This paper presents a method for extracting distinctive invariant features from images, which can be used to perform reliable matching between different images of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a a substantial range of affine distortion, addition of noise, change in 3D viewpoint, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through leastsquares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.

Registration is a fundamental task in image processing used to match two or more pictures taken, for example, at different times, from different sensors or from different viewpoints. Over the years, a broad range of techniques have been developed for the various types of data and problems. These techniques have been independently studied for several different applications resulting in a large body of research. This paper organizes this material by establishing the relationship between the distortions in the image and the type of registration techniques which are most suitable. Two major types of distortions are distinguished. The first type are those which are the source of misregistration, i.e., they are the cause of the misalignment between the two images. Distortions which are the source of misregistration determine the transformation class which will optimally align the two images. The transformation class in turn influences the general technique that should be taken....

INTRODUCTION Classical symbolic systems in psychology have proven to be powerful in explaining human cognition and behavior, especially in contrast to the preceding behaviorist approach. The engineering aspect of this approach, symbolic artificial intelligence, has similarly has shown itself to be capable of mimicking and often exceeding average human cognitive abilities. However, both the cognitive science and AI communities have experienced an increasing dissatisfaction with these approaches within the last decade or so. The problems manifest in both fields are similar. The things humans do with the most ease (e.g., recognizing patterns, moving around in the world, learning to speak) are the most difficult to explain and mimic with a symbolic approach. In both domains, this dissatisfaction has led to the acceptance of different viewpoints. In cognitive science, connectionism and ecological psychology are having major influences, and in AI, specifically the fields of robotics and comp

This paper has not already been accepted by and is not currently under review for a journal or another conference. Nor will it be submitted for such during the IJCAI's review period

The paper tackles the problem of feature points matching between pair of images of the same scene. This is a key problem in computer vision. The method we discuss here is a version of the SVD-matching proposed by Scott and Longuet-Higgins and later modified by Pilu, that we elaborate in order to cope with large scale variations. To this end we add to the feature detection phase a keypoint descriptor that is robust to large scale and view-point changes. Furthermore, we include this descriptor in the equations of the proximity matrix that is central to the SVD-matching. At the same time we remove from the proximity matrix all the information about the point locations in the image, that is the source of mismatches when the amount of scene variation increases. The main contribution of this work is in showing that this compact and easy algorithm can be used for severe scene variations. We present experimental evidence of the improved performance with respect to the previous versions of the algorithm.

There are striking parallels between ecological psychology and the new trends in robotics and computer vision, particularly regarding how agents interact with the environment. We present some ideas from ecological psychology, including control laws using optic flow, affordances and action modes, and describe our implementation of these concepts in a small mobile robot which can avoid obstacles and chase or flee moving targets solely using optic flow. The properties of these methods were further explored in simulation. This work ties in with that of others arguing for a methodological approach in robotics which foregoes a central model/planner. Ecological psychology may not only contribute to robotics, but robotic implementations may in turn provide a test bed for ecological principles and a source of ideas which could be tested in animals and humans. Keywords: ecological psychology, behavior-based robotics, optic flow, obstacle avoidance, tag. ECOLOGICAL ROBOTICS 2 Introduction Over...

We present a complete architecture for behavioral control of locomotion for both real and simulated agents and provide a design methodology for building the locomotion control systems that embody the architecture. A low-level locomotion engine controls an agent's actions directly based on intermediate-level reactive behaviors such as attraction and avoidance. High-level state machines schedule and control the reactive behaviors allowing for more "intelligent" decision processes, and an agent model provides a mechanism for varying locomotion according to agent state and personality attributes. In addition to providing specifications for a locomotion engine, we address the problem of selecting and organizing an appropriate set of behaviors. We present selection criteria and a method for partitioning the behaviors to aid in implementation. We discuss the challenges specific to human locomotion and explain how to...

In this paper we present a robust feature matching scheme in which features can be matched in 2.3µs. For a typical task involving 150 features per image, this results in a processing time of 500µs for feature extraction and matching. In order to achieve very fast matching we use simple features based on histograms of pixel intensities and an indexing scheme based on their joint distribution. The features are stored with a novel bit mask representation which requires only 44 bytes of memory per feature and allows computation of a dissimilarity score in 20ns. A training phase gives the patch-based features invariance to small viewpoint variations. Larger viewpoint variations are handled by training entirely independent sets of features from different viewpoints. A complete system is presented where a database of around 13,000 features is used to robustly localise a single planar target in just over a millisecond, including all steps from feature detection to model fitting. The resulting system shows comparable robustness to SIFT [8] and Ferns [14] while using a tiny fraction of the processing time, and in the latter case a fraction of the memory as well. 1.

The main problems of Optical Character Recognition (OCR) systems are solved if printed latin text is considered. Since OCR systems are based upon binary images, their results are poor if the text is degraded. In this paper a codex consisting of ancient manuscripts is investigated. Due to environmental effects the characters of the analyzed codex are washed out which leads to poor results gained by state of the art binarization methods. Hence, a segmentation free approach based on local descriptors is being developed. Regarding local information allows for recognizing characters that are only partially visible. In order to recognize a character the local descriptors are initially classified with a Support Vector Machine (SVM) and then identified by a voting scheme of neighboring local descriptors. State of the art local descriptor systems are evaluated in this paper in order to compare their performance for the recognition of degraded characters.

We present a novel matchpoint acquisition method capable of producing accurate correspondences at subpixel precision. Given the known representation of the point to be matched, such as a projected fiducial in a structured light system, the method estimates the fiducial location and its expected uncertainty. Improved matchpoint precision has application in a number of calibration tasks, and uncertainty estimates can be used to significantly improve overall calibration results.