Landmark Matching Research Articles

Landmark-assisted location and tracking in outdoor mobile network

Modern mobile devices integrating sensors, like accelerometers and cameras, are paving the way to the definition of high-quality and accurate geolocation solutions based on the informations acquired by these sensors, and data collected and managed by GSM/3G networks. In this paper, we present a technique that provides geolocation and mobility prediction of mobile devices, mixing the location information acquired with the GSM/3G infrastructure and the results of a landmark matching achieved thanks to the camera integrated on the mobile devices. Our geolocation approach is based on an advanced Time-Forwarding algorithm and on database correlation technique over Received Signal Strength Indication (RSSI) data, and integrates information produced by a landmark recognition infrastructure, to enhance algorithm performances in those areas with poor signal and low accurate geolocation. Performances of the algorithm are evaluated on real data from a complex urban environment.

A new approach to quantifying lung damage after stereotactic body radiation therapy

Radiological pneumonitis and fibrosis are common after stereotactic body radiotherapy (SBRT) but current scoring systems are qualitative and subjective. We evaluated the use of CT density measurements and a deformable registration tool to quantitatively measure lung changes post-SBRT. Material and methods. Four-dimensional CT datasets from 25 patients were imported into an image analysis program. Deformable registration was done using a B-spline algorithm (VelocityAI) and evaluated by landmark matching. The effects of respiration, contrast, and CT scanner on density measurements were evaluated. The relationship between density and clinician-scored radiological pneumonitis was assessed. Results. Deformable registration resulted in more accurate image matching than rigid registration. CT lung density was maximal at end-expiration, and most deformation with breathing occurred in the lower thorax. Use of contrast increased mean lung density by 18 HU (range 16–20 HU; p = 0.004). Diagnostic scans had a lower mean lung density than planning scans (mean difference 57 HU in lung contralateral to tumor; p = 0.048). Post-treatment CT density measurements correlated strongly with clinician-scored radiological pneumonitis (r = 0.75; p < 0.001). Conclusions. Quantitative analysis of changes in lung density correlated strongly with physician-assigned radiologic pneumonitis scores. Deformable registration and CT density measurements permit objective assessment of treatment toxicity.

Information-Theoretic Directly Manipulated Free-Form Deformation Labeled Point-Set Registration

Our previous contributions to the ITK community include a generalized B-spline approximation scheme as well as a generalized information-theoretic measure for assessing point-set correspondence known as the Jensen-Havrda-Charvat-Tsallis (JHCT) divergence. In this submission, we combine these two contributions for the registration of labeled point-sets. The transformation model which uses the former contribution is denoted as directly manipulated free-form deformation (DMFFD) and has been used for image registration. The information-theoretic approach described not only eliminates exact cardinality constraints which plague exact landmark matching algorithms, but it also incorporates the local point-set structure into the similarity measure calculation. Although theoretical discussion of these two components is deferred to other venues, the implementation details given in this submission should be adequate for those wishing to use our algorithm. Visualization of results is aided by another of our previous contributions. Additionally, we provide the rudimentary command line parsing classes used in our testing routines which were written in the ITK style and also available to use consistent with the open-source paradigm.

Optimized Conformal Surface Registration with Shape-based Landmark Matching

Surface registration, which transforms different sets of surface data into one common reference space, is an important process which allows us to compare or integrate the surface data effectively. If a nonrigid transformation is required, surface registration is commonly done by parameterizing the surfaces onto a simple parameter domain, such as the unit square or sphere. In this work, we are interested in looking for meaningful registrations between surfaces through parameterizations, using prior features in the form of landmark curves on the surfaces. In particular, we generate optimized conformal parameterizations which match landmark curves exactly with shape-based correspondences between them. We propose a variational method to minimize a compound energy functional that measures the harmonic energy of the parameterization maps and the shape dissimilarity between mapped points on the landmark curves. The novelty is that the computed maps are guaranteed to align the landmark features consistently and give a shape-based diffeomorphism between the landmark curves. We achieve this by intrinsically modeling our search space of maps as flows of smooth vector fields that do not flow across the landmark curves. By using the local surface geometry on the curves to define a shape measure, we compute registrations that ensure consistent correspondences between anatomical features. We test our algorithm on synthetic surface data. An application of our model to medical imaging research is shown, using experiments on brain cortical surfaces, with anatomical (sulcal) landmarks delineated, which show that our computed maps give a shape-based alignment of the sulcal curves without significantly impairing conformality. This ensures correct averaging and comparison of data across subjects.

Intelligent Sensing Systems for Rescue Robots: Landmark Identification and Three-Dimensional Mapping of Unknown Cluttered Urban Search and Rescue Environments

In this paper a unique landmark identification method is proposed for identifying large distinguishable landmarks for three-dimensional (3-D) visual simultaneous localization and mapping (SLAM) in unknown cluttered urban search and rescue (USAR) environments. The novelty of the method is the utilization of both 3-D (i.e., depth images) and 2-D images. By utilizing a scale-invariant feature transform (SIFT)-based approach and incorporating 3-D depth imagery, we can achieve more reliable and robust recognition and matching of landmarks from multiple images for 3-D mapping of the environment. Preliminary experiments utilizing the proposed methodology verify (i) its ability to identify clusters of SIFT keypoints in both 3-D and 2-D images for representation of potential landmarks in the scene, and (ii) the use of the identified landmarks in constructing a 3-D map of unknown cluttered USAR environments via 3-D visual SLAM.

Image Navigation for the FY2 Geosynchronous Meteorological Satellite

Abstract An automatic image navigation algorithm for Feng Yun 2 (FY2) spin-stabilized geosynchronous meteorological satellites was determined at the National Satellite Meteorological Center (NSMC) of the China Meteorological Administration (CMA). This paper derives the parameters and coordinate systems used in FY2 image navigation, with an emphasis on attitude and misalignment parameters. The solution to the navigation model does not depend on any landmark matching. The time series dataset of the satellite orientation with respect to the center line of the earth’s disk contains information on the two components of the attitude (orientation of the satellite spin axis) and the roll component of the misalignment. With this information, the two attitude components can be solved simultaneously, expressed as declination and right ascension (with diurnal variation in the fixed earth coordinate system) and the roll component of the misalignment (with no diurnal variation). In each spin cycle, the satellite views the sun and earth. The position of the sun is detected and used to align earth observation pixels in the scan line together with an angle subtended at the satellite by the sun and earth (β). With satellite position and attitude known, the β angle can be calculated and predicted with sufficient accuracy. Next, the image is assembled. Prediction of the β angle takes an important role in the image formation process, as imperfect β angle prediction may cause east–west shift and image deformation. In the image registration process of FY2, both the east–west shift and the image deformation are compensated for. The above-mentioned solution to the navigation model requires accurate knowledge of astronomical parameters and coordinate systems. The orbital, attitude, misalignment, and β angle parameters are produced automatically and routinely without any manual operation. Image navigation accuracy for the FY2 geosynchronous meteorological satellite approaches 5 km at the subsatellite point (SSP).

Brain structural abnormalities in survivors of pediatric posterior fossa brain tumors: A voxel-based morphometry study using free-form deformation

Voxel-based morphometry was used to compare brain structure of survivors of posterior fossa brain tumor (PFBT) with that of normal sibling controls to investigate disease- or cancer treatment-induced changes. Two different spatial normalization approaches that are available in public domain software (free-form deformation (FFD) and discrete cosine transform (DCT)) were compared for accuracy of normalization in the PFBT patients. Anatomical landmark matching demonstrated that spatial normalization was more accurate with FFD than with DCT. Voxel-based morphometry of the FFD-normalized magnetic resonance images from PFBT survivors and sibling controls detected reduced gray matter density in the thalamus and entorhinal cortex and reduced white matter density in the internal capsule, hypothalamus, corpus callosum, and cuneus of the occipital lobe in the PFBT survivors. Identification of these morphologic lesions may help localize the neural substrates of disease- or therapy-induced cognitive deficits in survivors of childhood cancer.

Mobile Robot Self-Localization and Local Map Alignment with a Dempster Shafer Sensor Fusion Algorithm

An important and challenging research issue associated with mobile robots is simultaneous localization and map building (SLAM), which refers to the mobile robot's capability of estimating its poses in the environment without external information, and simultaneous alignment of the local maps. To solve these kinds of research problems, researchers have proposed various methods such as odometry measurement, landmark matching, laser range image matching and a scale-invariant feature transform (SIFT)–based algorithm, all of which suffer from inevitable drawbacks such as a local minimum problem and a lack of SIFT features. Our solution for these problems is a sensor fusion method that uses a Dempster Shafer algorithm to fuse both the laser range information and the SIFT features information for the SLAM. Through a series of experiments, we tested and evaluated the proposed method. By real experiments, we analyzed the parameters of the ICP and SIFT features and we checked the robustness of our algorithm.

Automated Breath-Hold Perfusion SPECT/CT Fusion Images of the Lungs

The purpose of this study was to evaluate the clinical applicability and feasibility of deep-inspiratory breath-hold (DIBrH) perfusion SPECT for improving adverse respiratory motion effects and for accuracy of SPECT/CT image fusion. Eighty-seven consecutive patients with chronic obstructive pulmonary disease (COPD) (n = 43), acute pulmonary thromboembolism (PTE) (n = 26), and interstitial lung disease (ILD), (n = 18), underwent respiratory-monitored DIBrH SPECT with a dual-headed SPECT system. Two COPD and four acute PTE patients were excluded because of inappropriate scanning due to DIBrH difficulty. DIBrH SPECT was automatically fused with DIBrH CT. Perfusion defect clarity and heterogeneity and SPECT/CT matching were compared between DIBrH SPECT and non-breath-hold SPECT. Compared with non-breath-hold SPECT, DIBrH SPECT significantly enhanced defect clarity in acute PTE (p < 0.0001) and perfusion heterogeneity (coefficient of variations [CV] of pixel counts) in COPD and ILD (p < 0.0001). CV in COPD was also better correlated with lung diffusing capacity for carbon monoxide (p < 0.05). DIBrH SPECT also significantly improved SPECT/CT matching (p < 0.0001), with excellent matching of CT lung internal landmarks and pathology with corresponding defects. Fusion images confirmed wedge-shaped defects extending along specific pulmonary arterial branches in acute PTE and heterogeneous defects associated with airway or lung parenchymal abnormalities in COPD and ILD, with perfusion distribution consistent with lung CT attenuation changes. DIBrH SPECT is acceptable for routine application to improve respiratory motion effects and accuracy of SPECT/CT image fusion. Confirmative perfusion-morphologic correlation with reliable fusion images appears useful for clarifying the cause of perfusion defects and abnormal lung CT attenuation.

Diffeomorphic metric surface mapping in subregion of the superior temporal gyrus

This paper describes the application of large deformation diffeomorphic metric mapping to cortical surfaces based on the shape and geometric properties of subregions of the superior temporal gyrus in the human brain. The anatomical surfaces of the cortex are represented as triangulated meshes. The diffeomorphic matching algorithm is implemented by defining a norm between the triangulated meshes, based on the algorithms of Vaillant and Glaunès. The diffeomorphic correspondence is defined as a flow of the extrinsic three dimensional coordinates containing the cortical surface that registers the initial and target geometry by minimizing the norm. The methods are demonstrated in 40 high-resolution MRI cortical surfaces of planum temporale (PT) constructed from subsets of the superior temporal gyrus (STG). The effectiveness of the algorithm is demonstrated via the Euclidean positional distance, distance of normal vectors, and curvature before and after the surface matching as well as the comparison with a landmark matching algorithm. The results demonstrate that both the positional and shape variability of the anatomical configurations are being represented by the diffeomorphic maps.

A variational approach to blending based on warping for non-overlapped images

This paper presents a new model for image blending based on warping. The model is represented by partial differential equations (PDEs) and gives a sequence of images, which has the properties of both blending of image intensities and warping of image shapes. We modified the energy functional in [W.-H. Liao, A. Khuu, M. Bergsneider, L. Vese, S.-C. Huang, S. Osher, From Landmark Matching to Shape and Open Curve Matching: A Level Set Approach, Computational and Applied Mathematics (CAM) Technical Reports 02-59, UCLA, 2002.] in order to adapt the idea of the shape warping to the image blending. The PDEs from the proposed energy functional cover not only overlapped images but also non-overlapped ones.

PEPPeR, a Platform for Experimental Proteomic Pattern Recognition

Quantitative proteomics holds considerable promise for elucidation of basic biology and for clinical biomarker discovery. However, it has been difficult to fulfill this promise due to over-reliance on identification-based quantitative methods and problems associated with chromatographic separation reproducibility. Here we describe new algorithms termed "Landmark Matching" and "Peak Matching" that greatly reduce these problems. Landmark Matching performs time base-independent propagation of peptide identities onto accurate mass LC-MS features in a way that leverages historical data derived from disparate data acquisition strategies. Peak Matching builds upon Landmark Matching by recognizing identical molecular species across multiple LC-MS experiments in an identity-independent fashion by clustering. We have bundled these algorithms together with other algorithms, data acquisition strategies, and experimental designs to create a Platform for Experimental Proteomic Pattern Recognition (PEPPeR). These developments enable use of established statistical tools previously limited to microarray analysis for treatment of proteomics data. We demonstrate that the proposed platform can be calibrated across 2.5 orders of magnitude and can perform robust quantification of ratios in both simple and complex mixtures with good precision and error characteristics across multiple sample preparations. We also demonstrate de novo marker discovery based on statistical significance of unidentified accurate mass components that changed between two mixtures. These markers were subsequently identified by accurate mass-driven MS/MS acquisition and demonstrated to be contaminant proteins associated with known proteins whose concentrations were designed to change between the two mixtures. These results have provided a real world validation of the platform for marker discovery.

Geodesic Matching with Free Extremities

In this paper, we describe how to use geodesic energies defined on various sets of objects to solve several distance related problems. We first present the theory of metamorphoses and the geodesic distances it induces on a Riemannian manifold, followed by classical applications in landmark and image matching. We then explain how to use the geodesic distance for new issues, which can be embedded in a general framework of matching with free extremities. This is illustrated by results on image and shape averaging and unlabeled landmark matching.

Image Registration Based on Lifting Process: An Application to Digital Subtraction Radiography

In this paper, a digital subtraction radiology scheme is presented based on a new method for the automatic registration of dental radiographs acquired with or without rigorous a priori standardization. The scheme is comprised of an automatic registration method and a subtraction process. The proposed registration method can be considered as an object-based registration method without imposing the prerequisite of image segmentation in order to detect the boundary of the objects of interest or the automatic detection of matching landmarks. This is achieved by augmenting the dimensionality of the problem from two-dimensional gray-level matching to three-dimensional surface matching using the process of lifting in combination with a surface-matching technique. The pseudo three-dimensional affine transformation that matches the lifted images incorporates advantageous characteristics including spatial alignment of the surfaces, anisotropic correction of brightness/contrast differences, and stable convergence of the similarity function to its optimal value. The performance of the proposed automatic registration method is assessed against a manual method based on the projective transformation. The qualitative and quantitative assessments of the experiments have shown advantageous performance of the proposed automatic registration method against the manual one. Finally, the proposed registration method has been further improved in terms of execution time by the implementation of a surface decimation process.

Combining geodesic interpolating splines and affine transformations

Geodesic spline interpolation is a simple and efficient approach for landmark matching by nonambiguous mappings (diffeomorphisms), combining classic spline interpolation and flows of diffeomorphisms. Here, we extend the method to incorporate the estimation of a affine transformation, yielding a consistent and numerically stable algorithm. A theoretical justification is provided by studying the existence of the global minimum of the energy.

LANDMARK MATCHING ON THE SPHERE USING DISTANCE FUNCTIONS.

Nonlinear registration of 3D surfaces is important in many medical imaging applications, including the mapping of longitudinal changes in anatomy, or of multi-subject functional MRI data to a canonical surface for comparison and integration. To register 3D surfaces, such as the cortical surface of the brain, one approach is to transform them first to planar or spherical objects. Internal landmarks can then be matched on these simpler parameter domains. Here we study the diffeomorphic matching of landmarks on the sphere. Our method builds on the level set technique of Leow et al. [1] for the plane. Both forward and backward matching terms are included, thus ensuring the invertibility of the representation. We demonstrate our technique on a pair of lines on the sphere. The overall approach improves on earlier work in cortical matching by allowing the matching energy to be relaxed along sulcal landmarks, minimizing distortion, and also enables point and curve landmarks to be aligned in the same general framework as densely-defined scalar fields, such as curvature or cortical thickness maps.

Probabilistic relaxation method of matching visual landmarks for controlling the accurate positioning of mobile robots

The navigation problem of controlling the accurate positioning of a mobile robot (MR) with a computer vision system under conditions of uncertainty of information about its position is considered. Visual servo control is used, in which the error signal is calculated as the difference in the coordinates of natural visual landmarks detected by the computer vision system on the current and reference (received in a target position) images. To compute the error signal, a probabilistic relaxation method of correct matching of the landmarks extracted in the image is proposed. The efficiency of the proposed method has been confirmed by numerical experiments for processing real images.

Moving meshes by the deformation method

In this paper, we describe the deformation method for generation of moving meshes and its applications in computational fluid dynamics (CFD), and potential applications for image representation, segmentation, and landmark matching for image registration. We demonstrate that the deformation method can generate meshes of prescribed cell area. Numerical examples are presented to confirm that.

Vision-based localization algorithm based on landmark matching, triangulation, reconstruction, and comparison

Many generic position-estimation algorithms are vulnerable to ambiguity introduced by nonunique landmarks. Also, the available high-dimensional image data is not fully used when these techniques are extended to vision-based localization. This paper presents the landmark matching, triangulation, reconstruction, and comparison (LTRQ global localization algorithm, which is reasonably immune to ambiguous landmark matches. It extracts natural landmarks for the (rough) matching stage before generating the list of possible position estimates through triangulation. Reconstruction and comparison then rank the possible estimates. The LTRC algorithm has been implemented using an interpreted language, onto a robot equipped with a panoramic vision system. Empirical data shows remarkable improvement in accuracy when compared with the established random sample consensus method. LTRC is also robust against inaccurate map data.

Geometric determinants of human spatial memory

Geometric alterations to the boundaries of a virtual environment were used to investigate the representations underlying human spatial memory. Subjects encountered a cue object in a simple rectangular enclosure, with distant landmarks for orientation. After a brief delay, during which they were removed from the arena, subjects were returned to it at a new location and orientation and asked to mark the place where the cue had been. On some trials the geometry (size, aspect ratio) of the arena was varied between presentation and testing. Responses tended to lie somewhere between a location that maintained fixed distances from nearby walls and a location that maintained fixed ratios of the distances between opposing walls. The former were more common after expansions and for cued locations nearer to the edge while the latter were more common after contractions and for locations nearer to the center. The spatial distributions of responses predicted by various simple geometric models were compared to the data. The best fitting model was one derived from the response properties of ‘place cells’ in the rat hippocampus, which matches the ‘proximities’ 1/( d+ c) of the cue to the four walls of the arena, where d is the distance to a wall and c is a global constant. Subjects also tended to adopt the same orientation at presentation and testing, although this was not due to using a view matching strategy, which could be ruled out in 50% of responses. Disoriented responses were most often seen where the cued location was near the center of the arena or where the long axis of a rectangular arena was changed between presentation and testing, suggesting that the geometry of the arena acts as a weak cue to orientation. Overall, the results suggest a process of visual landmark matching to determine orientation, combined with an abstract representation of the proximity of the cued location to the walls of the arena consistent with the neural representation of location in the hippocampus.