Uma Mudenagudi

Space-Time Super-Resolution Using Graph-Cut Optimization

We address the problem of super-resolution-obtaining high-resolution images and videos from multiple low-resolution inputs. The increased resolution can be in spatial or temporal dimensions, or even in both. We present a unified framework which uses a generative model of the imaging process and can address spatial super-resolution, space-time super-resolution, image deconvolution, single-image expansion, removal of noise, and image restoration. We model a high-resolution image or video as a Markov random field and use maximum a posteriori estimate as the final solution using graph-cut optimization technique. We derive insights into what super-resolution magnification factors are possible and the conditions necessary for super-resolution. We demonstrate spatial super-resolution reconstruction results with magnifications higher than predicted limits of magnification. We also formulate a scheme for selective super-resolution reconstruction of videos to obtain simultaneous increase of resolutions in both spatial and temporal directions. We show that it is possible to achieve space-time magnification factors beyond what has been suggested in the literature by selectively applying super-resolution constraints. We present results on both synthetic and real input sequences.

A Study on Keyframe Extraction Methods for Video Summary

In this paper we carry out a survey on key frame extraction methods for Video Summary. We also discuss the summary evaluation criteria and compare the approaches based on the method, data set and the results. Video Summary is a process of presenting an abstract of entire video within a short period of time. It aims to provide a compact video representation, while preserving the essential activities of the original video. It is an essential task in video analysis and indexing applications. Most of the video summaries are based on selection of key frames within the shots of a video. Many of them use motion features and few use visual features for extracting the key frames. The video summary quality assessment methods are based more on subjective and less on objective measures. Tong wei Ren et al has provided a framework to assess the quality of the video against a given reference summary using both subjective and objective measures. Ciocca et al used the objective measures for evaluation of summary and most of them evaluate by taking the subjective opinion of experts. A framework for automatic evalution is needed based on both subjective and objective measures without the reference summary.

Super resolution of images of 3D scenecs

We address the problem of super resolved generation of novel views of a 3D scene with the reference images obtained from cameras in general positions; a problem which has not been tackled before in the context of super resolution and is also of importance to the field of image based rendering. We formulate the problem as one of estimation of the color at each pixel in the high resolution novel view without explicit and accurate depth recovery. We employ a reconstruction based approach using MRF-MAP formalism and solve using graph cut optimization. We also give an effective method to handle occlusion. We present compelling results on real images.

Super resolution using graph-cut

This paper addresses the problem of super resolution – obtaining a single high-resolution image given a set of low resolution images which are related by small displacements. We employ a reconstruction based approach using MRF-MAP formalism, and use approximate optimization using graph cuts to carry out the reconstruction. We also use the same formalism to investigate high resolution expansions from single images by deconvolution assuming that the point spread function is known. We present a method for the estimation of the point spread function for a given camera. Our results demonstrate that it is possible to obtain super-resolution preserving high frequency details well beyond the predicted limits of magnification.

Metric tensor and Christoffel symbols based 3D object categorization

In this paper we propose to address the problem of 3D object categorization. We model the 3D object as a 2D Riemannian manifold and propose metric tensor and Christoffel symbols as a novel set of features. The proposed set of features capture the local and global geometry of 3D objects by exploiting the positional dependence of the features. The categorization of 3D objects is carried out using polynomial kernel SVM classifier. The effectiveness of the proposed framework is demonstrated on 3D objects obtained from different datasets and achieve comparable results.

Detection of doctored images using correlations of PSF

We address the problem of detection of image doctoring using correlations of Point Spread Function (PSF) and iterative blind deconvolution. Doctoring is a process of tampering or hampering or changing the content of an image in order to deceive people or rewrite history or exaggerate the situations or customize ground-breaking advances in research, etc. We propose a method to detect a given image is doctored or original. We present an unified framework which uses a generative model of the imaging process and can address the problem of detection of doctoring. Doctoring process is modeled as the convolution of original image with the nonlinear filter used for generating the doctored image. The characteristics of the authentic image from the given imaging model are used to facilitate the detection of the doctored images. The correlation pattern of the estimated PSF is used to detect the doctoring in an image. We demonstrate the proposed algorithm on different doctored images, which includes doctoring using splicing, cloning and re-touching. On an average, we achieve a detection rate of 74% for doctored images generated with different doctoring methods.

Framework for 3D object hole filling

In this paper we address the problem of hole filling in a point cloud of 3D object. Even with most popular 3D scanning devices like Microsoft Kinect and Time of Flight (ToF) cameras, occlusions during the scanning process result in occurrence of missing regions or holes in 3D data. We propose a framework for hole filling in a point cloud of 3D object using Riemannian metric tensor and Christoffel symbols as a set of geometric features, which capture the inherent geometry of the 3D object. The framework involves detection and extraction of the boundary points surrounding the hole, decomposition of boundary points into basic shapes and selective surface interpolation to fill the hole. We demonstrate the performance of the proposed method on point clouds with different complexities and sizes for both synthetically generated holes and real missing regions during the capturing process on 3D models of heritage sites.

Cross layer routing and rate adaptation for video transmission in multi-radio Wireless Mesh Networks

In this paper, we propose a cross layer optimization technique for video transmission in multi-radio Wireless Mesh Networks (WMNs). WMNs are used as back haul to connect various networks such as Wi-Fi, Wi-MAX etc. to the internet. The presence of multiple radios in this networks increases the capacity but introduces an interference. Thus, designing a better routing metric to find optimal path is an important issue. Further, as the routing metric and rate adaptation decisions are strongly related, the joint approach is needed to improve the performance of the network. In this work, we propose the cross layer optimization technique by designing a routing metric which considers the link quality parameters from various layers and use some of these parameters for rate adaptation to improve the QoS parameters of the network. We implement our technique using AODV protocol in NS2. The results reveal that the joint approach improves the QoS parameters such as throughput, packet delivery fraction (PDF), Peak signal to noise ratio (PSNR) and frame delay compared to existing approaches.

3D Object Super Resolution using Metric Tensor and Christoffel Symbols

In this paper we address the problem of 3D super resolution. 3D super resolution is a process of generating high resolution point cloud, given a low resolution point cloud. We model 3D object as a set of Riemannian manifolds in continuous and discretized space. We propose to use Riemannian metric tensor and Christoffel symbols as a set of features to capture the inherent geometry of the 3D object. We propose a learning framework to decompose 3D object using metric tensor and Christoffel symbols into a set of basis functions to selectively super resolve the 3D object. We demonstrate the proposed algorithm on 3D objects and achieve better results than reported in literature.

Classification of facebook news feeds and sentiment analysis

As recently seen in Googles Gmail, the messages in inbox are classified into primary, social and promotions, which makes it easy for the users to differentiate the messages which they are looking for from the bulk of messages. Similarly, a users wall in facebook is usually flooded with huge amount of data which makes it annoying for the users to view the important news feeds among the rest. Thus we aim to focuses on classification of facebook news feeds. In this paper, we attempt to classify the users news feeds into various categories using classifiers to provide a better representation of data on users wall. News feeds collected from facebook are dynamically classified into various classes such as friends posts and liked pages posts. Friends posts are further categorized into life events posts and entertainment posts. Posts or updates from pages which are liked by the users are grouped as liked pages posts. Posts from friends are tagged as friends posts and those regarding the events occurring in their lives are said to be life event posts and the rest are tagged as entertainment posts. This helps users to find “important news feeds” from “live news feeds”. Sentiments are important as they depict the opinions and expressions of the user. Hence, detecting the sentiments of users from the life event posts also becomes an essential task. We also propose a system for automatic detection of sentiments from the life event posts and categorize based on sentiments into happy, neutral and bad feelings posts. This paper looks towards applying the classification methods from the literature to our dataset with the objective of evaluating methods of automatic news feeds classification and sentiment analysis which in future can provide facebook page a well organized and more appealing look.