Regression Tree CNN for Estimation of Ground Sampling Distance Based on Floating-Point Representation

The estimation of ground sampling distance (GSD) from a remote sensing image enables measurement of the size of an object as well as more accurate segmentation in the image. In this paper, we propose a regression tree convolutional neural network (CNN) for estimating the value of GSD from an input image. The proposed regression tree CNN consists of a feature extraction CNN and a binomial tree layer. The proposed network first extracts features from an input image. Based on the extracted features, it predicts the GSD value that is represented by the floating-point number with the exponent and its mantissa. They are computed by coarse scale classification and finer scale regression, respectively, resulting in improved results. Experimental results with a Google Earth aerial image dataset and a mixed dataset consisting of eight remote sensing image public datasets with different GSDs show that the proposed network reduces the GSD prediction error rate by 25% compared to a baseline network that directly estimates the GSD.

Download Full-text

A Spatial-Temporal Attention-Based Method and a New Dataset for Remote Sensing Image Change Detection

Remote Sensing ◽

10.3390/rs12101662 ◽

2020 ◽

Vol 12 (10) ◽

pp. 1662 ◽

Cited By ~ 1

Author(s):

Hao Chen ◽

Zhenwei Shi

Keyword(s):

Remote Sensing ◽

Change Detection ◽

Remote Sensing Image ◽

Google Earth ◽

Large Set ◽

Temporal Attention ◽

Computational Overhead ◽

Image Change Detection ◽

Image Pairs ◽

Public Datasets

Remote sensing image change detection (CD) is done to identify desired significant changes between bitemporal images. Given two co-registered images taken at different times, the illumination variations and misregistration errors overwhelm the real object changes. Exploring the relationships among different spatial–temporal pixels may improve the performances of CD methods. In our work, we propose a novel Siamese-based spatial–temporal attention neural network. In contrast to previous methods that separately encode the bitemporal images without referring to any useful spatial–temporal dependency, we design a CD self-attention mechanism to model the spatial–temporal relationships. We integrate a new CD self-attention module in the procedure of feature extraction. Our self-attention module calculates the attention weights between any two pixels at different times and positions and uses them to generate more discriminative features. Considering that the object may have different scales, we partition the image into multi-scale subregions and introduce the self-attention in each subregion. In this way, we could capture spatial–temporal dependencies at various scales, thereby generating better representations to accommodate objects of various sizes. We also introduce a CD dataset LEVIR-CD, which is two orders of magnitude larger than other public datasets of this field. LEVIR-CD consists of a large set of bitemporal Google Earth images, with 637 image pairs (1024 × 1024) and over 31 k independently labeled change instances. Our proposed attention module improves the F1-score of our baseline model from 83.9 to 87.3 with acceptable computational overhead. Experimental results on a public remote sensing image CD dataset show our method outperforms several other state-of-the-art methods.

Download Full-text

Semantic Multigranularity Feature Learning for High-Resolution Remote Sensing Image Scene Classification

Applied Sciences ◽

10.3390/app11199204 ◽

2021 ◽

Vol 11 (19) ◽

pp. 9204

Author(s):

Xinyi Ma ◽

Zhifeng Xiao ◽

Hong-sik Yun ◽

Seung-Jun Lee

Keyword(s):

Remote Sensing ◽

High Resolution ◽

Spatial Information ◽

Feature Learning ◽

Remote Sensing Image ◽

Input Image ◽

Training Data ◽

Aerial Image ◽

Scene Classification ◽

Feature Maps

High-resolution remote sensing image scene classification is a challenging visual task due to the large intravariance and small intervariance between the categories. To accurately recognize the scene categories, it is essential to learn discriminative features from both global and local critical regions. Recent efforts focus on how to encourage the network to learn multigranularity features with the destruction of the spatial information on the input image at different scales, which leads to meaningless edges that are harmful to training. In this study, we propose a novel method named Semantic Multigranularity Feature Learning Network (SMGFL-Net) for remote sensing image scene classification. The core idea is to learn both global and multigranularity local features from rearranged intermediate feature maps, thus, eliminating the meaningless edges. These features are then fused for the final prediction. Our proposed framework is compared with a collection of state-of-the-art (SOTA) methods on two fine-grained remote sensing image scene datasets, including the NWPU-RESISC45 and Aerial Image Datasets (AID). We justify several design choices, including the branch granularities, fusion strategies, pooling operations, and necessity of feature map rearrangement through a comparative study. Moreover, the overall performance results show that SMGFL-Net consistently outperforms other peer methods in classification accuracy, and the superiority is more apparent with less training data, demonstrating the efficacy of feature learning of our approach.

Download Full-text

Improved YOLO Network for Free-Angle Remote Sensing Target Detection

Remote Sensing ◽

10.3390/rs13112171 ◽

2021 ◽

Vol 13 (11) ◽

pp. 2171

Author(s):

Yuhao Qing ◽

Wenyi Liu ◽

Liuyan Feng ◽

Wanjia Gao

Keyword(s):

Remote Sensing ◽

Feature Extraction ◽

Target Detection ◽

Multiple Scales ◽

Classification Problem ◽

Input Image ◽

Detection Accuracy ◽

Feature Maps ◽

Regression Problem ◽

Public Datasets

Despite significant progress in object detection tasks, remote sensing image target detection is still challenging owing to complex backgrounds, large differences in target sizes, and uneven distribution of rotating objects. In this study, we consider model accuracy, inference speed, and detection of objects at any angle. We also propose a RepVGG-YOLO network using an improved RepVGG model as the backbone feature extraction network, which performs the initial feature extraction from the input image and considers network training accuracy and inference speed. We use an improved feature pyramid network (FPN) and path aggregation network (PANet) to reprocess feature output by the backbone network. The FPN and PANet module integrates feature maps of different layers, combines context information on multiple scales, accumulates multiple features, and strengthens feature information extraction. Finally, to maximize the detection accuracy of objects of all sizes, we use four target detection scales at the network output to enhance feature extraction from small remote sensing target pixels. To solve the angle problem of any object, we improved the loss function for classification using circular smooth label technology, turning the angle regression problem into a classification problem, and increasing the detection accuracy of objects at any angle. We conducted experiments on two public datasets, DOTA and HRSC2016. Our results show the proposed method performs better than previous methods.

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

WSF-NET: Weakly Supervised Feature-Fusion Network for Binary Segmentation in Remote Sensing Image

Remote Sensing ◽

10.3390/rs10121970 ◽

2018 ◽

Vol 10 (12) ◽

pp. 1970 ◽

Cited By ~ 9

Author(s):

Kun Fu ◽

Wanxuan Lu ◽

Wenhui Diao ◽

Menglong Yan ◽

Hao Sun ◽

...

Keyword(s):

Remote Sensing ◽

Feature Fusion ◽

Class Imbalance ◽

Remote Sensing Image ◽

Google Earth ◽

Training Strategy ◽

Binary Segmentation ◽

Supervised Methods ◽

Weakly Supervised ◽

The Given

Binary segmentation in remote sensing aims to obtain binary prediction mask classifying each pixel in the given image. Deep learning methods have shown outstanding performance in this task. These existing methods in fully supervised manner need massive high-quality datasets with manual pixel-level annotations. However, the annotations are generally expensive and sometimes unreliable. Recently, using only image-level annotations, weakly supervised methods have proven to be effective in natural imagery, which significantly reduce the dependence on manual fine labeling. In this paper, we review existing methods and propose a novel weakly supervised binary segmentation framework, which is capable of addressing the issue of class imbalance via a balanced binary training strategy. Besides, a weakly supervised feature-fusion network (WSF-Net) is introduced to adapt to the unique characteristics of objects in remote sensing image. The experiments were implemented on two challenging remote sensing datasets: Water dataset and Cloud dataset. Water dataset is acquired by Google Earth with a resolution of 0.5 m, and Cloud dataset is acquired by Gaofen-1 satellite with a resolution of 16 m. The results demonstrate that using only image-level annotations, our method can achieve comparable results to fully supervised methods.

Download Full-text

Acquisitions of Vegetation Coverage and Cultivated Land Occupation Ratio of Taiyuan Valley Plain for Example Using CBERS-02B CCD Image

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.518-523.5663 ◽

2012 ◽

Vol 518-523 ◽

pp. 5663-5667

Author(s):

Shi Wei Li ◽

Ji Long Zhang ◽

Jian Sheng Yang

Keyword(s):

Remote Sensing ◽

Water Conservation ◽

Vegetation Index ◽

Normalized Difference Vegetation Index ◽

Remote Sensing Image ◽

Google Earth ◽

Vegetation Coverage ◽

Cultivated Land ◽

Land Occupation ◽

Coverage Ratio

Vegetation covering situation is very important for the quality of air quality, soil and water conservation ability and soil forming in an area. By using the remote sensing image of Taiyuan Valley Plain, the application of Normalized Difference Vegetation Index (NDVI) and unsupervised classification, the vegetation coverage map which includes non-cultivated land disposition and cultivated land disposition was obtained using ERDAS Imagine software. To evaluate the accuracy of the results, 200 points were sampled randomly, the high spatial resolution remote sensing image from Google Earth was used as the reference. The overall classification accuracy is 82%, with the Kappa statistic of 0.81. By counting the totally pixel acreage, it was gotten that the vegetation coverage was 46% and the cultivated land coverage ratio was 31% in the study area.

Download Full-text

REMOTE SENSING SCENE CLASSIFICATION USING MULTIPLE PYRAMID POOLING

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-2-w16-279-2019 ◽

2019 ◽

Vol XLII-2/W16 ◽

pp. 279-284

Author(s):

Y. Yao ◽

H. Zhao ◽

D. Huang ◽

Q. Tan

Keyword(s):

Remote Sensing ◽

Spatial Relationship ◽

Image Data ◽

Remote Sensing Image ◽

Input Image ◽

Image Size ◽

Scene Classification ◽

Fixed Size ◽

Fixed Length ◽

Fully Connected

<p><strong>Abstract.</strong> Remote sensing image scene classification has gained remarkable attention, due to its versatile use in different applications like geospatial object detection, ground object information extraction, environment monitoring and etc. The scene not only contains the information of the ground objects, but also includes the spatial relationship between the ground objects and the environment. With rapid growth of the amount of remote sensing image data, the need for automatic annotation methods for image scenes is more urgent. This paper proposes a new framework for high resolution remote sensing images scene classification based on convolutional neural network. To eliminate the requirement of fixed-size input image, multiple pyramid pooling strategy is equipped between convolutional layers and fully connected layers. Then, the fixed-size features generated by multiple pyramid pooling layer was extended to one-dimension fixed-length vector and fed into fully connected layers. Our method could generate a fixed-length representation regardless of image size, at the same time get higher classification accuracy. On UC-Merced and NWPU-RESISC45 datasets, our framework achieved satisfying accuracies, which is 93.24% and 88.62% respectively.</p>

Download Full-text

Remote Sensing Image Scene Classification Based on Global Self-Attention Module

Remote Sensing ◽

10.3390/rs13224542 ◽

2021 ◽

Vol 13 (22) ◽

pp. 4542

Author(s):

Qingwen Li ◽

Dongmei Yan ◽

Wanrong Wu

Keyword(s):

Remote Sensing ◽

Semantic Information ◽

Remote Sensing Image ◽

Global Information ◽

Classification Methods ◽

Scene Classification ◽

Local Perception ◽

Proposed Model ◽

Public Datasets ◽

Fully Connected

The complexity of scene images makes the research on remote-sensing image scene classification challenging. With the wide application of deep learning in recent years, many remote-sensing scene classification methods using a convolutional neural network (CNN) have emerged. Current CNN usually output global information by integrating the depth features extricated from the convolutional layer through the fully connected layer; however, the global information extracted is not comprehensive. This paper proposes an improved remote-sensing image scene classification method based on a global self-attention module to address this problem. The global information is derived from the depth characteristics extracted by the CNN. In order to better express the semantic information of the remote-sensing image, the multi-head self-attention module is introduced for global information augmentation. Meanwhile, the local perception unit is utilized to improve the self-attention module’s representation capabilities for local objects. The proposed method’s effectiveness is validated through comparative experiments with various training ratios and different scales on public datasets (UC Merced, AID, and NWPU-NESISC45). The precision of our proposed model is significantly improved compared to other methods for remote-sensing image scene classification.

Download Full-text

Adaptive Filtering Remote Sensing Image Segmentation Network based on Attention Mechanism

10.5121/csit.2021.110903 ◽

2021 ◽

Author(s):

Cong zhong Wu ◽

Hao Dong ◽

Xuan jie Lin ◽

Han tong Jiang ◽

Li quan Wang ◽

...

Keyword(s):

Remote Sensing ◽

Adaptive Filtering ◽

High Frequency ◽

Remote Sensing Image ◽

Aerial Image ◽

Data Sets ◽

Road Extraction ◽

Image Labeling ◽

Dilated Convolution ◽

Segmentation Accuracy

It is difficult to segment small objects and the edge of the object because of larger-scale variation, larger intra-class variance of background and foreground-background imbalance in the remote sensing imagery. In convolutional neural networks, high frequency signals may degenerate into completely different ones after downsampling. We define this phenomenon as aliasing. Meanwhile, although dilated convolution can expand the receptive field of feature map, a much more complex background can cause serious alarms. To alleviate the above problems, we propose an attention-based mechanism adaptive filtered segmentation network. Experimental results on the Deepglobe Road Extraction dataset and Inria Aerial Image Labeling dataset showed that our method can effectively improve the segmentation accuracy. The F1 value on the two data sets reached 82.67% and 85.71% respectively.

Download Full-text

Remote Sense Image Classification Based on CART Algorithm

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.864-867.2782 ◽

2013 ◽

Vol 864-867 ◽

pp. 2782-2786

Author(s):

Bao Hua Yang ◽

Shuang Li

Keyword(s):

Remote Sensing ◽

Decision Tree ◽

Regression Tree ◽

Remote Sensing Image ◽

Classification And Regression Tree ◽

Classification Method ◽

Remote Sense ◽

Data Source ◽

Cart Algorithm ◽

Tree Method

This papers deals with the study of the algorithm of classification method based on decision tree for remote sensing image. The experimental area is located in the Xiangyang district, the data source for the 2010 satellite images of SPOT and TM fusion. Moreover, classification method based on decision tree is optimized with the help of the module of RuleGen and applied in regional remote sensing image of interest. The precision of Maximum likelihood ratio is 95.15 percent, and 94.82 percent for CRAT. Experimental results show that the classification method based on classification and regression tree method is as well as the traditional one.

Download Full-text