Deformation monitoring of a converter station of an electrical power transmission system will help to prevent potential damages to power facilities and properties. Corner reflector InSAR (CRInSAR) enables local deformation measurements in low coherence areas like construction-engineering projects. However, the accuracy of CRInSAR will be degraded by the phase unwrapping errors, especially when the deformation is large or dominated by nonlinear component. This letter reports a study that employs CRInSAR technique to monitor the deformations of ten CRs installed in Xiangtan converter station, China, with seven TerraSAR-X Spotlight images. A two-step phase unwrapping tactics is proposed based on the least squares ambiguity decorrelation adjustment (LAMBDA) algorithm to focus on estimating nonlinear deformation without being affected by unwrapping errors. The results reveal that the two-step LAMBDA algorithm can achieve an accuracy of less than 2 mm for CRInSAR deformation monitoring regardless of small- or large-scale deformations, as validated by the trigonometric leveling measurements.

High spatio-temporal resolution deformation series can be used to improve the understanding of deformation mechanism, thereby contributing to prevention and control of geological disasters such as mine subsidence, landslide, and earthquake. Among ground deformation monitoring technologies, global navigation satellite system has high temporal resolution but low spatial resolution, and interferometric synthetic aperture radar (InSAR) has high spatial resolution but low temporal resolution. Fusing these two data may generate high spatio-temporal resolution deformation series. Existing fusion methods usually use the bi-direction interpolation, which does not consider the spatio-temporal cross correlation and is computationally extensive. We propose a dynamic filtering fusion model based on the spatio-temporal random effect (a spatio-temporal Kalman filter) model. Experiments with simulated data and real data from the Los Angeles area are conducted to validate this method. Simulated experimental results are compared with truth data and the Los Angeles experiment data results are verified using the leave-one InSAR image-out validation method. The RMS results for them are around 13.8 and 5 mm, respectively, indicating that the proposed method can achieve high accuracy and high spatial-temporal resolution deformation time series.

An algorithm to estimate pan, tilt and zoom (PTZ) parameters of a PTZ camera from meta data and frame-to-frame (F2F) correspondences at different sampling rates is proposed in a real-time video surveillance and automatic object tracking system. Two extended Kalman filters are designed to simultaneously estimate zoom and pan-tilt parameters. Uncorrelated constant velocity models are used to model the kinematics of focal length, pan and tilt motions, while the F2F homography is employed to model the relative motion of the camera. Experiment results from both synthetic and real-time system data demonstrate that the F2F correspondence information can enhance the PTZ estimation accuracy as long as its error is smaller than a particular threshold.

The mean shift algorithm has achieved considerable success in object tracking due to its simplicity and robustness. It finds local minima of a similarity measure between the color histograms or kernel density estimates of the model and target image. The most typically used similarity measures are the Bhattacharyya coefficient or the Kullback-Leibler divergence. In practice, these approaches face three difficulties. First, the spatial information of the target is lost when the color histogram is employed, which precludes the application of more elaborate motion models. Second, the classical similarity measures are not very discriminative. Third, the sample-based classical similarity measures require a calculation that is quadratic in the number of samples, making real-time performance difficult. To deal with these difficulties we propose a new, simple-to-compute and more discriminative similarity measure in spatial-feature spaces. The new similarity measure allows the mean shift algorithm to track more general motion models in an integrated way. To reduce the complexity of the computation to linear order we employ the recently proposed improved fast Gauss transform. This leads to a very efficient and robust nonparametric spatial-feature tracking algorithm. The algorithm is tested on several image sequences and shown to achieve robust and reliable frame-rate tracking.

A very efficient and robust visual object tracking algorithm based on the particle filter is presented. The method characterizes the tracked objects using color and edge orientation histogram features. While the use of more features and samples can improve the robustness, the computational load required by the particle filter increases. To accelerate the algorithm while retaining robustness we adopt several enhancements in the algorithm. The first is the use of integral images for efficiently computing the color features and edge orientation histograms, which allows a large amount of particles and a better description of the targets. Next, the observation likelihood based on multiple features is computed in a coarse-to-fine manner, which allows the computation to quickly focus on the more promising regions. Quasi-random sampling of the particles allows the filter to achieve a higher convergence rate. The resulting tracking algorithm maintains multiple hypotheses and offers robustness against clutter or short period occlusions. Experimental results demonstrate the efficiency and effectiveness of the algorithm for single and multiple object tracking.

The computation and memory required for kernel machines with N train- ing samples is at least O(N 2). Such a complexity is significant even for moderate size problems and is prohibitive for large datasets. We present an approximation technique based on the improved fast Gauss transform to reduce the computation to O(N ). We also give an error bound for the approximation, and provide experimental results on the UCI datasets.

Evaluating sums of multivariate Gaussians is a common computational task in computer vision and pattern recognition, including in the general and powerful kernel density estimation technique. The quadratic computational complexity of the summation is a significant barrier to the scalability of this algorithm to practical applications. The fast Gauss transform (FGT) has successfully accelerated the kernel density estimation to linear running time for low-dimensional problems. Unfortunately, the cost of a direct extension of the FGT to higher-dimensional problems grows exponentially with dimension, making it impractical for dimensions above 3. We develop an improved fast Gauss transform to efficiently estimate sums of Gaussians in higher dimensions, where a new multivariate expansion scheme and an adaptive space subdivision technique dramatically improve the performance. The improved FGT has been applied to the mean shift algorithm achieving linear computational complexity. Experimental results demonstrate the efficiency and effectiveness of our algorithm.

Mean-shift analysis is a general nonparametric clustering technique based on density estimation for the analysis of complex feature spaces. The algorithm consists of a simple iterative procedure that shifts each of the feature points to the nearest stationary point along the gradient directions of the estimated density function. It has been successfully applied to many applications such as segmentation and tracking. However, despite its promising performance, there are applications for which the algorithm converges too slowly to be practical. We propose and implement an improved version of the mean-shift algorithm using quasiNewton methods to achieve higher convergence rates. Another benefit of our algorithm is its ability to achieve clustering even for very complex and irregular feature-space topography. Experimental results demonstrate the efficiency and effectiveness of our algorithm.

We present an algorithm for automatic image orientation estimation using a Bayesian learning framework. We demonstrate that a small codebook (the optimal size of codebook is selected using a modified MDL criterion) extracted from a learning vector quantizer (LVQ) can be used to estimate the class-conditional densities of the observed features needed for the Bayesian methodology. We further show how principal component analysis (PCA) and linear discriminant analysis (LDA) can be used as a feature extraction mechanism to remove redundancies in the high-dimensional feature vectors used for classification. The proposed method is compared with four different commonly used classifiers, namely k-nearest neighbor, support vector machine (SVM), a mixture of Gaussians, and hierarchical discriminating regression (HDR) tree. Experiments on a database of 16 344 images have shown that our proposed algorithm achieves an accuracy of approximately 98% on the training set and over 97% on an independent test set. A slight improvement in classification accuracy is achieved by employing classifier combination techniques.

Inspired by the technique proposed by Zhang (1998), we proposed a camera calibration technique, which only requires observing three or more planar concentric conics at a few (at least two) different orientations. All computations involved are linear matrix manipulations. Compared with the classical techniques where an expensive calibration pattern is commonly used, our technique is easy to implement and more flexible. Using conics also simplifies the problem of correspondence. Both computer simulation and real data are used to test the proposed technique.

This paper presents a new camera intrinsic parameters self-calibration technique for ordinary active vision system. By controlling a pan-tilt-translation camera platform to do a sequence of specially designed motions (called a camera motion configuration here), we rigorously proved that the camera intrinsic parameters can be determined linearly under such two configurations: (1)regulating the camera’s orientation by 3 tilts, at each camera’s orientation, controlling the camera to translate twice along 2 orthogonal directions; (2)regulating the camera’s orientation by 1 pan and 2 tilts, at each camera’s orientation, controlling the camera to translate twice along 2 orthogonal directions. Furthermore, based on extensive simulations of stability analysis, it is shown that the configuration 2 is robust, whereas the configuration 1 is numerically unstable and sensitive to noise. Experiments with real data were carried out and the calibration results have been verified by a stereo vision experiment. A comparison with other camera calibration approaches is also reported here. 1.