly formed through the construction of city walls during the Ming and Qing dynasties, and the expansion process was mostly highly related to important political events, traffic development, and other factors. In summary, the BTH area, similarly to China and most regions of the world, has experienced rapid urbanization and the history of such ancient cities should be further preserved with the combined use of old maps.

Download Full-text