Krishnan Ramnath

Learn More
In this paper, we describe an interest point detector using edge foci. Unlike traditional detectors that compute interest points directly from image intensities, we use normalized intensity edges and their orientations. We hypothesize that detectors based on the presence of oriented edges are more robust to non-linear lighting variations and background(More)
We present a system that detects 3D mirror-symmetric objects in images and then reconstructs their visible symmetric parts. Our detection stage is based on matching mirror symmetric feature points and descriptors and then estimating the symmetry direction using RANSAC. We enhance this step by augmenting feature descriptors with their affinedeformed versions(More)
Active appearance models (AAMs) typically only use 50-100 mesh vertices because they are usually constructed from a set of training images with the vertices hand-labeled on them. In this paper, we propose an algorithm to increase the density of an AAM. Our algorithm operates by iteratively building the AAM, refitting the AAM to the training data, and(More)
Active Appearance Models (AAMs) are generative, parametric models that have been successfully used in the past to model deformable objects such as human faces. The original AAMs formulation was 2D, but they have recently been extended to include a 3D shape model. A variety of single-view algorithms exist for fitting and constructing 3D AAMs but one area(More)
We present a new approach for recognizing the make and model of a car from a single image. While most previous methods are restricted to fixed or limited viewpoints, our system is able to verify a car's make and model from an arbitrary view. Our model consists of 3D space curves obtained by backprojecting image curves onto silhouette-based visual hulls and(More)
We propose a new method for warping highresolution images to efficiently track objects on the ground plane in real time. Recently, the emergence of high resolution video cameras (>5 megapixels) has enabled surveillance over a much larger area using only a single camera. However, real-time processing of high resolution video for automatic detection and(More)
Modern automated video analysis systems consist of large networks of heterogeneous sensors. These systems must extract, integrate and present relevant information from the sensors in real-time. This paper addresses some of the major challenges such systems face: efficient video processing for high-resolution sensors; data fusion across multiple modalities;(More)
AutoCaption is a system that helps a smartphone user generate a caption for their photos. It operates by uploading the photo to a cloud service where a number of parallel modules are applied to recognize a variety of entities and relations. The outputs of the modules are combined to generate a large set of candidate captions, which are returned to the(More)
This paper presents an overview of self-contained automated video analytics units that are man-portable and constitute nodes of a large-scale distributed sensor network. The paper highlights issues with traditional video surveillance systems in volatile environments such as a battle field and provides solutions to them in the form of Rapidly Deployable(More)
Images are often used to convey many different concepts or illustrate many different stories. We propose an algorithm to mine <i>multiple</i> diverse, relevant, and interesting text snippets for images on the web. Our algorithm scales to <i>all</i> images on the web. For each image, <i>all</i> webpages that contain it are considered. The top-K text snippet(More)