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

Being capable of enhancing the flexibility and observing ability of synthetic aperture radar (SAR), squint mode is one of the most essential operating modes in SAR applications. However, processing of highly squinted SAR data is usually a challenging task attributed to the spatial-variant range cell migration over a long aperture. The Omega-k algorithm is generally accepted as an ideal solution to this problem. In this paper, we focus on using the wavenumber-domain approach for highly squinted unmanned aerial vehicle (UAV) SAR imagery. A squinted phase gradient autofocus (SPGA) algorithm is proposed to overcome the severe motion errors, including phase and nonsystematic errors. Herein, the inconsistence of phase error and range error in the squinted wavenumber-domain imaging is first presented, which reveals that even the motion error introduces very small phase error, it causes considerable range error due to the Stolt mapping. Based on this, two schemes of SPGA-based motion compensation are developed according to the severity of motion error. By adapting the advantages of weighted phase gradient autofocus and quality phase gradient autofocus, the robustness of SPGA is ensured. Real measured data sets are used to validate the proposed approach for highly squinted UAV-SAR imagery.

Wavenumber-Domain Autofocusing for Highly Squinted UAV SAR Imagery

A new inverse synthetic aperture radar (ISAR) imaging approach is presented for application in situations where the maneuverability of noncooperative target is not too severe and the Doppler variation of subechoes from scatterers can be approximated as a first-order polynomial. The proposed algorithm is referred to as the range centroid Doppler (RCD) ISAR imaging technique and is based on the stretch Keystone-Wigner transform (SKWT). The SKWT introduces a stretch weight factor containing a range of chirp rate into the autocorrelation function of each cross-range profile and uses a 1-D interpolation of the phase history which we call stretch keystone formatting. The processing simultaneously eliminates the effects of linear frequency migration for all signal components regardless of their unknown chirp rate in time-frequency plane, but not for the noise or for the cross terms. By utilizing this novel technique, clear ISAR imaging can be achieved for maneuvering targets without an exhaustive search procedure for the motion parameters. Performance comparison is carried out to evaluate the improvement of the RCD technique versus other methods such as the conventional range Doppler (RD) technique, the range instantaneous Doppler (RID) technique, and adaptive joint time-frequency (AJTF) technique. Examples provided demonstrate the effectiveness of the RCD technique with both simulated and experimental ISAR data.

ISAR Imaging of Maneuvering Targets Based on the Range Centroid Doppler Technique

Inverse synthetic aperture radar (ISAR) imaging of the noncooperative maneuvering target is a challenging task because of its time variant orientation and rotation velocity which cannot be measured accurately. This correspondence investigates the principles of ISAR imaging of maneuvering targets, and proposes an algorithm for application in situations where the maneuverability is not too severe and the Doppler variation of subechoes from scatterers can be approximated as a first-order polynomial. The imaging results obtained by using real data show the effectiveness of the new method.

Time-frequency approaches to ISAR imaging of maneuvering targets and their limitations

For a target with rotating parts, the ISAR image of its main body may be overshadowed by micro-Doppler signals, which are traditionally treated as interference and removed from radar echoes. However, it is potentially useful to perform imaging using micro-Doppler signals because they contain information on the geometrical structure of the rotating part. Inspired by the inverse Radon transform, well-known in the image processing community, this paper creates a data-recording model for two-dimensional (2D) ISAR imaging of rotating parts. Based on this model, the real-valued inverse Radon transform is applied to image formation in the range-slow time domain. Then we put forward a complex-valued inverse Radon transform for imaging of rotating parts, which utilizes both the sinusoidal modulus and the phase of the radar echoes. Additionally, we analyze possible problems when applying these algorithms in real world situations and provide corresponding solutions. Finally, the effectiveness of the algorithms is demonstrated using simulated and measured data.

High Resolution ISAR Imaging of Targets with Rotating Parts

Narrow-band interference (NBI) is a common interference source in synthetic aperture radar (SAR) imaging. Its existence will degrade the imaging quality greatly. Based on detailed analysis on the characteristics of NBI, this letter proposes a new NBI suppression algorithm using the complex empirical mode decomposition (CEMD) method. In this algorithm, echoes that include NBI are recognized in the time domain first. Then, these echoes are decomposed into a number of intrinsic mode functions (IMFs) via the CEMD. After that, IMFs that correspond to NBI are subtracted from the echoes by thresholding. Finally, well-focused SAR imagery can be obtained from the separated target echoes using traditional SAR imaging algorithms. The effective data loss in this algorithm is smaller than other NBI suppression approaches. In addition, this algorithm is robust to time-varying NBI. Imaging results of measured data have proved the validity of this algorithm.

Mengdao Xing

Papers

Wavenumber-Domain Autofocusing for Highly Squinted UAV SAR Imagery

ISAR Imaging of Maneuvering Targets Based on the Range Centroid Doppler Technique

Time-frequency approaches to ISAR imaging of maneuvering targets and their limitations

High Resolution ISAR Imaging of Targets with Rotating Parts

Narrow-Band Interference Suppression for SAR Based on Complex Empirical Mode Decomposition