The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the U.S. government. Recognizing landmarks in sequences of images is a challenging problem for a number of reasons. First of all, the appearance of any given landmark varies substantially from one observation to the next. In addition to variations due to different aspects, an illumination change, external clutter, and changing geometry of the imaging devices are other factors affecting the variability of the observed landmarks. Finally, it is typically difficult to make use of accurate 3D information in landmark recognition applications. For those reasons, it is not possible to use many of the object recognition techniques based on strong geometric models. The alternative is to use image-based techniques in which landmarks are represented by collections of images which capture the “typical ” appearance of the object. The information most relevant to recognition is extracted from the collection of raw images and used as the model for recognition. This process is often referred to as “visual learning.” Models of landmarks are acquired from image sequences and later recognized for vehicle localization

Abstract- A new general registration method for images of different nature is presented in this paper. As grey-levels or textures cannot be used for the registration of images from separate spectral bands, an edge-based method has been developed. Edge images are processed to extract straight linear segments, which are then grouped to form triangles. A set of candidate transformations is determined by matching triangles from the source and destination images. The transformations are then evaluated by matching the transformed set of source segments to the set of destination segments. As the coincidence of vertices or edge overlapping cannot be assumed in the registration of images of different nature, a new function for evaluating the matching quality between source and destination segments which does not rely on overlapping measures is proposed. Results and subjective evaluation of the registration of visual and thermal infrared images are presented.

In this paper, a new method for reconstruction of 3D segments from multiple images in urban areas environment is presented. Compared to previous algorithms, this one performs the matching of 2D segments in the Object Space through a sweep plane technique, thus avoiding the combinatorial exploration of all possible correspondences and handling images in a symmetric way. Furthermore, a method for reconstruction of 3D line from 2D lines, which takes into account the uncertainty on the parameters that define the 2D lines is also presented. It enables to get normalized residuals, which is used as a geometric criterion usable whatever the number of images is, to assess or reject potential correspondences. This criterion along with an unicity criterion is at the heart of the algorithm to prune the set of possible correspondences and to keep only reliable matches. Promising results are presented on simulated and real data. They show the ability of the algorithm to overcome detection errors in images and its robustness to occlusions in some images. 1.1 Context 1

Polyhedral descriptions of objects are needed in applications like vision-based robotics, e.g. to carry out grasping and assembling tasks. This work presents a novel methodology for the subtask of localizing a three-dimensional target object in the image and extracting the two-dimensional depiction of the boundary. By eliciting the general principles underlying the process of image formation we exhaustively make use of general, qualitative assumptions, and thus reduce the role of object-specific knowledge for boundary extraction. Geometric/photometric consensus principles are involved in a Hough transformation based approach for extracting line segments. The perceptual organization of line segments into polygons or arrangements of polygons, which originate from the silhouette or the shape of approximate polyhedral objects, is based on shape regularities and quasi-invariants of projective transformation. An affiliated saliency measure combines evaluations of geometric/photometric consen...

Computational models for computer vision

In this paper we propose a comprehensive framework that allows existing local appearance methods to collaborate in order to overcome their mutual drawbacks. Our approach tends to use the best suited local descriptors for a recognition task, and is capable of combining evidence of different methods in the case where no clearly superior type of descriptor exists. We achieve this collaboration by locally matching geometric configurations and permit each match contribute to the computation of the apparent motion between a model image and the unknown query image. We show in this paper that, if we have a set of local methods conforming to a small set of conditions, they can share information about evidence of objects in a scene. This shared evidence results in recognition performances that lie beyond the capacities of any of the currently used individual methods. Keywords:

Abstract 1 Recognizing landmark is a critical task for mobile robots. Landmarks are used for robot positioning, and for building maps of unknown environments. In this context, the traditional recognition techniques based on strong geometric models cannot be used. Rather, models of landmarks must be built from observations using image-based visual learning techniques. Beyond its application to mobile robot navigation, this approach addresses the more general problem of identifying groups of images with common attributes in sequences of images. We show that, with the appropriate domain constraints and image descriptions, this can be done using efficient algorithms as follows: Starting with a “training ” sequence of images, we identify groups of images corresponding to distinctive landmarks. Each group is described by a set of feature distributions. At run-time, the observed images are compared with the sets of models in order to recognize the landmarks in the input stream. 1.

In this paper we address both automatic recognition of sketched symbols and the construction of the corresponding models from user drawn examples. Our approach is based on a two stage process. In a rst phase we use an Adjacency Grammar to express topological properties of the symbol. In order to be able to further disambiguate topologically similar con gurations on the rules of the grammar that are triggered by the recognition process produce a set of local geometric invariants is de ned. The combination of both steps results in an e cient recognition method for user drawn sketches. Furthermore, we show that the same approach can easily be adapted for the generation of Adjacency Grammars from user provided and hand drawn examples. 1