Tanuja Joshi

Structure and motion estimation from dynamic silhouettes under perspective projection

Addresses the problem of estimating the structure and motion of a smooth curved object from its silhouettes observed over time by a trinocular stereo rig under perspective projection. We first construct a model for the local structure along the silhouette for each frame in the temporal sequence. Successive local models are then integrated into a global surface description by estimating the motion between successive time instants. The algorithm tracks certain surface features (parabolic points) and image features (silhouette inflections and frontier points) which are used to bootstrap the motion estimation process. The entire silhouette along with the reconstructed local structure are then used to refine the initial motion estimate. We have implemented the proposed approach and report results on real images.<<ETX>>

Crosslingual location search

Address geocoding, the process of finding the map location for a structured postal address, is a relatively well-studied problem. In this paper we consider the more general problem of crosslingual location search, where the queries are not limited to postal addresses, and the language and script used in the search query is different from the one in which the underlying data is stored. To the best of our knowledge, our system is the first crosslingual location search system that is able to geocode complex addresses. We use a statistical machine transliteration system to convert location names from the script of the query to that of the stored data. However, we show that it is not sufficient to simply feed the resulting transliterations into a monolingual geocoding system, as the ambiguity inherent in the conversion drastically expands the location search space and significantly lowers the quality of results. The strength of our approach lies in its integrated, end-to-end nature: we use abstraction and fuzzy search (in the text domain) to achieve maximum coverage despite transliteration ambiguities, while applying spatial constraints (in the geographic domain) to focus only on viable interpretations of the query. Our experiments with structured and unstructured queries in a set of diverse languages and scripts (Arabic, English, Hindi and Japanese) searching for locations in different regions of the world, show full crosslingual location search accuracy at levels comparable to that of commercial monolingual systems. We achieve these levels of performance using techniques that may be applied to crosslingual searches in any language/script, and over arbitrary spatial data.

Robust location search from text queries

Robust, global, address geocoding is challenging because there is no single address format that applies to all geographies, and in any case, users may not restrict themselves to well-formed addresses. Particularly in online mapping systems, users frequently enter queries with missing or conflicting information, misspellings, address transpositions, and other such variations. We present a novel system which handles these difficulties by using a combination of textual similarity and spatial coherence to guide a depth-first search over the large space of possible interpretations of a text query. The system robustly matches text subsequences of a query with text attributes (i.e., any text labels associated with the entity) in a spatial-entity database. Each matched attribute is associated with the pre-computed spatial union of all entities that have that attribute. Candidate results are formed by incremental spatial intersections of these unions. Experimental results demonstrate that our system is capable of supporting regions with widely differing address formats, without region-specific customization or training. Furthermore, we show that our system significantly outperforms commercial systems for unstructured location queries and queries containing errors.

Hot curves for modelling and recognition of smooth curved 3D objects

Major advances in object representation, modelling and matching are required to develop vision systems capable of recognizing complex curved 3D objects observed in monocular images from a large database of models. In this paper, we propose to represent smooth curved 3D shapes by a set of curves where the surface admits high-order tangents. These HOT curves have two remarkable properties: they determine the structure of the image contours and its catastrophic changes, and there is a natural correspondence between two of them (parabolic and limiting bitangent curves) and monocular image features (contour inflections and bitangents). We present a method for automatically constructing these two curves from continuous sequences of video images and describe an approach to object recognition using viewpoint-dependent monocular image features as indexes into a database of models and as a basis for pose estimation. We have implemented both algorithms and present results obtained from real images. We briefly discuss the construction of the whole set of HOT curves and its application to aspect graph construction from image data.

Structure and Motion Estimation from Dynamic Silhouettes under Perspective Projection

We address the problem of estimating the structure and motion of a smooth curved object from its silhouettes observed over time by a trinocular stereo rig under perspective projection. We first construct a model for the local structure along the silhouette for each frame in the temporal sequence. The local models are then integrated into a global surface description by estimating the motion between successive time instants. The algorithm tracks certain surface features (parabolic points) and image features (silhouette inflections and frontier points) which are used to bootstrap the motion estimation process. The entire silhouettes along with the reconstructed local structure are then used to refine the initial motion estimate. We have implemented the proposed approach and report results on real images.

Towards structure and motion estimation from dynamic silhouettes

Addresses the problem of estimating the structure and motion of a smooth curved object from its silhouettes observed over time by a trinocular imagery. We first construct a model for the local structure along the silhouette for each frame in the temporal sequence. The local models are then integrated into a global surface description by estimating the motion between successive frames. The algorithm tracks certain surface and image features (parabolic points and silhouette inflections, frontier points) which are used to bootstrap the motion estimation process. The whole silhouette is then used to refine the initial motion estimate. We have implemented the proposed approach and report preliminary results.<<ETX>>