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

As a special multiple-input multiple-output (MIMO) radar networking mode, missile-borne forward-looking synthetic aperture radar (MFL-SAR) has many potential applications. This paper describes and analyzes properties of this new configuration. Range history and Doppler history are analyzed and derived using the designed geometric configuration. Then the expressions of range and Doppler resolution are determined based on the validity of two-dimensional (2D) resolution imaging capability. To help to design the proper system and motion parameters of this configuration, key parameters affecting the imaging ability are found out. Due to high velocities and accelerations of both transmitter and receiver, high-order terms in the slant range equation should be kept to reduce the approximation error. The range resolution and Doppler resolution of MFL-SAR are both space-variant and time-variant owing to the complexity of this configuration. The tiny changes of 2D resolution during the synthetic aperture time should be considered when designing the imaging algorithm of MFL-SAR.

/pdf/property-analysis-of-mimo-based-missile-borne-forward-50pxdb51y2.pdf

Property Analysis of MIMO-Based Missile-Borne Forward-Looking SAR

Among the techniques for range ambiguity suppression, the azimuth phase coding (APC) stands out for its effectiveness for point and distributed targets with low implementation complexity. After modulation to the transmitted signal and the corresponding demodulation to the received signal, the residual modulation phase of the ambiguity signal shifts its Doppler spectrum, so that the spectrum of the useful signal and that of the ambiguity are not exactly superimposed. This enables an azimuth filter to eliminate a part of the ambiguity power. If it is desired to get an ambiguity-free SAR image, the pulse reputation frequency (PRF) should be several times larger than the Doppler bandwidth of the desired Doppler spectrum, which is hard to be satisfied in high-resolution wide-swath spaceborne SAR systems. This paper introduces a method for range ambiguity suppression based on the APC technology in multichannel SAR systems when the PRF is only a bit larger than the Doppler bandwidth. After applying the APC technique, the space-time spectrum of the ambiguity swath is separated from that of the useful signal. In multichannel SAR systems, the desired 2-D spectrum and the spectrum of the ambiguity swath can be obtained simultaneously by using the position information of antenna phase centres. Conventional imaging algorithms can then be applied to both spectrums to obtain SAR images of the imaging area and the ambiguity swaths. Simulation results confirm the effectiveness of this method. (5 pages)

Range ambiguity suppression by azimuth phase coding in multichannel SAR systems

For target detection in complex scenes of synthetic aperture radar (SAR) images, the false alarms in the land areas are hard to eliminate, especially for the ones near the coastline. Focusing on the problem, an algorithm based on the fusion of multiscale superpixel segmentations is proposed in this paper. Firstly, the SAR images are partitioned by using different scales of superpixel segmentation. For the superpixels in each scale, the land-sea segmentation is achieved by judging their statistical properties. Then, the land-sea segmentation results obtained in each scale are combined with the result of the constant false alarm rate (CFAR) detector to eliminate the false alarms located on the land areas of the SAR image. In the end, to enhance the robustness of the proposed algorithm, the detection results obtained in different scales are fused together to realize the final target detection. Experimental results on real SAR images have verified the effectiveness of the proposed algorithm.

https://www.mdpi.com/1424-8220/21/5/1643/pdf

Realizing Target Detection in SAR Images Based on Multiscale Superpixel Fusion.

The Analysis of FMCW SAR Signal and Image Study: The Analysis of FMCW SAR Signal and Image Study

In high-resolution radar imaging, there is inevitable migration through range cells (MTRCs) in an inverse synthetic aperture radar (ISAR) image due to the manoeuvrability of the target. In the case of sparse aperture (SA) measurement, it is generally difficult to accurately correct MTRCs to degrade the imaging performance. An approach of SA-imaging jointly with MTRC correction for manoeuvring targets is presented. Under a chirp-Fourier dictionary by involving MTRCs, the ISAR image formation is treated as a sparse-driven optimisation to overcome the SA. Experiments based on the measured data are performed to confirm the effectiveness of the proposed algorithm.

Mengdao Xing

Papers

Property Analysis of MIMO-Based Missile-Borne Forward-Looking SAR

Range ambiguity suppression by azimuth phase coding in multichannel SAR systems

Realizing Target Detection in SAR Images Based on Multiscale Superpixel Fusion.

The Analysis of FMCW SAR Signal and Image Study: The Analysis of FMCW SAR Signal and Image Study

High-resolution inverse synthetic aperture radar imaging of manoeuvring targets with sparse aperture