On robust estimation of the location parameter

Exploring and identifying structure is even more important for multivariate data than univariate data, given the difficulties in graphically presenting multivariate data and the comparative lack of parametric models to represent it. Unfortunately, such exploration is also inherently more difficult.

Multivariate Density Estimation

Object-based image classification for land-cover mapping purposes using remote-sensing imagery has attracted significant attention in recent years. Numerous studies conducted over the past decade have investigated a broad array of sensors, feature selection, classifiers, and other factors of interest. However, these research results have not yet been synthesized to provide coherent guidance on the effect of different supervised object-based land-cover classification processes. In this study, we first construct a database with 28 fields using qualitative and quantitative information extracted from 254 experimental cases described in 173 scientific papers. Second, the results of the meta-analysis are reported, including general characteristics of the studies (e.g., the geographic range of relevant institutes, preferred journals) and the relationships between factors of interest (e.g., spatial resolution and study area or optimal segmentation scale, accuracy and number of targeted classes), especially with respect to the classification accuracy of different sensors, segmentation scale, training set size, supervised classifiers, and land-cover types. Third, useful data on supervised object-based image classification are determined from the meta-analysis. For example, we find that supervised object-based classification is currently experiencing rapid advances, while development of the fuzzy technique is limited in the object-based framework. Furthermore, spatial resolution correlates with the optimal segmentation scale and study area, and Random Forest (RF) shows the best performance in object-based classification. The area-based accuracy assessment method can obtain stable classification performance, and indicates a strong correlation between accuracy and training set size, while the accuracy of the point-based method is likely to be unstable due to mixed objects. In addition, the overall accuracy benefits from higher spatial resolution images (e.g., unmanned aerial vehicle) or agricultural sites where it also correlates with the number of targeted classes. More than 95.6% of studies involve an area less than 300 ha, and the spatial resolution of images is predominantly between 0 and 2 m. Furthermore, we identify some methods that may advance supervised object-based image classification. For example, deep learning and type-2 fuzzy techniques may further improve classification accuracy. Lastly, scientists are strongly encouraged to report results of uncertainty studies to further explore the effects of varied factors on supervised object-based image classification.

A review of supervised object-based land-cover image classification

Convolutional neural networks (CNNs) have been attracting increasing attention in hyperspectral (HS) image classification due to their ability to capture spatial–spectral feature representations. Nevertheless, their ability in modeling relations between the samples remains limited. Beyond the limitations of grid sampling, graph convolutional networks (GCNs) have been recently proposed and successfully applied in irregular (or nongrid) data representation and analysis. In this article, we thoroughly investigate CNNs and GCNs (qualitatively and quantitatively) in terms of HS image classification. Due to the construction of the adjacency matrix on all the data, traditional GCNs usually suffer from a huge computational cost, particularly in large-scale remote sensing (RS) problems. To this end, we develop a new minibatch GCN (called miniGCN hereinafter), which allows to train large-scale GCNs in a minibatch fashion. More significantly, our miniGCN is capable of inferring out-of-sample data without retraining networks and improving classification performance. Furthermore, as CNNs and GCNs can extract different types of HS features, an intuitive solution to break the performance bottleneck of a single model is to fuse them. Since miniGCNs can perform batchwise network training (enabling the combination of CNNs and GCNs), we explore three fusion strategies: additive fusion, elementwise multiplicative fusion, and concatenation fusion to measure the obtained performance gain. Extensive experiments, conducted on three HS data sets, demonstrate the advantages of miniGCNs over GCNs and the superiority of the tested fusion strategies with regard to the single CNN or GCN models. The codes of this work will be available at https://github.com/danfenghong/IEEE_TGRS_GCN for the sake of reproducibility.

Graph Convolutional Networks for Hyperspectral Image Classification

Convolutional neural networks (CNNs) have been attracting increasing attention in hyperspectral (HS) image classification, owing to their ability to capture spatial-spectral feature representations. Nevertheless, their ability in modeling relations between samples remains limited. Beyond the limitations of grid sampling, graph convolutional networks (GCNs) have been recently proposed and successfully applied in irregular (or non-grid) data representation and analysis. In this paper, we thoroughly investigate CNNs and GCNs (qualitatively and quantitatively) in terms of HS image classification. Due to the construction of the adjacency matrix on all the data, traditional GCNs usually suffer from a huge computational cost, particularly in large-scale remote sensing (RS) problems. To this end, we develop a new mini-batch GCN (called miniGCN hereinafter) which allows to train large-scale GCNs in a mini-batch fashion. More significantly, our miniGCN is capable of inferring out-of-sample data without re-training networks and improving classification performance. Furthermore, as CNNs and GCNs can extract different types of HS features, an intuitive solution to break the performance bottleneck of a single model is to fuse them. Since miniGCNs can perform batch-wise network training (enabling the combination of CNNs and GCNs) we explore three fusion strategies: additive fusion, element-wise multiplicative fusion, and concatenation fusion to measure the obtained performance gain. Extensive experiments, conducted on three HS datasets, demonstrate the advantages of miniGCNs over GCNs and the superiority of the tested fusion strategies with regards to the single CNN or GCN models. The codes of this work will be available at this https URL for the sake of reproducibility.

Road information has a fundamental role in modern society. Road extraction from optical satellite images is an economic and efficient way to obtain and update a transportation database. This paper presents an integrated method to extract urban main-road centerlines from satellite optical images. The proposed method has four main steps. First, general adaptive neighborhood is introduced to implement spectral-spatial classification to segment the images into two categories: road and nonroad groups. Second, road groups and homogeneous property, measured by local Geary's C, are fused to improve road-group accuracy. Third, road shape features are used to extract reliable road segments. Finally, local linear kernel smoothing regression is performed to extract smooth road centerlines. Road networks are then generated using tensor voting. The proposed method is tested and subsequently validated using a large set of multispectral high-resolution images. A comparison with several existing methods shows that the proposed method is more suitable for urban main-road centerline extraction.

/pdf/an-integrated-method-for-urban-main-road-centerline-3zpa8jwdcz.pdf

An Integrated Method for Urban Main-Road Centerline Extraction From Optical Remotely Sensed Imagery

Standard deviational ellipse (SDE) has long served as a versatile GIS tool for delineating the geographic distribution of concerned features. This paper firstly summarizes two existing models of calculating SDE, and then proposes a novel approach to constructing the same SDE based on spectral decomposition of the sample covariance, by which the SDE concept is naturally generalized into higher dimensional Euclidean space, named standard deviational hyper-ellipsoid (SDHE). Then, rigorous recursion formulas are derived for calculating the confidence levels of scaled SDHE with arbitrary magnification ratios in any dimensional space. Besides, an inexact-newton method based iterative algorithm is also proposed for solving the corresponding magnification ratio of a scaled SDHE when the confidence probability and space dimensionality are pre-specified. These results provide an efficient manner to supersede the traditional table lookup of tabulated chi-square distribution. Finally, synthetic data is employed to generate the 1-3 multiple SDEs and SDHEs. And exploratory analysis by means of SDEs and SDHEs are also conducted for measuring the spread concentrations of Hong Kong’s H1N1 in 2009.

/pdf/confidence-analysis-of-standard-deviational-ellipse-and-its-4a88e7qf9r.pdf

Confidence Analysis of Standard Deviational Ellipse and Its Extension into Higher Dimensional Euclidean Space

Road centerline extraction from remotely sensed imagery can be used to update a Geographic Information System (GIS) database. The common road extraction from high-resolution imagery is based on spectral information only; it is difficult to separate road features from background completely, and a thinning algorithm always results in short spurs which reduce the smoothness of the road centerline. To overcome the aforementioned shortcomings of the common existing road centerline algorithms, this letter presents a new method to extract the road centerline from high-resolution imagery based on shape features and multivariate adaptive regression splines (MARS), in which potential road segments were obtained based on shape features and spectral feature, followed by MARS to extract road centerlines. Two experiments are performed to evaluate the accuracy of the proposed method.

http://www.lsgi.polyu.edu.hk/academic_staff/John.Shi/publications/064-Road_centerline_extraction_from_high-resolution_imagery.pdf

Road Centerline Extraction From High-Resolution Imagery Based on Shape Features and Multivariate Adaptive Regression Splines

Landslide mapping from aerial photographs using change detection-based Markov random field

This letter presents a semi-automatic approach to delineating road networks from very high resolution satellite images. The proposed method consists of three main steps. First, the geodesic method is used to extract the initial road segments that link the road seed points prescribed in advance by users. Next, a road probability map is produced based on these coarse road segments and a further direct thresholding operation separates the image into two classes of surfaces: the road and nonroad classes. Using the road class image, a kernel density estimation map is generated, upon which the geodesic method is used once again to link the foregoing road seed points. Experiments demonstrate that this proposed method can extract smooth correct road centerlines.

Zelang Miao

Papers

An Integrated Method for Urban Main-Road Centerline Extraction From Optical Remotely Sensed Imagery

Confidence Analysis of Standard Deviational Ellipse and Its Extension into Higher Dimensional Euclidean Space

Road Centerline Extraction From High-Resolution Imagery Based on Shape Features and Multivariate Adaptive Regression Splines

Landslide mapping from aerial photographs using change detection-based Markov random field

A Semi-Automatic Method for Road Centerline Extraction From VHR Images