- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
A top-down approach for semantic segmentation of big remote sensing images
摘要： The increasing amount of remote sensing data has opened the door to new challenging research topics. Nowadays, significant efforts are devoted to pixel and object based classification in case of massive data. This paper addresses the problem of semantic segmentation of big remote sensing images. To do this, we proposed a top-down approach based on two main steps. The first step aims to compute features at the object-level. These features constitute the input of a multi-layer feed-forward network to generate a structure for classifying remote sensing objects. The goal of the second step is to use this structure to label every pixel in new images. Several experiments are conducted based on real datasets and results show good classification accuracy of the proposed approach. In addition, the comparison with existing classification techniques proves the effectiveness of the proposed approach especially for big remote sensing data.
关键词： Neural networks,Remote sensing images,Big data,Semantic segmentation
更新于2025-09-23 15:23:52
-
Geometric accuracy of remote sensing images over oceans: The use of global offshore platforms
摘要： The geometric accuracy of tens of millions of scenes of medium-resolution remote sensing (RS) images collected in the past 45 years has been systematically evaluated for land scenes, but the accuracy of ocean scenes is poorly known due to the lack of ground control points (GCPs). In this study, the locations of offshore platforms are first derived from time-series of Landsat-8 OLI images, and are then used as offshore reference points to systematically assess the geometric performance of RS images covering offshore oil/gas development areas. An inventory of 16,131 offshore platforms at the global scale is established, and then a novel method using the position-invariant characteristic of offshore platforms and the coherent characteristic of the geometric shift among tie-points (i.e. between sensed points from to-be-assessed images and the corresponding OLI-derived reference points) is developed for assessing the geometric accuracy of Landsat and other RS images. The method has been applied to 112,935 Landsat scenes (~1.87% of the entire archive) over oceans. The results indicate an optimal performance of Landsat OLI images (both pre-collection and Collection-1) but a less reliable performance of Landsat TM/ETM+ L1TP images. Approximately 50% of TM L1GS and ETM+ L1GT images have at least 2 pixels of geometric error. The new reference points inventory and the developed method were also applied to many other low-resolution and finer-resolution imagery (e.g. VIIRS Night-fire product, Terra/Aqua MODIS active fire product, ENVISAT ASAR, ALOS-1 PALSAR, Sentinel-1 SAR, Sentinel-2 MSI, the National Agriculture Imagery Program (NAIP) aerial images, and images from several Chinese satellites), and a quantitative description of the geometric accuracy of these sensors is also presented. The findings suggest that the new offshore reference point inventory is probably useful to help establish more robust offshore GCPs for U.S. Geological Survey (USGS) GCP library and further improve the ongoing USGS Global GCP improvement plan and European Space Agency Global Reference Image plan.
关键词： Offshore platforms,Remote sensing images,Landsat,Geometric accuracy,Ground control points
更新于2025-09-23 15:23:52
-
Scale Adaptive Proposal Network for Object Detection in Remote Sensing Images
摘要： Object detection in aerial images is widely applied in many applications. In recent years, faster region convolutional neural network shows a great improvement on object detecting in natural images. Considering the size and distribution characteristic of object in remote sensing images, the region proposal network (RPN) should be changed before being adopted. In this letter, a scale adaptive proposal network (SAPNet) is proposed to improve the accuracy of multiobject detection in remote sensing images. The SAPNet consists of multilayer RPNs which are designed to generate multiscale object proposals, and a ?nal detection subnetwork in which fusion feature layer has been applied for better multiobject detection. Comparative experimental results show that the proposed SAPNet signi?cantly improves the accuracy of multiobject detection.
关键词： region proposal network (RPN),multiobject detection,remote sensing images,Convolution neural network (CNN)
更新于2025-09-23 15:22:29
-
Ship detection based on squeeze excitation skip-connection path networks for optical remote sensing images
摘要： Ship detection plays a crucial role in remote sensing image processing, which has drawn great attention in recent years. A novel neural network architecture named squeeze excitation skip-connection path networks (SESPNets) is proposed. A bottom-up path is added to feature pyramid network to improve feature extraction capability, and path-level skip-connection structure is firstly proposed to enhance information flow and reduce parameter redundancy. Also, squeeze excitation module is adopted, which can adaptively recalibrate channel-wise feature responses by adding an extra branch after each shortcut path connection block. The multi-scale fused region of interest (ROI) align is then proposed to obtain more accurate and multi-scale proposals. Finally, soft-non-maximum suppression is utilized to overcome the problem of non-maximum suppression (NMS) in ship detection. As demonstrated in the experiments, it can be seen that the SESPNets model has achieved the state-of-the-art performance, which shows the effectiveness of proposed method.
关键词： Skip-connection path networks,Squeeze excitation,Ship detection,Optical remote sensing images,Deep learning
更新于2025-09-23 15:22:29
-
Mixed Pixel Decomposition Based on Extended Fuzzy Clustering for Single Spectral Value Remote Sensing Images
摘要： The presence of mixed pixels in remote sensing images is the major issue for accurate classification. In this paper, we have focused on two aspects of mixed pixel problem: firstly, to identify mixed pixels from an image and secondly to label them to their appropriate class. In phase I, extraction of mixed pixels has been performed from the RSI images-based super-pixel algorithm and RGB model by using fuzzy C-means (FCM). In phase II, the extracted mixed pixel from phase I has been decomposed to the appropriate class. This new proposed technique is the amalgamation of PSO-FCM (particle swarm optimization-fuzzy C-means) for clustering of mixed pixels and ANN-BPO (artificial neural network-biogeography-based particle swarm optimization) for the classification purpose. Experimental results reveal that the proposed method has improved the accuracy as compared to the existing techniques and succeeds in better classification of the remote sensing images.
关键词： Fuzzy C-means,BBO,Remote sensing images,Pure pixels,Mixed pixels,PSO,Neural network
更新于2025-09-23 15:22:29
-
A Sample Update-Based Convolutional Neural Network Framework for Object Detection in Large-Area Remote Sensing Images
摘要： This letter addresses the issue of accurate object detection in large-area remote sensing images. Although many convolutional neural network (CNN)-based object detection models can achieve high accuracy in small image patches, the models perform poorly in large-area images due to the large quantity of false and missing detections that arise from complex backgrounds and diverse groundcover types. To address this challenge, this letter proposes a sample update-based CNN (SUCNN) framework for object detection in large-area remote sensing images. The proposed framework contains two stages. In the first stage, a base model—single-shot multibox detector—is trained with the training data set. In the second stage, artificial composite samples are generated to update the training set. The parameters of the first-stage model are fine-tuned with the updated data set to obtain the second-stage model. The first- and second-stage models are evaluated using the large-area remote sensing image test set. Comparison experiments show the effectiveness and superiority of the proposed SUCNN framework for object detection in large-area remote sensing images.
关键词： large-area remote sensing images,sample update,object detection,Convolutional neural networks (CNNs)
更新于2025-09-23 15:22:29
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - A New Registration Algorithm for Multimodal Remote Sensing Images
摘要： Automatic registration of remote sensing images is a challenging problem in the applications of remote sensing. The multimodal remote sensing images have significant nonlinear radiometric differences, which lead to the failure of area-based and feature-based registration methods. In this paper, to overcome significant nonlinear radiometric differences and large scale differences of multimodal remote sensing images, we propose a new registration algorithm, which can meet the need of initial registration of multimodal remote sensing images that conform to similarity transformation model. Our synthetic and real-data experimental results demonstrate the effectiveness and good performance of the proposed method in terms of visualization and registration accuracy.
关键词： multi-scale atlas,phase correlation,Log-Gabor filter,Multimodal remote sensing images,image registration
更新于2025-09-23 15:22:29
-
An efficient pixel clustering-based method for mining spatial sequential patterns from serial remote sensing images
摘要： The accumulation of serial remote sensing images provides plentiful data for discovering sequential spatial patterns in various fields such as agricultural monitoring, urban development, and vegetation cover. Otherwise, traditional sequential pattern-mining algorithms cannot be directly or efficiently applied to remote sensing images. In this study, we propose a pixel clustering-based method to improve the efficiency of mining spatial sequential patterns from raster serial remote sensing images (SRSI). Firstly, the images are compressed by using the Run-Length coding schema. Then, pixels with identical sequences are clustered by means of the Run-length code-based spatial overlay operation. Finally, a pruning strategy is proposed, to extend the prefixSpan algorithm to skip unnecessary database scanning when mining from pixel groups. The experimental results indicate that the method presented in this paper could extract spatial sequential patterns from SRSI efficiently. Although accurate support rates for the patterns may not be obtained, our method could ensure that all patterns are extracted with a lower time cost.
关键词： Sequence mining,Spatial sequential pattern,Pixels cluster,Serial remote sensing images
更新于2025-09-23 15:22:29
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Multi-Attribute Super-Tensor Model for Remote Sensing Image Classification with High Spatial Resolution
摘要： With the development of remote sensors, it is much easier to acquire large amount of remote sensing images (RSIs) with very high spatial resolution, which has made the spatial characteristics play an important role in classification task. Many work of spatial-spectral classification have been done and achieved good results, especially superpixel-based methods. However, these methods didn’t take each superpixel as an entirety, which had ignored the relationship between spatial and spectral signature. It is well known that RSI can be treated as a third-order data cube, thus it can also be represented by a third-order tensor. This paper proposed a Multi-Attribute Superpixel Tensor (MAST) model to address the aforementioned problem. Experiments conducted on two real RSIs and compared with several well-known methods demonstrate the effectiveness of the proposed model.
关键词： remote sensing images,superpixel,spatial-spectral classification,EMAP,tensor
更新于2025-09-23 15:21:21
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Classification of Remote Sensing Images Using Attribute Profiles and Feature Profiles from Different Trees: A Comparative Study
摘要： The motivation of this paper is to conduct a comparative study on remote sensing image classification using the morphological attribute profiles (APs) and feature profiles (FPs) generated from different types of tree structures. Over the past few years, APs have been among the most effective methods to model the image’s spatial and contextual information. Recently, a novel extension of APs called FPs has been proposed by replacing pixel gray-levels with some statistical and geometrical features when forming the output profiles. FPs have been proved to be more efficient than the standard APs when generated from component trees (max-tree and min-tree). In this work, we investigate their performance on the inclusion tree (tree of shapes) and partition trees (alpha tree and omega tree). Experimental results from both panchromatic and hyperspectral images again confirm the efficiency of FPs compared to APs.
关键词： tree representation,classification,Remote sensing images,attribute profiles,feature profiles,attribute filters
更新于2025-09-23 15:21:01