Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Обнаружение транспортных средств на изображениях загородных шоссе на основе метода Single shot multibox Detector

This chapter introduces the subject of statistical pattern recognition (SPR). It starts by considering how features are defined and emphasizes that the nearest neighbor algorithm achieves error rates comparable with those of an ideal Bayes’ classifier. The concepts of an optimal number of features, representativeness of the training data, and the need to avoid overfitting to the training data are stressed. The chapter shows that methods such as the support vector machine and artificial neural networks are subject to these same training limitations, although each has its advantages. For neural networks, the multilayer perceptron architecture and back-propagation algorithm are described. The chapter distinguishes between supervised and unsupervised learning, demonstrating the advantages of the latter and showing how methods such as clustering and principal components analysis fit into the SPR framework. The chapter also defines the receiver operating characteristic, which allows an optimum balance between false positives and false negatives to be achieved.

Statistical Pattern Recognition

Object detection in optical remote sensing images, being a fundamental but challenging problem in the field of aerial and satellite image analysis, plays an important role for a wide range of applications and is receiving significant attention in recent years. While enormous methods exist, a deep review of the literature concerning generic object detection is still lacking. This paper aims to provide a review of the recent progress in this field. Different from several previously published surveys that focus on a specific object class such as building and road, we concentrate on more generic object categories including, but are not limited to, road, building, tree, vehicle, ship, airport, urban-area. Covering about 270 publications we survey (1) template matching-based object detection methods, (2) knowledge-based object detection methods, (3) object-based image analysis (OBIA)-based object detection methods, (4) machine learning-based object detection methods, and (5) five publicly available datasets and three standard evaluation metrics. We also discuss the challenges of current studies and propose two promising research directions, namely deep learning-based feature representation and weakly supervised learning-based geospatial object detection. It is our hope that this survey will be beneficial for the researchers to have better understanding of this research field.

A survey on object detection in optical remote sensing images

In this paper, we examine the role of polarimetry in synthetic aperture radar (SAR) interferometry. We first propose a general formulation for vector wave interferometry that includes conventional scalar interferometry as a special case. Then, we show how polarimetric basis transformations can be introduced into SAR interferometry and applied to form interferograms between all possible linear combinations of polarization states. This allows us to reveal the strong polarization dependency of the interferometric coherence. We then solve the coherence optimization problem involving maximization of interferometric coherence and formulate a new coherent decomposition for polarimetric SAR interferometry that allows the separation of the effective phase centers of different scattering mechanisms. A simplified stochastic scattering model for an elevated forest canopy is introduced to demonstrate the effectiveness of the proposed algorithms. In this way, we demonstrate the importance of wave polarization for the physical interpretation of SAR interferograms. We investigate the potential of polarimetric SAR interferometry using results from the evaluation of fully polarimetric interferometric shuttle imaging radar (SIR)-C/X-SAR data collected during October 8-9, 1994, over the SE Baikal Lake Selenga delta region of Buriatia, Southeast Siberia, Russia.

Polarimetric SAR interferometry

/pdf/dynamic-ensemble-algorithm-of-smote-and-rotation-forest-for-2mllb02g.pdf

Dynamic ensemble algorithm of SMOTE and rotation forest for imbalanced hyperspectral remote sensing classification

Due to the constraint of minimum antenna area, azimuth ambiguity resolving is a challenging task in the ship focusing for single-channel synthetic aperture radar (SAR) mounted on high-speed maneuvering platforms. In order to accommodate the issues, a ship focusing algorithm based on azimuth ambiguity resolving is proposed in this paper. For ship SAR imaging with small-aperture data, the energies of different targets are separated in Doppler domain with different Doppler ambiguity numbers. Thus, the Doppler ambiguity number of a single target can be estimated by residual envelope inclination. Then, the target can be accurately focused and located at the correct position by the known Doppler ambiguity number. After the operation of each target is completed, the focusing SAR image of the whole scene can be obtained. Finally, simulation results are presented to validate the proposed algorithm.

Ship Imaging based on Azimuth Ambiguity Resolving for High-Speed Maneuvering Platforms Sar with Small-Aperture

In a direction-finding process, high-resolution subspace-based algorithms are the most popular ones. It is well-known that their performance of direction of arrival (DOA) estimation mainly depends on the accuracy of the signal subspace. However, the traditional methods of capturing the signal subspace do not mine the information hidden in the array output in depth, which may restrict their application to some extent. In this study, we elaborate on a novel scheme to extract the signal subspace through refinement of the correlation matrix of the array output. In the developed scheme, a collection of spatial-temporal correlation matrices is first established. Then, we define a weighting vector for the correlation matrices and take the weighted average of the correlation matrices as the covariance matrix of the array output. It is clear that this covariance matrix is more general than the traditional covariance matrix, and the signal subspace can be optimized through adjustment of the weighting vector. In this study, we present an optimal weighting vector by adopting particle swarm optimization (PSO). Simulation results demonstrate that the proposed approach has a better performance in root mean square error (RMSE) compared to the existing schemes.

High-Accuracy DOA Estimation Based on an Improved Sample Correlation Matrix

Recently bistatic synthetic aperture radar (SAR), especially spaceborne SARs, has attracted the attention of many radar researchers. Generally, the orbit of satellite for remote sensing purposes is an ellipse with small eccentricity, and the earth should be modeled as an ellipsoid. It is well known that a second-order relative motion model can be a good approximation to a monostotic spaceborne SAR. However, for bistatic cases, this phase history model mismatches the real relative motion between a satellite and a rotating earth, dissatisfying the imaging accuracy requirement, and it limits the available azimuth resolution. In order to use the well studied SAR imaging algorithms, we develop a new second-order phase history model for bistatic spaceborne SAR using the phase error fitting method based on the ephemeris data. The new model strengthens the applicability of the conventional second-order phase history model of spaceborne bistatic SAR significantly.

Modified phase history model for high resolution spaceborne bistatic SAR

The curved trajectory and long synthetic aperture time of medium-earth-orbit (MEO) synthetic aperture radar (SAR) lead to a two-dimensional spatial variation in the signals. Traditional methods treat the range and azimuth variations separately, and usually suffer from high computational complexities. We investigate the Doppler rate distribution across a large scene, and exploit an optimal imaging coordinate system, in which the MEO SAR signals satisfy the azimuth-shift-invariant property. The additional processing of the azimuth spatial variation in MEO SAR imaging algorithms can be avoided, and the efficiency of the image formation processor can be improved. Finally, processing of simulated stripmap-mode data with 2-m resolution can validate the proposed algorithm.

Mengdao Xing

Papers

Dynamic ensemble algorithm of SMOTE and rotation forest for imbalanced hyperspectral remote sensing classification

Ship Imaging based on Azimuth Ambiguity Resolving for High-Speed Maneuvering Platforms Sar with Small-Aperture

High-Accuracy DOA Estimation Based on an Improved Sample Correlation Matrix

Modified phase history model for high resolution spaceborne bistatic SAR

An Efficient MEO SAR Imaging Algorithm Based on Optimal Imaging Coordinate System