Object identification is the task of identifying specific objects belonging to the same class such as cars. We often need to recognize an object that we have only seen a few times. In fact, we often observe only one example of a particular object before we need to recognize it again. Thus we are interested in building a system which can learn to extract distinctive markers from a single example and which can then be used to identify the object in another image as “same ” or “different”. Previous work by Ferencz et al. introduced the notion of hyper-features, which are properties of an image patch that can be used to estimate the utility of the patch in subsequent matching tasks. In this work, we show that hyper-feature based models can be more efficiently estimated using discriminative training techniques. In particular, we describe a new hyper-feature model based upon logistic regression that shows improved performance over previously published techniques. Our approach significantly outperforms Bayesian face recognition that is considered as a standard benchmark for face recognition. 1

We describe a realtime system for finding and tracking unstructured paths in off-road conditions. The system was designed as part of the recent Darpa Grand Challenge and was tested over hundreds of miles of off-road driving. The unique feature of our approach is to combine geometric projection used for recovering Pitch and Yaw with Learning approaches for identifying familiar "drivable" regions in the scene. The region-based component segments the image to "path" and "non-path" regions based on texture analysis borne out of a learning-by-examples principle. The boundary-based component looks for the path bounding lines assuming a geometric model of a planar pathway bounded by parallel edges taken by a perspective camera. The combined effect of both sub-systems forms a robust system capable of finding the path even in situations where the vehicle is positioned out of the path - a situation which is not common for human drivers but is relevant for autonomous driving where the vehicle may find itself occasionally veering out of the path.

Object identification (OID) is specialized recognition where the category is known (e.g. cars) and the algorithm recognizes an object's exact identity (e.g. Bob's BMW). Two special challenges characterize OID. (1) Interclass variation is often small (many cars look alike) and may be dwarfed by illumination or pose changes. (2) There may be many classes but few or just one positive "training" examples per class. Due to (1), a solution must locate possibly subtle object-specific salient features (a door handle) while avoiding distracting ones (a specular highlight). However, (2) rules out direct techniques of feature selection. We describe an online algorithm that takes one model image from a known category and builds an efficient "same" vs. "different" classification cascade by predicting the most discriminative feature set for that object. Our method not only estimates the saliency and scoring function for each candidate feature, but also models the dependency between features, building an ordered feature sequence unique to a specific model image, maximizing cumulative information content. Learned stopping thresholds make the classifier very efficient. To make this possible, category-specific characteristics are learned automatically in an off-line training procedure from labeled image pairs of the category, without prior knowledge about the category. Our method, using the same algorithm for both cars and faces, outperforms a wide variety of other methods.

We address the problem of identifying specific instances of a class (cars) from a set of images all belonging to that class. Although we cannot build a model for any particular instance (as we may be provided with only one "training" example of it), we can use information extracted from observ- ing other members of the class. We pose this task as a learning problem, in which the learner is given image pairs, labeled as matching or not, and must discover which image features are most consistent for matching in- stances and discriminative for mismatches. We explore a patch based representation, where we model the distributions of similarity measure- ments defined on the patches. Finally, we describe an algorithm that selects the most salient patches based on a mutual information criterion. This algorithm performs identification well for our challenging dataset of car images, after matching only a few, well chosen patches.

In this paper, we present a pipeline and several key techniques necessary for editing a real scene captured with both cameras and laser range scanners. We develop automatic algorithms to segment the geometry from range images into distinct surfaces, register texture from radiance images with the geometry, and synthesize compact high-quality texture maps. The result is an object-level representation of the scene which can be rendered with modifications to structure via traditional rendering methods. The segmentation algorithm for geometry operates directly on the point cloud from multiple registered 3D range images instead of a reconstructed mesh. It is a top-down algorithm which recursively partitions a point set into two subsets using a pairwise similarity measure. The result is a binary tree with individual surfaces as leaves. Our image registration technique performs a very efficient search to automatically find the camera poses for arbitrary position and orientation relative to the geometry. Thus, we can take photographs from any location without precalibration between the scanner and the camera. The algorithms have been applied to large-scale real data. We demonstrate our ability to edit a captured scene by moving, inserting, and deleting objects.

We present a new technique for morphing two video sequences.Our approach extends still image metamorphosis techniques to video by performing motion tracking on the objects.Besides reducing the amount of user input required to morph two sequences by an order of magnitude, the additional motion information helps us to segment the image into foreground and background parts.By morphing these parts independently and overlaying the results, output quality is improved.We compare our approach to conventional motion image morphing techniques in terms of the quality of the output image and the human input required.