In this paper we start from a set of images obtained by the robot that is moving around in an environment. We present a method to automatically group the images into groups that correspond to convex subspaces in the environment which are related to the human concept of rooms. Pairwise similarities between the images are computed using local features extracted from the images and geometric constraints. The images with the proposed similarity measure can be seen as a graph or in a way a base level dense topological map. From this low level representation the images are grouped using a graph-clustering technique which effectively finds convex spaces in the environment. The method is tested and evaluated on challenging data sets acquired in real home environments. The resulting higher level maps are compared with the maps humans made based on the same data.

Abstract. We present a fast, simple location recognition and image localization method that leverages feature correspondence and geometry estimated from large Internet photo collections. Such recovered structure contains a significant amount of useful information about images and image features that is not available when considering images in isolation. For instance, we can predict which views will be the most common, which feature points in a scene are most reliable, and which features in the scene tend to co-occur in the same image. Based on this information, we devise an adaptive, prioritized algorithm for matching a representative set of SIFT features covering a large scene to a query image for efficient localization. Our approach is based on considering features in the scene database, and matching them to query image features, as opposed to more conventional methods that match image features to visual words or database features. We find this approach results in improved performance, due to the richer knowledge of characteristics of the database features compared to query image features. We present experiments on two large city-scale photo collections, showing that our algorithm compares favorably to image retrieval-style approaches to location recognition.

In this paper we propose an image indexing and matching algorithm that relies on selecting distinctive high dimensional features. In contrast with conventional techniques that treated all features equally, we claim that one can benefit significantly from focusing on distinctive features. We propose a bag-of-words algorithm that combines the feature distinctiveness in visual vocabulary generation. Our approach compares favorably with the state of the art in image matching tasks on the University of Kentucky Recognition Benchmark dataset and on an indoor localization dataset. We also show that our approach scales up more gracefully on a large scale Flickr dataset. 1.

Abstract—Loop closing in vision based SLAM applications isadifficulttask.Comparingnewimagedatawithallprevious imagedataacquiredforthemapispracticallyimpossiblebecause of the high computational costs. This problem is part of the bigger problem to acquire local geometric constraints from sensordataforgeometricmapbuildingtermeddataassociation. Commonlythecomputationalcostsarekeptsmallbysampling theimagedatauniformlyovertimeorusingapositionestimate fromamappingandlocalizationalgorithm.Inthispaperwe proposeamorenaturalsamplingapproach,bydetermininga subsetthatbestdescribesthecompleteimagedatainthespace of all previously seen images. The actual problem of finding suchasubsetiscalledtheConnectedDominatingSetproblem which is well studied in field of graph theory. The proposed methodisparticularlybeneficialforrealisticmappingscenarios includingmovingobjectsandpersons,motionblurandchanging light conditions. Evaluation on multiple large indoor datasets show that the method performance is very close to that of an exhaustive data association scheme and outperforms other samplingapproaches. I.

Abstract — We present a new strategy for active vision-based localization and navigation of a mobile robot in a visual memory, i.e., within a previously-visited area represented as a large collection of images. Vision-based localization in such a large and dynamic visual map is intrinsically ambiguous, since more than one map-locations can exhibit the same visual appearance as the current image observed by the robot. Most existing approaches are passive, i.e., they do not devise any strategy to resolve this ambiguity. In this work, we present an active vision-based localization and navigation strategy that can disambiguate the true initial location among possible hypotheses by controlling the mobile observer across a sequence of highly distinctive images, while concurrently navigating towards the target image. The performance of our active localization and navigation algorithm is demonstrated experimentally on a robot moving within a large outdoor environment. I.