Georegistration of airborne hyperspectral image data

A suite of geometric sensor and platform modeling tools has been developed which have achieved consistent subpixel accuracy in orthorectification experiments. Aircraft platforms in turbulent atmospheric conditions present unique challenges and have required creative modeling approaches. The geometric relationship between an image point and a ground object has been modeled by rigorous photogrammetric methods. First and second order Gauss-Markov processes have been used to estimate the platform trajectory. These methods have been successfully applied to HYDICE and HyMap data sets. The most important contributors to the subpixel rectification accuracy have been the first order Gauss-Markov model with control linear features     

Dense optical flow via robust data fusion

Locally optimised differential methods for computing optical flow have the merit of being faster and more reliable under noise when compared to their globally optimised counterparts. However, they produce sparse flow estimates as a result of being unable to deal with local image regions of little texture. They are also particularly inefficient for regions whose change of feature-constancy function is highly nonlinear. In this study, we treat several limitations of the local approach in monochrome images. We present a robust H_∞ data fusion-based framework to propagate flow information from high confidence regions to those suspected of poor quality estimates. The adopted data fusion engine is tolerant towards uncertainty and error inherited in the optical flow computation process. A new integrated confidence measure is also presented to predict the accuracy of the recovered flow across the image enabling the data fusion engine to work as an intelligent filling-in effect, not only when the intensity is problematic but also for other uncertain regions. Results demonstrate the significance of the proposed method.     

Registering Landsat images by point matching

Image registration of Landsat Thematic Mapper scenes with translational and rotational differences is studied. Two major steps of image registration, control-point selection and control-point matching, are emphasized. In control-point selection, the properties that a good control point should satisfy are defined. Several potential control-point candidates are suggested, and methods are discussed for extracting them from the input image. In control-point matching, a relaxation algorithm proposed in the literature is improved by reducing its time complexity from O(n⁴) to O(n³ ), where n is the number of control points. The matching algorithm also uses a two-way matching concept which utilizes the inherent symmetry property of the point-matching problem. The robustness of the proposed algorithm was demonstrated through simulation experiments by evaluating a matching index. Experimental results on Landsat images show that the proposed method produces results comparable to those obtained by an experienced photointerpreter     

一种改进的快速鲁棒性特征匹配算法

针对光照变化、噪声、局部遮挡等在图像配准技术中对配准精度有重要影响,提出了一种在多尺度空间下点预测快速鲁棒性不变特征的匹配算法。针对在探测对图像的尺度、旋转,仿射具有不变性的斑状特征极值点过程中计算复杂度较高的问题,提出一种特征点预测方法降低了描述子提取的复杂度,增强了对外部环境光照变化、噪声以及局部遮挡的适应能力;并在KD(KD Tree)树基础上,提出了一种动态平衡KD树(DBKD-Tree)快速搜索匹配算法,有效克服了KD树可能存在的病态划分,采用条件约束最邻近搜索,提升匹配效率,实现特征点高精度匹配。通过对在不同光照条件、噪声环境的仿射变换图像特征匹配测试,在加入20%的高斯噪声后,均能100%地完成重复特征检测,达到亚像素定位精度,误配率降低为零。     

Robust object tracking based on adaptive templates matching via the fusion of multiple features

Moving object tracking under complex scenes remains to be a challenging problem because the appearance of a target object can be drastically changed due to several factors, such as occlusions, illumination, pose, scale change and deformation. This study proposes an adaptive multi–feature fusion strategy, in which the target appearance is modeled based on timed motion history image with HSV color histogram features and edge orientation histogram features. The variances based on the similarities between the candidate patches and the target templates are used for adaptively adjusting the weight of each feature. Double templates matching, including online and offline template matching, is adopted to locate the target object in the next frame. Experimental evaluations on challenging sequences demonstrate the accuracy and robustness of the proposed algorithm in comparison with several state-of-the-art algorithms.     

Object matching algorithms using robust Hausdorff distance measures

A Hausdorff distance (HD) is one of commonly used measures for object matching. This work analyzes the conventional HD measures and proposes two robust HD measures based on m-estimation and least trimmed square (LTS) which are more efficient than the conventional HD measures. By computer simulation, the matching performance of the conventional and proposed HD measures is compared with synthetic and real images.     

Fast algorithm for robust template matching with M-estimators

We propose a fast algorithm for speeding up the process of template matching that uses M-estimators for dealing with outliers. We propose a particular image hierarchy called the p-pyramid that can be exploited to generate a list of ascending lower bounds of the minimal matching errors when a nondecreasing robust error measure is adopted. Then, the set of lower bounds can be used to prune the search of the p-pyramid, and a fast algorithm is thereby developed in this paper. This fast algorithm ensures finding the global minimum of the robust template matching problem in which a nondecreasing M-estimator serves as an error measure. Experimental results demonstrate the effectiveness of our method.     

Layered video coding based on displaced frame difference prediction and multiresolution block matching

This paper presents a new video-coding technique based on displaced frame difference (DFD) prediction and multiresolution block matching for layered transmission. Starting from the base layer, the algorithm encodes one layer at a time until the design of the top layer is completed. For the encoding of each layer, the DFD prediction and multistage motion-vector quantization (MSMVQ) techniques are employed so that the results of DFD encoding and block matching at previous layers can be used to enhance the coding efficiency at that layer. Numerical results show that the algorithm is effective for the applications where high rate-distortion performance and low computational complexity for layered video transmission are required.     

A bayesian approach to classification of multiresolution remote sensing data

Several earth observation satellites acquire image bands with different spatial resolutions, e.g., a panchromatic band with high resolution and spectral bands with lower resolution. Likewise, we often face the problem of different resolutions when performing joint analysis of images acquired by different satellites. This work presents models and methods for classification of multiresolution images. The approach is based on the concept of a reference resolution, corresponding to the highest resolution in the dataset. Prior knowledge about the spatial characteristics of the classes is specified through a Markov random field model at the reference resolution. Data at coarser scales are modeled as mixed pixels by relating the observations to the classes at the reference resolution. A Bayesian framework for classification based on this multiscale model is proposed. The classification is realized by an iterative conditional modes (ICM) algorithm. The parameter estimation can be based both on a training set and on pixels with unknown class. A computationally efficient scheme based on a combination of the ICM and the expectation-maximization algorithm is proposed. Results obtained on simulated and real satellite images are presented.     

Context-aware features and robust image representations

Local image features are often used to efficiently represent image content. The limited number of types of features that a local feature extractor responds to might be insufficient to provide a robust image representation. To overcome this limitation, we propose a context-aware feature extraction formulated under an information theoretic framework. The algorithm does not respond to a specific type of features; the idea is to retrieve complementary features which are relevant within the image context. We empirically validate the method by investigating the repeatability, the completeness, and the complementarity of context-aware features on standard benchmarks. In a comparison with strictly local features, we show that our context-aware features produce more robust image representations. Furthermore, we study the complementarity between strictly local features and context-aware ones to produce an even more robust representation.     

Atmospheric effects on Landsat TM thermal IR data

The components of atmospherically attenuated target radiance and the path radiance emitted by the atmosphere are calculated to explain the fact that for certain meteorological conditions, properly calibrated thermal IR (infrared) data gathered from aircraft and spacecraft altitudes provide accurate temperature measurements of surface water bodies even when atmospheric corrections are not applied. Results show that although the 8-14-μm atmospheric window is far from being transparent (<50% transmission), the amount of atmospheric path radiance may be equal to the amount of attenuated target radiance. Errors in remotely sensed temperatures introduced by atmospheric effects are shown to be smaller than or of the same order of magnitude as those errors caused by sensor noise and the effects of applying a cubic convolution during the process of converting the TM (Thematic Mapper) data from A-tape to geometrically corrected P-tape data format     

Landmark matching via large deformation diffeomorphisms

This paper describes the generation of large deformation diffeomorphisms phi:Omega=[0,1](3)right harpoon over left harpoonOmega for landmark matching generated as solutions to the transport equation dphi(x,t)/dt=nu(phi(x,t),t),tin[0,1] and phi(x,0)=x, with the image map defined as phi(.,1) and therefore controlled via the velocity field nu(.,t),tin[0,1]. Imagery are assumed characterized via sets of landmarks {x(n), y(n), n=1, 2, ..., N}. The optimal diffeomorphic match is constructed to minimize a running smoothness cost parallelLnu parallel(2) associated with a linear differential operator L on the velocity field generating the diffeomorphism while simultaneously minimizing the matching end point condition of the landmarks. Both inexact and exact landmark matching is studied here. Given noisy landmarks x(n) matched to y(n ) measured with error covariances Sigma(n), then the matching problem is solved generating the optimal diffeomorphism phi;(x,1)=integral(0)(1 )nu;(phi;(x,t),t)dt+x where nu;(.)argmin(nu(.))integral(1) (1)integral(Omega) parallelLnu(x,t) parallel(2)dxdt +Sigma(n=1)(N)[y(n)-phi(x(n),1)] (T)Sigma(n)(-1)[y(n)-phi(x(n ),1)]. Conditions for the existence of solutions in the space of diffeomorphisms are established, with a gradient algorithm provided for generating the optimal flow solving the minimum problem. Results on matching two-dimensional (2-D) and three-dimensional (3-D) imagery are presented in the macaque monkey.     

Automated co-superpixel generation via graph matching

In this paper, a novel ‘co-superpixel’ generation method is proposed via the graph matching. The co-superpixel can capture the common semantic information in coupled images. Therefore, it is significant for various applications in visual pattern recognition. Specifically, we first introduce a superpixel correspondence method based on the graph matching. The main property is that it has the ability to capture the consistent intermediate-level semantic information in coupled images, which can represent the region-based similarity rather than the conventional similarity based on low-level vision features. Second, a new co-superpixel generation method is proposed by the superpixel-merging incorporated with the graph matching cost and the adjacent superpixel appearance similarity in coupled images simultaneously. Furthermore, we extend the proposed co-superpixel method to tackle the object matching problem. The experimental results show that the object matching can be effectively addressed by the co-superpixel. The proposed method is effective for challenging cases in which object appearance changes, deformation and background clutter.     

Constrained solutions in importance via robust statistics

The problem of estimating estimating expectations of functions of random vectors via simulation is investigated. Monte Carlo simulations, also known as simple averaging, have been used as a direct means of estimation. A technique known as importance sampling can be used to modify the simulation via weighted averaging in the hope that the estimate will converge more rapidly to the expected value than standard Monte Carlo simulations. A constrained optimal solution to the problem of minimizing the variance of the importance sampling estimator is derived. This is accomplished by finding the distribution which is closest to the unconstrained optimal solution in the Ali-Silvey sense (S. Ali et al., 1966). The solution from the constraint class is shown to be the least favorable density function in terms of Bayes risk against the optimal density function. Examples of constraint classes, which include ϵ-mixture, show that the constrained optimal solution can be made arbitrarily close to the optimal solution. Applications to estimating probability of error in communication systems are presented     

Robust gait recognition via discriminative set matching

In this paper, we propose a framework for gait recognition across varying views and walking conditions based on gait sequences collected from multiple viewpoints. Different from most existing view-dependent gait recognition systems, we devise a new Multiview Subspace Representation (MSR) method which considers gait sequences collected from different views of the same subject as a feature set and extracts a linear subspace to describe the feature set. Subspace-based feature representation methods measure the variances among samples, and can handle certain intra-subject variations. To better exploit the discriminative information from these subspaces for recognition, we further propose a marginal canonical correlation analysis (MCCA) method which maximizes the margins of interclass subspaces within a neighborhood. Experimental results on a widely used multiview gait database are presented to demonstrate the effectiveness of the proposed framework.     

Universal lossless compression via multilevel pattern matching

A universal lossless data compression code called the multilevel pattern matching code (MPM code) is introduced. In processing a finite-alphabet data string of length n, the MPM code operates at O(log log n) levels sequentially. At each level, the MPM code detects matching patterns in the input data string (substrings of the data appearing in two or more nonoverlapping positions). The matching patterns detected at each level are of a fixed length which decreases by a constant factor from level to level, until this fixed length becomes one at the final level. The MPM code represents information about the matching patterns at each level as a string of tokens, with each token string encoded by an arithmetic encoder. From the concatenated encoded token strings, the decoder can reconstruct the data string via several rounds of parallel substitutions. A O(1/log n) maximal redundancy/sample upper bound is established for the MPM code with respect to any class of finite state sources of uniformly bounded complexity. We also show that the MPM code is of linear complexity in terms of time and space requirements. The results of some MPM code compression experiments are reported     

Wavelet based robust sub-band features for phoneme recognition

Wavelet transform has been found to be an effective tool for the time-frequency analysis of non-stationary and quasi-stationary signals. Recent years have seen wavelet transform being used for feature extraction in speech recognition applications. In the paper a sub-band feature extraction technique based on an admissible wavelet transform is proposed and the features are modified to make them robust to additive white Gaussian noise. The performance of this system is compared with the conventional mel frequency cepstral coefficients (MFCC) under various signal to noise ratios. The recognition performance based on the eight sub-band features is found to be superior under the noisy conditions compared with MFCC features.     

Bayesian channel equalisation and robust features for speechrecognition

The use of a speech recognition system with telephone channel environments, or different microphones, requires channel equalisation. In speech recognition, the speech model provides a bank of statistical information that can be used in the channel identification and equalisation process. The authors consider HMM-based channel equalisation, and present results demonstrating that substantial improvement can be obtained through the equalisation process. An alternative method, for speech recognition, is to use a feature set which is more robust to channel distortion. Channel distortions result in an amplitude tilt of the speech cepstrum, and therefore differential cepstral features provide a measure of immunity to channel distortions. In particular the cepstral-time feature matrix, in addition to providing a framework for representing speech dynamics, can be made robust to channel distortions. The authors present results demonstrating that a major advantage of cepstral-time matrices is their channel insensitive character     

Speeded up robust features for efficient iris recognition

Iris recognition system is one of the biometric systems in which the development is growing rapidly. In this paper, speeded up robust features (SURFs) are used for detecting and describing iris keypoints. For feature matching, simple fusion rules are applied at different levels. Contrast-limited adaptive histogram equalization (CLAHE) is applied on the normalized image and is compared with histogram equalization (HE) and adaptive histogram equalization (AHE). The aim is to find the best enhancement technique with SURF and to verify the necessity of iris image enhancement. The recognition accuracy in each case is calculated. Experimental results demonstrate that CLAHE is a crucial enhancement step for SURF-based iris recognition. More keypoints can be extracted with enhancement using CLAHE compared to HE and AHE. This alleviates the problem of feature loss and increases the recognition accuracy. The accuracies of recognition using left and right iris images are 99 and 99.5 %, respectively. Fusion of local distances and choosing suitable fusion rules affect the recognition accuracy, noticeably. The proposed SURF-based algorithm is compared with scale-invariant feature transform, histogram of oriented gradients, maximally stable extremal regions and DAISY. Results show that the proposed algorithm is robust to different image variations and gives the highest recognition accuracy.