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

Synthetic aperture radar (SAR) raw data simulator is an important tool for parameter-optimizing and algorithm-testing, particularly for those complicated configurations in which real raw data is difficult to obtain. As a new and special imaging mode, bistatic forward-looking SAR with constant acceleration (BFCA-SAR) can perform two-dimensional imaging for targets in the straight-ahead position over mono-static SAR. But there exist more complicated square roots and high-order terms in range history owing to high velocities and accelerations from both platforms. In addition, space variances in phase terms of two-dimensional frequency spectrum (2-D FS) make it difficult to gain echo data accurately. In this paper, a fast scene raw data simulator for BFCA-SAR based on quantitative analysis and effective correction of phase space variance is proposed. With high precision, our method can generate raw data more efficiently than traditional algorithms.

Fast raw data simulator of extended scenes for bistatic forward-looking synthetic aperture radar with constant acceleration

Clutter suppression is always problematic in synthetic aperture radar (SAR) imaging. Especially when clutter is strong, inappropriate threshold on image amplitude may lead to failure to completely separate the background and the region of interest (ROI). Therefore, this paper firstly presents an adaptive threshold estimation method from the view of coherence. To protect weak scatterers, neighbored points around the extracted centers are also preserved. With the strong sparsity of the ROI in the image, the resolution of the extracted target region is enhanced by the sparse signal processing technique. Experimental results on simulated and real data both confirm its practicability.

http://ieeexplore.ieee.org/iel7/7422354/7428505/07428585.pdf

Enhanced target extraction in strong clutter scene

To meet the demand for large area environment monitoring during short synthetic aperture time, this paper proposes an imaging algorithm for high squint beam steering (HS-BS) SAR platforms with constant acceleration. To achieve a good performance and high efficiency, the baseband azimuth scaling (BAS) method cannot be directly applied for the azimuth focusing. The signal is calculated based on high squint concentric circle (HS-CC) range model. The conventional derotation operation is modified by nonlinear phase and range-dependent derotation. Then the space-variant (SV) Doppler chirp rate is corrected by BAS method without sub-aperture processing.

Applications of Baseband Azimuth Scaling on High Squint Beam Steering SAR Imaging with Contant Acceleration

An algorithm for estimating full aperture with sparse data is proposed in this paper. For wide vacant aperture in sparse data, by measuring sparse data actually, accurate sparse data frequency domain energy distribution estimate can be obtained with parametric approaches. With estimated power spectrum as prior information, minimum weighted norm as the restraint, underdetermined equations are solved to interpolate vacant aperture, thus wide aperture data segment estimate is obtained. This algorithm can be effectively applied to ISAR imaging in sparse data. Resulting simulation and actual data processing results confirm validity of the proposed algorithm

A New Algorithm for Sparse Aperture Extrapolation

Bistatic SAR Data Focusing Using a Frequency Scaling Algorithm Based on an Analytical Spectrum in Tandem Configuration: Bistatic SAR Data Focusing Using a Frequency Scaling Algorithm Based on an Analytical Spectrum in Tandem Configuration

Mengdao Xing

Papers

Fast raw data simulator of extended scenes for bistatic forward-looking synthetic aperture radar with constant acceleration

Enhanced target extraction in strong clutter scene

Applications of Baseband Azimuth Scaling on High Squint Beam Steering SAR Imaging with Contant Acceleration

A New Algorithm for Sparse Aperture Extrapolation

Bistatic SAR Data Focusing Using a Frequency Scaling Algorithm Based on an Analytical Spectrum in Tandem Configuration: Bistatic SAR Data Focusing Using a Frequency Scaling Algorithm Based on an Analytical Spectrum in Tandem Configuration