In this paper, we propose a new framework to visualize hyperspectral images. We present three goals for such a visualization: 1) preservation of spectral distances; 2) discriminability of pixels with different spectral signatures; 3) and interactive visualization for analysis. The introduced method considers all three goals at the same time and produces higher quality output than existing methods. The technical contribution of our mapping is to derive a simplified convex optimization from a complex nonlinear optimization problem. During interactive visualization, we can map the spectral signature of pixels to red, green, and blue colors using a combination of principal component analysis and linear programming. In the results, we present a quantitative analysis to demonstrate the favorable attributes of our algorithm.

This paper presents a robust extrinsic parameter estimation algorithm to calibrate field cameras which were used to observe the formation of clouds on a mountainous region. Generally, camera calibration needs accurate landmark survey and image feature identification. However, our observation area is a large scale scene in a physically inaccessible area, therefore the landmark surveys are not precise. Since clouds are distant to cameras, cloud features in the images are also difficult to accurately identify for stereo correspondences. The noise in landmark survey and cloud feature correspondence makes it challenging to obtain desired cloud observation accuracy by using traditional least squares based camera calibration approaches. Our camera calibration approach is based on a generalized total least square (GTLS) algorithm instead of a normal least square method. Experiments show that the GTLS-based camera calibration is more accurate and robust than LS-based methods for our application.

In this paper, an automatic road tracking method is presented for detecting roads from satellite images. This method is based on shape classification of a local homogeneous region around a pixel. The local homogeneous region is enclosed by a polygon, called the pixel footprint. We introduce a spoke wheel operator to obtain the pixel footprint and propose a Fourier-based approach to classify footprints for automatic seeding and growing of the road tracker. We experimentally demonstrate that our proposed road tracker can extract the centerlines of roads with sharp turns and intersections effectively, and has relatively small amount of leakage.

In this paper, a new two-step approach (detecting and pruning) for automatic extraction of road networks from aerial images is presented. The road detection step is based on shape classification of a local homogeneous region around a pixel. The local homogeneous region is enclosed by a polygon, called the footprint of the pixel. This step involves detecting road footprints, tracking roads, and growing a road tree. We use a spoke wheel operator to obtain the road footprint. We propose an automatic road seeding method based on rectangular approximations to road footprints and a toe-finding algorithm to classify footprints for growing a road tree. The road tree pruning step makes use of a Bayes decision model based on the area-to-perimeter ratio (the A/P ratio) of the footprint to prune the paths that leak into the surroundings. We introduce a lognormal distribution to characterize the conditional probability of A/P ratios of the footprints in the road tree and present an automatic method to estimate the parameters that are related to the Bayes decision model. Results are presented for various aerial images. Evaluation of the extracted road networks using representative aerial images shows that the completeness of our road tracker ranges from 84% to 94%, correctness is above 81%, and quality is from 82% to 92%.

In this paper, we present a deformable surface geometric model for segmenting targets from volumetric data. This model deforms under external forces only, and changes its geometry and topology by using improved geometric constraints. External forces are calculated by using the sum of inflation forces, whose contributions take place on internal regions of objects, and the gradient forces, which play a key role when the surface is near the boundary of objects. A new set of geometric constraints is proposed which includes constraints on vertices, edges and faces. Once a constraint is broken, the corresponding topological transformation will occur to keep the geometric and topological integrity of the surface unaltered. We demonstrate that our model can efficiently segment complex anatomic structures from medical 3D images, and achieve the requirements of accuracy and geometry for image segmentation.

The concentration edge -detection and Gegenbauer image-reconstruction methods were previously shown to improve the quality of segmentation in magnetic resonance imaging. In this study, these methods are utilized as a pre-processing step to the Weibull E-SD field segmentation. It is demonstrated that the combination of the concentration edge detection and Gegenbauer reconstruction method improves the accuracy of segmentation for the simulated test data and real magnetic resonance images used in this study.

This paper presents a coarse-grain approach for segmentation of objects with gray levels appearing in volume data. The input data is on a 3D structured grid of vertices v(i. j. k), each associated with a scalar value. In this paper, we consider a voxel as a /spl kappa/ /spl times/ /spl kappa/ /spl times/ /spl kappa/ cube and each voxel is assigned two values: expectancy and standard deviation (E-SD). We use the Weibull noise index to estimate the noise in a voxel and to obtain more precise E-SD values for each voxel. We plot the frequency of voxels which have the same E-SD, then 3D segmentation based on the Weibull E-SD field is presented. Our test bed includes synthetic data as well as real volume data from a confocal laser scanning microscope (CLSM). Analysis of these data all show distinct and defining regions in their E-SD fields. Under the guide of the E-SD field, we can efficiently segment the objects embedded in real and simulated 3D data.