Desenvolvimento de um aplicativo para processamento de imagens obtidas por fotografias aéreas

Pós-graduação em Agronomia (Energia na Agricultura) - FCA

Efficient subsequence alignment of time series

Zeitreihen sind allgegenwärtig. Die Erfassung und Verarbeitung kontinuierlich gemessener Daten ist in allen Bereichen der Naturwissenschaften, Medizin und Finanzwelt vertreten. Das enorme Anwachsen aufgezeichneter Datenmengen, sei es durch automatisierte Monitoring-Systeme oder integrierte Sensoren, bedarf außerordentlich schneller Algorithmen in Theorie und Praxis. Infolgedessen beschäftigt sich diese Arbeit mit der effizienten Berechnung von Teilsequenzalignments. Komplexe Algorithmen wie z.B. Anomaliedetektion, Motivfabfrage oder die unüberwachte Extraktion von prototypischen Bausteinen in Zeitreihen machen exzessiven Gebrauch von diesen Alignments. Darin begründet sich der Bedarf nach schnellen Implementierungen. Diese Arbeit untergliedert sich in drei Ansätze, die sich dieser Herausforderung widmen. Das umfasst vier Alignierungsalgorithmen und ihre Parallelisierung auf CUDA-fähiger Hardware, einen Algorithmus zur Segmentierung von Datenströmen und eine einheitliche Behandlung von Liegruppen-wertigen Zeitreihen.rnrnDer erste Beitrag ist eine vollständige CUDA-Portierung der UCR-Suite, die weltführende Implementierung von Teilsequenzalignierung. Das umfasst ein neues Berechnungsschema zur Ermittlung lokaler Alignierungsgüten unter Verwendung z-normierten euklidischen Abstands, welches auf jeder parallelen Hardware mit Unterstützung für schnelle Fouriertransformation einsetzbar ist. Des Weiteren geben wir eine SIMT-verträgliche Umsetzung der Lower-Bound-Kaskade der UCR-Suite zur effizienten Berechnung lokaler Alignierungsgüten unter Dynamic Time Warping an. Beide CUDA-Implementierungen ermöglichen eine um ein bis zwei Größenordnungen schnellere Berechnung als etablierte Methoden.rnrnAls zweites untersuchen wir zwei Linearzeit-Approximierungen für das elastische Alignment von Teilsequenzen. Auf der einen Seite behandeln wir ein SIMT-verträgliches Relaxierungschema für Greedy DTW und seine effiziente CUDA-Parallelisierung. Auf der anderen Seite führen wir ein neues lokales Abstandsmaß ein, den Gliding Elastic Match (GEM), welches mit der gleichen asymptotischen Zeitkomplexität wie Greedy DTW berechnet werden kann, jedoch eine vollständige Relaxierung der Penalty-Matrix bietet. Weitere Verbesserungen umfassen Invarianz gegen Trends auf der Messachse und uniforme Skalierung auf der Zeitachse. Des Weiteren wird eine Erweiterung von GEM zur Multi-Shape-Segmentierung diskutiert und auf Bewegungsdaten evaluiert. Beide CUDA-Parallelisierung verzeichnen Laufzeitverbesserungen um bis zu zwei Größenordnungen.rnrnDie Behandlung von Zeitreihen beschränkt sich in der Literatur in der Regel auf reellwertige Messdaten. Der dritte Beitrag umfasst eine einheitliche Methode zur Behandlung von Liegruppen-wertigen Zeitreihen. Darauf aufbauend werden Distanzmaße auf der Rotationsgruppe SO(3) und auf der euklidischen Gruppe SE(3) behandelt. Des Weiteren werden speichereffiziente Darstellungen und gruppenkompatible Erweiterungen elastischer Maße diskutiert.

Assessment of spline-based 2D-3D registration for image-guided spine surgery

2D-3D registration of pre-operative 3D volumetric data with a series of calibrated and undistorted intra-operative 2D projection images has shown great potential in CT-based surgical navigation because it obviates the invasive procedure of the conventional registration methods. In this study, a recently introduced spline-based multi-resolution 2D-3D image registration algorithm has been adapted together with a novel least-squares normalized pattern intensity (LSNPI) similarity measure for image guided minimally invasive spine surgery. A phantom and a cadaver together with their respective ground truths were specially designed to experimentally assess possible factors that may affect the robustness, accuracy, or efficiency of the registration. Our experiments have shown that it is feasible for the assessed 2D-3D registration algorithm to achieve sub-millimeter accuracy in a realistic setup in less than one minute.

Unifying energy minimization and mutual information maximization for robust 2D/3D registration of X-ray and CT images

Similarity measure is one of the main factors that affect the accuracy of intensity-based 2D/3D registration of X-ray fluoroscopy to CT images. Information theory has been used to derive similarity measure for image registration leading to the introduction of mutual information, an accurate similarity measure for multi-modal and mono-modal image registration tasks. However, it is known that the standard mutual information measure only takes intensity values into account without considering spatial information and its robustness is questionable. Previous attempt to incorporate spatial information into mutual information either requires computing the entropy of higher dimensional probability distributions, or is not robust to outliers. In this paper, we show how to incorporate spatial information into mutual information without suffering from these problems. Using a variational approximation derived from the Kullback-Leibler bound, spatial information can be effectively incorporated into mutual information via energy minimization. The resulting similarity measure has a least-squares form and can be effectively minimized by a multi-resolution Levenberg-Marquardt optimizer. Experimental results are presented on datasets of two applications: (a) intra-operative patient pose estimation from a few (e.g. 2) calibrated fluoroscopic images, and (b) post-operative cup alignment estimation from single X-ray radiograph with gonadal shielding.

NEW TOOLS FOR MONITORING GAMMA CAMERA UNIFORMITY

Detector uniformity is a fundamental performance characteristic of all modern gamma camera systems, and ensuring a stable, uniform detector response is critical for maintaining clinical images that are free of artifact. For these reasons, the assessment of detector uniformity is one of the most common activities associated with a successful clinical quality assurance program in gamma camera imaging. The evaluation of this parameter, however, is often unclear because it is highly dependent upon acquisition conditions, reviewer expertise, and the application of somewhat arbitrary limits that do not characterize the spatial location of the non-uniformities. Furthermore, as the goal of any robust quality control program is the determination of significant deviations from standard or baseline conditions, clinicians and vendors often neglect the temporal nature of detector degradation (1). This thesis describes the development and testing of new methods for monitoring detector uniformity. These techniques provide more quantitative, sensitive, and specific feedback to the reviewer so that he or she may be better equipped to identify performance degradation prior to its manifestation in clinical images. The methods exploit the temporal nature of detector degradation and spatially segment distinct regions-of-non-uniformity using multi-resolution decomposition. These techniques were tested on synthetic phantom data using different degradation functions, as well as on experimentally acquired time series floods with induced, progressively worsening defects present within the field-of-view. The sensitivity of conventional, global figures-of-merit for detecting changes in uniformity was evaluated and compared to these new image-space techniques. The image-space algorithms provide a reproducible means of detecting regions-of-non-uniformity prior to any single flood image’s having a NEMA uniformity value in excess of 5%. The sensitivity of these image-space algorithms was found to depend on the size and magnitude of the non-uniformities, as well as on the nature of the cause of the non-uniform region. A trend analysis of the conventional figures-of-merit demonstrated their sensitivity to shifts in detector uniformity. The image-space algorithms are computationally efficient. Therefore, the image-space algorithms should be used concomitantly with the trending of the global figures-of-merit in order to provide the reviewer with a richer assessment of gamma camera detector uniformity characteristics.

A Multiresolution Image Alignment Technique Based on Direct Methods for Pose Estimation of Aerial Vehicles

In this paper, we seek to expand the use of direct methods in real-time applications by proposing a vision-based strategy for pose estimation of aerial vehicles. The vast majority of approaches make use of features to estimate motion. Conversely, the strategy we propose is based on a MR (Multi-Resolution) implementation of an image registration technique (Inverse Compositional Image Alignment ICIA) using direct methods. An on-board camera in a downwards-looking configuration, and the assumption of planar scenes, are the bases of the algorithm. The motion between frames (rotation and translation) is recovered by decomposing the frame-to-frame homography obtained by the ICIA algorithm applied to a patch that covers around the 80% of the image. When the visual estimation is required (e.g. GPS drop-out), this motion is integrated with the previous known estimation of the vehicles' state, obtained from the on-board sensors (GPS/IMU), and the subsequent estimations are based only on the vision-based motion estimations. The proposed strategy is tested with real flight data in representative stages of a flight: cruise, landing, and take-off, being two of those stages considered critical: take-off and landing. The performance of the pose estimation strategy is analyzed by comparing it with the GPS/IMU estimations. Results show correlation between the visual estimation obtained with the MR-ICIA and the GPS/IMU data, that demonstrate that the visual estimation can be used to provide a good approximation of the vehicle's state when it is required (e.g. GPS drop-outs). In terms of performance, the proposed strategy is able to maintain an estimation of the vehicle's state for more than one minute, at real-time frame rates based, only on visual information.

ITEM: Inter-Texture Error Measurement for 3D Meshes

We introduce a simple and innovative method to compare any two texture maps, regardless of their sizes, aspect ratios, or even masks, as long as they are both meant to be mapped onto the same 3D mesh. Our system is based on a zero-distortion 3D mesh unwrapping technique which compares two new adapted texture atlases with the same mask but different texel colors, and whose every texel covers the same area in 3D. Once these adapted atlases are created, we measure their difference with ITEM-RMSE, a slightly modified version of the standard RMSE defined for images. ITEM-RMSE is more meaningful and reliable than RMSE because it only takes into account the texels inside the mask, since they are the only ones that will actually be used during rendering. Our method is not only very useful to compare the space efficiency of different texture atlas generation algorithms, but also to quantify texture loss in compression schemes for multi-resolution textured 3D meshes.

Minimal template size for Iris-Recognition

A method to achieve improvement in template size for an iris-recognition system is reported. To achieve this result, the biological characteristics of the human iris have been studied. Processing has been performed by image processing techniques, isolating the iris and enhancing the area of study, after which multi resolution analysis is made. Reduction of the pattern obtained has been obtained via statistical study.

A scaleless data model for direct and progressive spatial query processing

A progressive spatial query retrieves spatial data based on previous queries (e.g., to fetch data in a more restricted area with higher resolution). A direct query, on the other side, is defined as an isolated window query. A multi-resolution spatial database system should support both progressive queries and traditional direct queries. It is conceptually challenging to support both types of query at the same time, as direct queries favour location-based data clustering, whereas progressive queries require fragmented data clustered by resolutions. Two new scaleless data structures are proposed in this paper. Experimental results using both synthetic and real world datasets demonstrate that the query processing time based on the new multiresolution approaches is comparable and often better than multi-representation data structures for both types of queries.

Multisensorial obstacles detection and classification for ADAS and autonomous driving

A reliable perception of the real world is a key-feature for an autonomous vehicle and the Advanced Driver Assistance Systems (ADAS). Obstacles detection (OD) is one of the main components for the correct reconstruction of the dynamic world. Historical approaches based on stereo vision and other 3D perception technologies (e.g. LIDAR) have been adapted to the ADAS first and autonomous ground vehicles, after, providing excellent results. The obstacles detection is a very broad field and this domain counts a lot of works in the last years. In academic research, it has been clearly established the essential role of these systems to realize active safety systems for accident prevention, reflecting also the innovative systems introduced by industry. These systems need to accurately assess situational criticalities and simultaneously assess awareness of these criticalities by the driver; it requires that the obstacles detection algorithms must be reliable and accurate, providing: a real-time output, a stable and robust representation of the environment and an estimation independent from lighting and weather conditions. Initial systems relied on only one exteroceptive sensor (e.g. radar or laser for ACC and camera for LDW) in addition to proprioceptive sensors such as wheel speed and yaw rate sensors. But, current systems, such as ACC operating at the entire speed range or autonomous braking for collision avoidance, require the use of multiple sensors since individually they can not meet these requirements. It has led the community to move towards the use of a combination of them in order to exploit the benefits of each one. Pedestrians and vehicles detection are ones of the major thrusts in situational criticalities assessment, still remaining an active area of research. ADASs are the most prominent use case of pedestrians and vehicles detection. Vehicles should be equipped with sensing capabilities able to detect and act on objects in dangerous situations, where the driver would not be able to avoid a collision. A full ADAS or autonomous vehicle, with regard to pedestrians and vehicles, would not only include detection but also tracking, orientation, intent analysis, and collision prediction. The system detects obstacles using a probabilistic occupancy grid built from a multi-resolution disparity map. Obstacles classification is based on an AdaBoost SoftCascade trained on Aggregate Channel Features. A final stage of tracking and fusion guarantees stability and robustness to the result.

From cardinal spline wavelet bases to highly coherent dictionaries

Wavelet families arise by scaling and translations of a prototype function, called the mother wavelet. The construction of wavelet bases for cardinal spline spaces is generally carried out within the multi-resolution analysis scheme. Thus, the usual way of increasing the dimension of the multi-resolution subspaces is by augmenting the scaling factor. We show here that, when working on a compact interval, the identical effect can be achieved without changing the wavelet scale but reducing the translation parameter. By such a procedure we generate a redundant frame, called a dictionary, spanning the same spaces as a wavelet basis but with wavelets of broader support. We characterize the correlation of the dictionary elements by measuring their 'coherence' and produce examples illustrating the relevance of highly coherent dictionaries to problems of sparse signal representation.

Extended principal component analysis and its applications to image analysis

The objectives of this research are to analyze and develop a modified Principal Component Analysis (PCA) and to develop a two-dimensional PCA with applications in image processing. PCA is a classical multivariate technique where its mathematical treatment is purely based on the eigensystem of positive-definite symmetric matrices. Its main function is to statistically transform a set of correlated variables to a new set of uncorrelated variables over $\IR\sp{n}$ by retaining most of the variations present in the original variables.^ The variances of the Principal Components (PCs) obtained from the modified PCA form a correlation matrix of the original variables. The decomposition of this correlation matrix into a diagonal matrix produces a set of orthonormal basis that can be used to linearly transform the given PCs. It is this linear transformation that reproduces the original variables. The two-dimensional PCA can be devised as a two successive of one-dimensional PCA. It can be shown that, for an $m\times n$ matrix, the PCs obtained from the two-dimensional PCA are the singular values of that matrix.^ In this research, several applications for image analysis based on PCA are developed, i.e., edge detection, feature extraction, and multi-resolution PCA decomposition and reconstruction. ^

3D TerraFly: Quality of service management for online interactive 3D geographic information system

3D geographic information system (GIS) is data and computation intensive in nature. Internet users are usually equipped with low-end personal computers and network connections of limited bandwidth. Data reduction and performance optimization techniques are of critical importance in quality of service (QoS) management for online 3D GIS. In this research, QoS management issues regarding distributed 3D GIS presentation were studied to develop 3D TerraFly, an interactive 3D GIS that supports high quality online terrain visualization and navigation. ^ To tackle the QoS management challenges, multi-resolution rendering model, adaptive level of detail (LOD) control and mesh simplification algorithms were proposed to effectively reduce the terrain model complexity. The rendering model is adaptively decomposed into sub-regions of up-to-three detail levels according to viewing distance and other dynamic quality measurements. The mesh simplification algorithm was designed as a hybrid algorithm that combines edge straightening and quad-tree compression to reduce the mesh complexity by removing geometrically redundant vertices. The main advantage of this mesh simplification algorithm is that grid mesh can be directly processed in parallel without triangulation overhead. Algorithms facilitating remote accessing and distributed processing of volumetric GIS data, such as data replication, directory service, request scheduling, predictive data retrieving and caching were also proposed. ^ A prototype of the proposed 3D TerraFly implemented in this research demonstrates the effectiveness of our proposed QoS management framework in handling interactive online 3D GIS. The system implementation details and future directions of this research are also addressed in this thesis. ^

Rigid and Non-rigid Point-based Medical Image Registration

The primary goal of this dissertation is to develop point-based rigid and non-rigid image registration methods that have better accuracy than existing methods. We first present point-based PoIRe, which provides the framework for point-based global rigid registrations. It allows a choice of different search strategies including (a) branch-and-bound, (b) probabilistic hill-climbing, and (c) a novel hybrid method that takes advantage of the best characteristics of the other two methods. We use a robust similarity measure that is insensitive to noise, which is often introduced during feature extraction. We show the robustness of PoIRe using it to register images obtained with an electronic portal imaging device (EPID), which have large amounts of scatter and low contrast. To evaluate PoIRe we used (a) simulated images and (b) images with fiducial markers; PoIRe was extensively tested with 2D EPID images and images generated by 3D Computer Tomography (CT) and Magnetic Resonance (MR) images. PoIRe was also evaluated using benchmark data sets from the blind retrospective evaluation project (RIRE). We show that PoIRe is better than existing methods such as Iterative Closest Point (ICP) and methods based on mutual information. We also present a novel point-based local non-rigid shape registration algorithm. We extend the robust similarity measure used in PoIRe to non-rigid registrations adapting it to a free form deformation (FFD) model and making it robust to local minima, which is a drawback common to existing non-rigid point-based methods. For non-rigid registrations we show that it performs better than existing methods and that is less sensitive to starting conditions. We test our non-rigid registration method using available benchmark data sets for shape registration. Finally, we also explore the extraction of features invariant to changes in perspective and illumination, and explore how they can help improve the accuracy of multi-modal registration. For multimodal registration of EPID-DRR images we present a method based on a local descriptor defined by a vector of complex responses to a circular Gabor filter.

Multi-scale colorectal tumour segmentation using a novel coarse to fine strategy

This paper addresses the problem of colorectal tumour segmentation in complex real world imagery. For efficient segmentation, a multi-scale strategy is developed for extracting the potentially cancerous region of interest (ROI) based on colour histograms while searching for the best texture resolution. To achieve better segmentation accuracy, we apply a novel bag-of-visual-words method based on rotation invariant raw statistical features and random projection based l2-norm sparse representation to classify tumour areas in histopathology images. Experimental results on 20 real world digital slides demonstrate that the proposed algorithm results in better recognition accuracy than several state of the art segmentation techniques.