Extracting Building Areas from Photogrammetric DSM and DOM by Automatically Selecting Training Samples from Historical DLG Data

This paper presents an automatic building extraction method which utilizes a photogrammetric digital surface model (DSM) and digital orthophoto map (DOM) with the help of historical digital line graphic (DLG) data. To reduce the need for manual labeling, the initial labels were automatically obtained from historical DLGs. Nonetheless, a proportion of these labels are incorrect due to changes (e.g., new constructions, demolished buildings). To select clean samples, an iterative method using random forest (RF) classifier was proposed in order to remove some possible incorrect labels. To get effective features, deep features extracted from normalized DSM (nDSM) and DOM using the pre-trained fully convolutional networks (FCN) were combined. To control the computation cost and alleviate the burden of redundancy, the principal component analysis (PCA) algorithm was applied to reduce the feature dimensions. Three data sets in two areas were employed with evaluation in two aspects. In these data sets, three DLGs with 15%, 65%, and 25% of noise were applied. The results demonstrate the proposed method could effectively select clean samples, and maintain acceptable quality of extracted results in both pixel-based and object-based evaluations.

Download Full-text

JointL1/2-Norm Constraint and Graph-Laplacian PCA Method for Feature Extraction

BioMed Research International ◽

10.1155/2017/5073427 ◽

2017 ◽

Vol 2017 ◽

pp. 1-14 ◽

Cited By ~ 1

Author(s):

Chun-Mei Feng ◽

Ying-Lian Gao ◽

Jin-Xing Liu ◽

Juan Wang ◽

Dong-Qin Wang ◽

...

Keyword(s):

Feature Extraction ◽

Error Function ◽

Principal Component ◽

Graph Laplacian ◽

Specific Gene ◽

Data Sets ◽

Pca Method ◽

Norm Constraint ◽

Alm Method ◽

Pca Algorithm

Principal Component Analysis (PCA) as a tool for dimensionality reduction is widely used in many areas. In the area of bioinformatics, each involved variable corresponds to a specific gene. In order to improve the robustness of PCA-based method, this paper proposes a novel graph-Laplacian PCA algorithm by adoptingL1/2constraint (L1/2gLPCA) on error function for feature (gene) extraction. The error function based onL1/2-norm helps to reduce the influence of outliers and noise. Augmented Lagrange Multipliers (ALM) method is applied to solve the subproblem. This method gets better results in feature extraction than other state-of-the-art PCA-based methods. Extensive experimental results on simulation data and gene expression data sets demonstrate that our method can get higher identification accuracies than others.

Download Full-text

A Novel Object-Based Deep Learning Framework for Semantic Segmentation of Very High-Resolution Remote Sensing Data: Comparison with Convolutional and Fully Convolutional Networks

Remote Sensing ◽

10.3390/rs11060684 ◽

2019 ◽

Vol 11 (6) ◽

pp. 684 ◽

Cited By ~ 17

Author(s):

Maria Papadomanolaki ◽

Maria Vakalopoulou ◽

Konstantinos Karantzalos

Keyword(s):

Deep Learning ◽

State Of The Art ◽

Semantic Segmentation ◽

Novel Object ◽

Convolutional Networks ◽

Learning Framework ◽

Fully Convolutional Networks ◽

Object Based ◽

Deep Networks ◽

Very High

Deep learning architectures have received much attention in recent years demonstrating state-of-the-art performance in several segmentation, classification and other computer vision tasks. Most of these deep networks are based on either convolutional or fully convolutional architectures. In this paper, we propose a novel object-based deep-learning framework for semantic segmentation in very high-resolution satellite data. In particular, we exploit object-based priors integrated into a fully convolutional neural network by incorporating an anisotropic diffusion data preprocessing step and an additional loss term during the training process. Under this constrained framework, the goal is to enforce pixels that belong to the same object to be classified at the same semantic category. We compared thoroughly the novel object-based framework with the currently dominating convolutional and fully convolutional deep networks. In particular, numerous experiments were conducted on the publicly available ISPRS WGII/4 benchmark datasets, namely Vaihingen and Potsdam, for validation and inter-comparison based on a variety of metrics. Quantitatively, experimental results indicate that, overall, the proposed object-based framework slightly outperformed the current state-of-the-art fully convolutional networks by more than 1% in terms of overall accuracy, while intersection over union results are improved for all semantic categories. Qualitatively, man-made classes with more strict geometry such as buildings were the ones that benefit most from our method, especially along object boundaries, highlighting the great potential of the developed approach.

Download Full-text

An Object-Based Image Analysis Method for Enhancing Classification of Land Covers Using Fully Convolutional Networks and Multi-View Images of Small Unmanned Aerial System

Remote Sensing ◽

10.3390/rs10030457 ◽

2018 ◽

Vol 10 (3) ◽

pp. 457 ◽

Cited By ~ 15

Author(s):

Tao Liu ◽

Amr Abd-Elrahman

Keyword(s):

Image Analysis ◽

Unmanned Aerial System ◽

Analysis Method ◽

Image Analysis Method ◽

Convolutional Networks ◽

Object Based Image Analysis ◽

Fully Convolutional Networks ◽

Object Based ◽

Land Covers

Download Full-text

Comparing fully convolutional networks, random forest, support vector machine, and patch-based deep convolutional neural networks for object-based wetland mapping using images from small unmanned aircraft system

GIScience & Remote Sensing ◽

10.1080/15481603.2018.1426091 ◽

2018 ◽

Vol 55 (2) ◽

pp. 243-264 ◽

Cited By ~ 71

Author(s):

Tao Liu ◽

Amr Abd-Elrahman ◽

Jon Morton ◽

Victor L. Wilhelm

Keyword(s):

Neural Networks ◽

Support Vector Machine ◽

Unmanned Aircraft ◽

Support Vector ◽

Wetland Mapping ◽

Deep Convolutional Neural Networks ◽

Convolutional Networks ◽

Fully Convolutional Networks ◽

Object Based ◽

Aircraft System

Download Full-text

BUILDING CLASSIFICATION OF VHR AIRBORNE STEREO IMAGES USING FULLY CONVOLUTIONAL NETWORKS AND FREE TRAINING SAMPLES

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

10.5194/isprs-archives-xlii-4-87-2018 ◽

2018 ◽

Vol XLII-4 ◽

pp. 87-92

Author(s):

Y. Chen ◽

W. Gao ◽

E. Widyaningrum ◽

M. Zheng ◽

K. Zhou

Keyword(s):

Large Scale ◽

Semantic Segmentation ◽

Fine Tuning ◽

Stereo Images ◽

Convolutional Networks ◽

Fully Convolutional Networks ◽

Area Of Interest ◽

Learning Rates ◽

Training Samples ◽

Benchmark Datasets

Abstract. Semantic segmentation, especially for buildings, from the very high resolution (VHR) airborne images is an important task in urban mapping applications. Nowadays, the deep learning has significantly improved and applied in computer vision applications. Fully Convolutional Networks (FCN) is one of the tops voted method due to their good performance and high computational efficiency. However, the state-of-art results of deep nets depend on the training on large-scale benchmark datasets. Unfortunately, the benchmarks of VHR images are limited and have less generalization capability to another area of interest. As existing high precision base maps are easily available and objects are not changed dramatically in an urban area, the map information can be used to label images for training samples. Apart from object changes between maps and images due to time differences, the maps often cannot perfectly match with images. In this study, the main mislabeling sources are considered and addressed by utilizing stereo images, such as relief displacement, different representation between the base map and the image, and occlusion areas in the image. These free training samples are then fed to a pre-trained FCN. To find the better result, we applied fine-tuning with different learning rates and freezing different layers. We further improved the results by introducing atrous convolution. By using free training samples, we achieve a promising building classification with 85.6% overall accuracy and 83.77% F1 score, while the result from ISPRS benchmark by using manual labels has 92.02% overall accuracy and 84.06% F1 score, due to the building complexities in our study area.

Download Full-text

Fully Convolutional Networks and Geographic Object-Based Image Analysis for the Classification of VHR Imagery

Remote Sensing ◽

10.3390/rs11050597 ◽

2019 ◽

Vol 11 (5) ◽

pp. 597 ◽

Cited By ~ 21

Author(s):

Nicholus Mboga ◽

Stefanos Georganos ◽

Tais Grippa ◽

Moritz Lennert ◽

Sabine Vanhuysse ◽

...

Keyword(s):

Democratic Republic Of Congo ◽

State Of The Art ◽

Computational Cost ◽

Convolutional Networks ◽

Object Based Image Analysis ◽

Fully Convolutional Networks ◽

Object Based ◽

Geographic Object ◽

End To End ◽

Future Work

Land cover Classified maps obtained from deep learning methods such as Convolutional neural networks (CNNs) and fully convolutional networks (FCNs) usually have high classification accuracy but with the detailed structures of objects lost or smoothed. In this work, we develop a methodology based on fully convolutional networks (FCN) that is trained in an end-to-end fashion using aerial RGB images only as input. Skip connections are introduced into the FCN architecture to recover high spatial details from the lower convolutional layers. The experiments are conducted on the city of Goma in the Democratic Republic of Congo. We compare the results to a state-of-the art approach based on a semi-automatic Geographic object image-based analysis (GEOBIA) processing chain. State-of-the art classification accuracies are obtained by both methods whereby FCN and the best baseline method have an overall accuracy of 91.3% and 89.5% respectively. The maps have good visual quality and the use of an FCN skip architecture minimizes the rounded edges that is characteristic of FCN maps. Additional experiments are done to refine FCN classified maps using segments obtained from GEOBIA generated at different scale and minimum segment size. High OA of up to 91.5% is achieved accompanied with an improved edge delineation in the FCN maps, and future work will involve explicitly incorporating boundary information from the GEOBIA segmentation into the FCN pipeline in an end-to-end fashion. Finally, we observe that FCN has a lower computational cost than the standard patch-based CNN approach especially at inference.

Download Full-text

Adversarial Reconstruction-Classification Networks for PolSAR Image Classification

Remote Sensing ◽

10.3390/rs11040415 ◽

2019 ◽

Vol 11 (4) ◽

pp. 415 ◽

Cited By ~ 3

Author(s):

Yanqiao Chen ◽

Yangyang Li ◽

Licheng Jiao ◽

Cheng Peng ◽

Xiangrong Zhang ◽

...

Keyword(s):

Image Classification ◽

Training Sample ◽

Prediction Problem ◽

Polarimetric Synthetic Aperture Radar ◽

Convolutional Networks ◽

Fully Convolutional Networks ◽

Training Samples ◽

Adversarial Training ◽

Composite Representation ◽

Supervised Image Classification

Polarimetric synthetic aperture radar (PolSAR) image classification has become more and more widely used in recent years. It is well known that PolSAR image classification is a dense prediction problem. The recently proposed fully convolutional networks (FCN) model, which is very good at dealing with the dense prediction problem, has great potential in resolving the task of PolSAR image classification. Nevertheless, for FCN, there are some problems to solve in PolSAR image classification. Fortunately, Li et al. proposed the sliding window fully convolutional networks (SFCN) model to tackle the problems of FCN in PolSAR image classification. However, only when the labeled training sample is sufficient, can SFCN achieve good classification results. To address the above mentioned problem, we propose adversarial reconstruction-classification networks (ARCN), which is based on SFCN and introduces reconstruction-classification networks (RCN) and adversarial training. The merit of our method is threefold: (i) A single composite representation that encodes information for supervised image classification and unsupervised image reconstruction can be constructed; (ii) By introducing adversarial training, the higher-order inconsistencies between the true image and reconstructed image can be detected and revised. Our method can achieve impressive performance in PolSAR image classification with fewer labeled training samples. We have validated its performance by comparing it against several state-of-the-art methods. Experimental results obtained by classifying three PolSAR images demonstrate the efficiency of the proposed method.

Download Full-text

Chunk-wise regularised PCA-based imputation of missing data

Statistical Methods & Applications ◽

10.1007/s10260-021-00575-5 ◽

2021 ◽

Author(s):

A. Iodice D’Enza ◽

A. Markos ◽

F. Palumbo

Keyword(s):

Missing Data ◽

Principal Component ◽

Multivariate Techniques ◽

Sufficient Information ◽

Data Sets ◽

Incremental Approach ◽

Distributed Approach ◽

Missing Completely At Random ◽

Incremental Computation ◽

Pca Algorithm

AbstractStandard multivariate techniques like Principal Component Analysis (PCA) are based on the eigendecomposition of a matrix and therefore require complete data sets. Recent comparative reviews of PCA algorithms for missing data showed the regularised iterative PCA algorithm (RPCA) to be effective. This paper presents two chunk-wise implementations of RPCA suitable for the imputation of “tall” data sets, that is, data sets with many observations. A “chunk” is a subset of the whole set of available observations. In particular, one implementation is suitable for distributed computation as it imputes each chunk independently. The other implementation, instead, is suitable for incremental computation, where the imputation of each new chunk is based on all the chunks analysed that far. The proposed procedures were compared to batch RPCA considering different data sets and missing data mechanisms. Experimental results showed that the distributed approach had similar performance to batch RPCA for data with entries missing completely at random. The incremental approach showed appreciable performance when the data is missing not completely at random, and the first analysed chunks contain sufficient information on the data structure.

Download Full-text

Detecting High-Rise Buildings from Sentinel-2 Data Based on Deep Learning Method

Remote Sensing ◽

10.3390/rs13204073 ◽

2021 ◽

Vol 13 (20) ◽

pp. 4073

Author(s):

Liwei Li ◽

Jinming Zhu ◽

Gang Cheng ◽

Bing Zhang

Keyword(s):

Large Scale ◽

3D Structure ◽

Image Features ◽

Convolutional Networks ◽

High Rise ◽

Fully Convolutional Networks ◽

Four Seasons ◽

Training Samples ◽

Definition Of ◽

Sentinel 2

High-rise buildings (HRBs) as a modern and visually distinctive land use play an important role in urbanization. Large-scale monitoring of HRBs is valuable in urban planning and environmental protection and so on. Due to the complex 3D structure and seasonal dynamic image features of HRBs, it is still challenging to monitor large-scale HRBs in a routine way. This paper extends our previous work on the use of the Fully Convolutional Networks (FCN) model to extract HRBs from Sentinel-2 data by studying the influence of seasonal and spatial factors on the performance of the FCN model. 16 Sentinel-2 subset images covering four diverse regions in four seasons were selected for training and validation. Our results indicate the performance of the FCN-based method at the extraction of HRBs from Sentinel-2 data fluctuates among seasons and regions. The seasonal change of accuracy is larger than that of the regional change. If an optimal season can be chosen to get a yearly best result, F1 score of detected HRBs can reach above 0.75 for all regions with most errors located on the boundary of HRBs. FCN model can be trained on seasonally and regionally combined samples to achieve similar or even better overall accuracy than that of the model trained on an optimal combination of season and region. Uncertainties exist on the boundary of detected results and may be relieved by revising the definition of HRBs in a more rigorous way. On the whole, the FCN based method can be largely effective at the extraction of HRBs from Sentinel-2 data in regions with a large diversity in culture, latitude, and landscape. Our results support the possibility to build a powerful FCN model on a larger size of training samples for operational monitoring HRBs at the regional level or even on a country scale.

Download Full-text

Flood Detection in Gaofen-3 SAR Images via Fully Convolutional Networks

Sensors ◽

10.3390/s18092915 ◽

2018 ◽

Vol 18 (9) ◽

pp. 2915 ◽

Cited By ~ 11

Author(s):

Wenchao Kang ◽

Yuming Xiang ◽

Feng Wang ◽

Ling Wan ◽

Hongjian You

Keyword(s):

Detection Method ◽

State Of The Art ◽

Sar Images ◽

Convolutional Network ◽

Training Time ◽

Convolutional Networks ◽

Fully Convolutional Networks ◽

Training Samples ◽

Flood Detection ◽

Fine Tune

Emergency flood monitoring and rescue need to first detect flood areas. This paper provides a fast and novel flood detection method and applies it to Gaofen-3 SAR images. The fully convolutional network (FCN), a variant of VGG16, is utilized for flood mapping in this paper. Considering the requirement of flood detection, we fine-tune the model to get higher accuracy results with shorter training time and fewer training samples. Compared with state-of-the-art methods, our proposed algorithm not only gives robust and accurate detection results but also significantly reduces the detection time.

Download Full-text