Abstract — A pan-tilt-zoom robotic camera can provide detailed live video of selected areas of interest within a large potential viewing field. To provide spatial context for human observers, it is desirable to insert the resulting live video into a large spherical panoramic display representing the entire viewing field. Accurate alignment of the video stream within the panoramic display is difficult due to small errors in the robot pan-tilt values and image distortion due to nonlinear projection. Existing image alignment algorithms cannot keep up with rapid changes in camera position. In this paper, we present a constant-time image alignment algorithm based on spherical projection and projection-invariant selective sampling that accurately registers paired images at 25 frames per second on a standard PC. Experiments suggest that the new alignment algorithm is faster than previous algorithms by a factor four or more. In a companion paper [1], we present a new calibration algorithm based on image variance density that optimally estimates camera pan-tilt parameters. I.

Abstract. IntraVascular UltraSound is an imaging technique very helpful for the diagnosis and treatment of cardiac diseases, since it allows the visualization of vessel morphology together with vessel geometry and dynamics induced by heart motion. Non rigid arterial deformation is of clinical interest, since it serves to measure vessel wall stiffness and, through elastographic analysis, to determine vessel plaque nature. However, rigid arterial displacement is a main artifact in any study involving geometric measurements (segmentation, elastography, etc). In this paper, we present a novel method based on spectral analysis which removes rigid cardiac dynamics and preserves the vessel geometry. Results on invivo sequences show that the proposed strategy aligns vessel structures regardless of the acquisition device characteristics. 1

Abstract—In this paper, we present three techniques for 6DOF natural feature tracking in real time on mobile phones. We achieve interactive frame rates of up to 30 Hz for natural feature tracking from textured planar targets on current generation phones. We use an approach based on heavily modified state-of-the-art feature descriptors, namely SIFT and Ferns plus a template-matching-based tracker. While SIFT is known to be a strong, but computationally expensive feature descriptor, Ferns classification is fast, but requires large amounts of memory. This renders both original designs unsuitable for mobile phones. We give detailed descriptions on how we modified both approaches to make them suitable for mobile phones. The template-based tracker further increases the performance and robustness of the SIFT- and Ferns-based approaches. We present evaluations on robustness and performance and discuss their appropriateness for Augmented Reality applications. Index Terms—Information interfaces and presentation, multimedia information systems, artificial, augmented, and virtual realities, image processing and computer vision, scene analysis, tracking. Ç 1

Abstract—This paper investigates the possibility of augmenting an Unmanned Aerial Vehicle (UAV) navigation system with a passive video camera in order to cope with long-term GPS outages. The paper proposes a vision based navigation architecture which combines inertial sensors, visual odometry and registration of the on-board video to a geo-referenced aerial image. The vision-aided navigation system developed is capable of providing high-rate and drift-free state estimation for UAV autonomous navigation without the GPS system. Due to the use of image-to-map registration for absolute position calculation, drift-free position performance depends on the structural characteristics of the terrain. Experimental evaluation of the approach based on off-line flight data is provided. In addition the architecture proposed has been implemented on-board an experimental UAV helicopter platform and tested during vision-based autonomous flights. 1.

In this work, we extend a previously demonstrated entropy based groupwise registration method to include a free-form deformation model based on B-splines. We provide an efficient implementation using stochastic gradient descents in a multi-resolution setting. We demonstrate the method in application to a set of 50 MRI brain scans and compare the results to a pairwise approach using segmentation labels to evaluate the quality of alignment. Our results indicate that increasing the complexity of the deformation model improves registration accuracy significantly, especially at cortical regions.

A new approach to image registration is proposed. The approach enables the proper segregation of the transformation space into a low dimensional so-called coarse space and a remaining non-linear socalled fine part. The segregation concept is combined with a multilevel approach, where the two parts are treated simultaneously. Modeling and computation issues are discussed. Finally, we present a highly non-linear real life example. 1

Abstract. In the last decades there has been tremendous research towards the design of fully automatic non-rigid registration schemes. However, apart from the ITK based implementation of Rueckerts B-spline oriented approach, there is a lack of sound publicly available implementations of the modern schemes. The Flexible Image Registration Toolbox (FLIRT) is an attempt to close this gap. It focuses on non-parametric schemes as popularized in the book by Modersitzki [1]. To be successful, it is crucial for any registration scheme to reflect the special properties of the underlying registration problem. Consequently, FLIRT has an open object-oriented architecture which allows for the incorporation of user prescribed building blocks. In its present form, most of the prominent blocks are already implemented. They may be arranged in a consistent way and cover a wide range of applications. Apart from the flexibility issue, great care has been taken towards fast execution times. The most computationally intensive part, the solution of the underlying linear systems, is implemented by state-of-the-art solution techniques. The FLIRT package is publicly available, it comes with a user guide and a collection of example problems. It is the purpose of this note, to describe some of the features of the toolbox. 1

Medical image registration is a difficult problem. Not only a registration algorithm needs to capture both large and small scale image deformations, it also has to deal with global and local image intensity variations. In this paper we describe a new multiresolution elastic image registration method that challenges these difficulties in image registration. To capture large and small scale image deformations, we use both global and local affine transformation algorithms. To address global and local image intensity variations, we apply an image intensity standardization algorithm to correct image intensity variations. This transforms image intensities into a standard intensity scale, which allows highly accurate registration of medical images. 1

We consider the estimation of affine transformations aligning a known 2D shape and its distorted observation. The classical way to solve this registration problem is to find correspondences between the shapes and then compute the transformation parameters from these landmarks. Here we propose a novel approach where the exact transformation is obtained as the solution of a polynomial system of equations. The method has been tested on synthetic as well as on real images and its robustness in the presence of segmentation errors and additive geometric noise has also been demonstrated. We have successfully applied the method for the registration of hip prosthesis X-ray images. The advantage of the proposed solution is that it is fast, easy to implement, has linear time complexity, works without established correspondences and provides an exact solution regardless of the magnitude of transformation. Key words: Image registration, shape matching, affine transformation 1

Abstract — A new generation of inexpensive robotic pan-tilt cameras can maintain high-resolution panoramic displays of natural environments. However, the pan-tilt mechanisms are imprecise: small errors can produce large errors in the panoramic display. It is thus important to accurately estimate pan-tilt values. We present a new calibration algorithm that does not rely on calibration markers or fixed orthogonal edges which are rarely available in natural scenes. Our calibration algorithm uses image variance density to optimally estimate camera pan and tilt values by incrementally refining image registration using overlapping images from prior frames. Experiments suggest that the new calibration algorithm can reduce calibration error by 81%. In a companion paper [19], we present a new image registration algorithm based on spherical projection that optimally aligns the resulting frames. I.