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

A novel motion compensation (MoCo) algorithm for high resolution (HR) spotlight SAR imagery is proposed. It is capable of correcting both phase error and range cell migration (RCM) in the post-PFA data domain. It is a robust way to estimate phase error by Map-drift (MD) method, including range-invariant and range-variant ones. What is more, the random characteristic of RCM is also taken into consideration to achieve a well aligned range profile data. Finally, series experimental results are listed to validate the proposal.

Motion compensation in post-PFA domain for high resolution spotlight SAR imagery

Single Range Matching Filtering Based Space Debris Radar Image: Single Range Matching Filtering Based Space Debris Radar Image

High squint multichannel (HSMC) synthetic aperture radar (SAR) mounted on high speed maneuvering platforms is an available mode to achieve wide swath imaging. However, the traditional multichannel reconstruction methods are not suitable because of range-dependent and time-variant steering vector caused by the nonlinear trajectory. To address the issue, a novel unambiguous signal reconstruction algorithm is proposed in this paper. According to the geometry model, the properties of range-dependent and time-variant steering vector are analyzed. Then, a range-dependent and time-variant inter-channel phase compensation method is proposed to correct the space time spectrum, and the constant steering vector is obtained. Before the reconstruction, the range walk correction (RWC) is performed to remove the mismatch between the reconstruction filters and the squinted signal. Furthermore, a modified spatial domain filter is proposed to reconstruct the unambiguous Doppler spectrum. Finally, simulation results are presented to validate the proposed approach.

Unambiguous Signal Reconstruction Algorithm for High Squint Multichannel SAR Mounted on High Speed Maneuvering Platforms

Traditional three-dimensional (3-D) laser imaging systems are based on real aperture imaging technology, whose resolution decreases as the range increases. In this paper, we develop a novel 3-D imaging technique based on the synthetic aperture technology in which the imaging resolution is significantly improved and does not degrade with the increase of the range. We consider an imaging laser radar (ladar) system using the floodlight transmitting mode and multi-beam receiving mode. High 3-D imaging resolutions are achieved by matched filtering the linear frequency modulated (LFM) signals respectively in range, synthetic aperture along-track, and the real aperture across-track. In this paper, a novel 3-D imaging signal model is given first. Because of the motion during the transmission of a sweep, the Doppler shift induced by the continuous motion is taken into account. And then, a proper algorithm for the 3-D imaging geometry is given. Finally, simulation results validate the effectiveness of the proposed technique.

Mengdao Xing

Papers

Motion compensation in post-PFA domain for high resolution spotlight SAR imagery

Single Range Matching Filtering Based Space Debris Radar Image: Single Range Matching Filtering Based Space Debris Radar Image

Unambiguous Signal Reconstruction Algorithm for High Squint Multichannel SAR Mounted on High Speed Maneuvering Platforms

A Novel 3-D Imaging Configuration Exploiting Synthetic Aperture Ladar

A modified Omega-K algorithm for squint circular trace scanning SAR using improved range model