CVIT Home CVIT Home
  • Home
  • People
    • Faculty
    • Staff
    • PhD Students
    • MS Students
    • Alumni
    • Post-doctoral
    • Honours Student
  • Research
    • Publications
    • Thesis
    • Projects
    • Resources
  • Events
    • Talks and Visits
    • Major Events
    • Visitors
    • Summer Schools
  • Gallery
  • News & Updates
    • News
    • Blog
    • Newsletter
    • Banners
  • Contact Us
  • Login

GSWall: A Scalable Tiled-Display Wall


Nirnimesh (homepage)

Tiled displays can provide high resolution and large display area. Cluster-based tiled displays are cost-effective and scalable. Chromium is a popular software API used to build such displays; Chromium based tiled displays tend to be network-limited affecting the scalability in the number of nodes and the ability to handle large environment models. This thesis presents a tiled Display Wall setup based on a client-server architecture, with the server managing all the aspects leaving the clients with rendering as their sole responsibility. Our system uses off-the-shelf graphics hardware and standard ethernet net- work. High-level scene structure and hierarchy of a scene graph (OpenSceneGraph) is used by a central server to minimize network load. The view-frustums of the rendering nodes are treated hierarchically as well. A novel algorithm combines the object hierarchy of the scene graph with the hierarchy of frustums to determine the optimal process of unfolding the hierarchies so as to minimize the number of computations involved. Visible parts of the scene graph are transmitted and cached by the clients to take advantage of temporal coherence. The server, following a push-philosophy, is able to exploit the high degree of overlap in the computation space for each rendering node to avoid concurrent redundant com- putations. We use a multicast oriented protocol for data-transmission to the clients, making the system scalable. Geometry push philosophy from the server helps keep the clients in sync with one another and facilitates the pipelining of the constituent stages. Distributed rendering allows the display wall to be able to render scenes which are otherwise too bulky for any of the individual rendering nodes. No node, including the server, needs to render the entire environment, making our system suitable for interactive rendering of massive models. We show performance measures for the different underlying aspects of our display wall. The display wall application is implemented as a library-intercept mechanism to seam- lessly render any OpenSceneGraph-based graphics application to a tiled-display wall without the need of modification, recompilation or even relinking. This makes our display wall easy to use for several already existing applications. Our studies show that the server and network loads grow sub-linearly with the number of tiles. This makes our scheme suitable for the construction of very large-resolution displays.

 

Year of completion:  2006
 Advisor :

P. J. Narayanan


Related Publications


    Downloads

    thesis

     ppt

     

    Document Annotation and Retrieval Systems


    A. Balasubramanian

    Digital documents are now omnipresent. Techniques and algorithms to process and understand these documents are still evolving. This thesis focuses on the non-textual documents of textual content. Example of this category are online handwritten documents and scanned printed books. Algorithms for accessing such documents at the content-level are still missing, specially for Indian Languages. This thesis addresses two fundamental problems in this area: Annotation and Retrieval. Annotated datasets of handwriting are a prerequisite for the design and training of hand- writing recognition algorithms. Retrieval from annotated data sets is relatively straightforward. However retrieval from unannotated datasets is still an open problem. We explore algorithms which make these two tasks possible. Annotation of large datasets is a tedious and expensive process. The problem becomes compounded for handwritten documents, where the characters correspond to one or more strokes. We have developed a versatile, robust annotation tool for online handwriting data. This tool is aimed at supporting the emerging UPX/hwDataset schema, a promising successor of the UNIPEN. We provide easy-to-use interface for the annotation tool. However, still the annotation is highly manual. We then propose a novel, automated method for annotation of online handwriting data at the character level, given a parallel corpus of online handwritten data and typed text. The method employs a model-based handwriting synthesis unit to map the two corpora to the same space. Annotation is then propagated to the word level and finally to the individual characters using elastic matching. The initial results of annotation are used to improve the handwriting synthesis model for the user under consideration, which in turn refine the annotation. The method takes care of errors in the handwriting such as spurious and missing strokes and characters. The output is stored in the UPX format. (more...)

     

    Year of completion:  2006
     Advisor :

    C. V. Jawahar


    Related Publications

    • Anand Kumar, A. Balasubramanian, Anoop M. Namboodiri and C.V. Jawahar - Model-Based Annotation of Online Handwritten Datasets, International Workshop on Frontiers in Handwriting Recognition(IWFHR'06), October 23-26, 2006, La Baule, Centre de Congreee Atlantia, France. [PDF]

    • C. V. Jawahar and A. Balasubramanian - Synthesis of Online Handwriting in Indian Languages, International Workshop on Frontiers in Handwriting Recognition(IWFHR'06), October 23-26, 2006, La Baule, Centre de Congree Atlantia, France. [PDF]

    • A. Balasubramanian, Million Meshesha and C. V. Jawahar - Retrieval from Document Image Collections, Proceedings of Seventh IAPR Workshop on Document Analysis Systems, 2006 (LNCS 3872), pp 1-12. [PDF]

    • Sachin Rawat, K. S. Sesh Kumar, Million Meshesha, Indineel Deb Sikdar, A. Balasubramanian and C. V. Jawahar - A Semi-Automatic Adaptive OCR for Digital Libraries, Proceedings of Seventh IAPR Workshop on Document Analysis Systems, 2006 (LNCS 3872), pp 13-24. [PDF]

    • C. V. Jawahar, Million Meshesha and A. Balasubramanian, Searching in Document Images, Proceedings of the Indian Conference on Vision, Graphics and Image Processing(ICVGIP), Dec. 2004, Calcutta, India, pp. 622--627. [PDF]

    • A. Bhaskarbhatla, S. Madhavanath, M. Pavan Kumar, A. Balasubramanian, and C. V. Jawahar - Representation and Annotation of Online Handwritten Data, Proceedings of the International Workshop on Frontiers in Handwriting Recognition(IWFHR), Oct. 2004, Tokyo, Japan, pp. 136--141. [PDF]

    • C. V. Jawahar, A. Balasubramanian and Million Meshesha, Word-Level Access to Document Image Datasets, Proceedings of the Workshop on Computer Vision, Graphics and Image Processing(WCVGIP), Feb. 2004, Gwalior, India, pp. 73--76. [PDF]


    Downloads

    thesis

     ppt

    Towards Understanding Texture Processing


    Gopal Datt Joshi (homepage)

    A fundamental goal of texture research is to develop automated computational methods for retrieving visual information and understanding image content based on textural properties in images. A synergy between biological and computer vision research in low-level vision can give substantial insights about the processes for extracting color, edge, motion, and spatial frequency information from images. In this thesis, we seek to understand the texture processing that takes place in low level human vision in order to develop new and effective methods for texture analysis in computer vision. The different representations formed by the early stages of HVS and visual computations carried out by them to handle various texture patterns is of interest. Such information is needed to identify the mechanisms that can be use in texture analysis tasks. We examine two types of cells, namely the bar and grating cells, which have been identified in literature to play an important role in texture processing, and develop functional models for the same. The model for the bar cell is based on the notion of surround inhibition and excitation. Whereas, the model for the grating cell is based on the fact that a grating cell receives direct inputs from the M-type ganglion cells. The representations derived by these cells are used to design solutions to two important problems of texture: texture based segmentation and classification. The former is addressed in the domain of natural image understanding and the latter is addressed in the domain of document image understanding. Based on our work, we conclude that the early stages of HVS effectively represent various texture patterns and also provide ample information to solve the higher level texture analysis tasks. The richness of information emerges from the capability of the HVS to extract global visual primitives from local features. The presented work is an initial attempt to integrate the current knowledge of HVS mechanisms and computational theories developed for texture analysis. (more...) 

     

    Year of completion:
    December 2006
     Advisor :

    Jayanthi Sivaswamy


    Related Publications

    • Joshi Datt Joshi, Saurabh Garg and Jayanthi Sivaswamy - Script Identification from Indian Documents, Proceedings of IAPR Workshop on Document Analysis Systems (DAS 2006), Nelson, pp.255-267. [PDF]

    • Gopal Datt Joshi, Saurabh Garg and Jayanthi Sivaswamy - A Generalised Framework for Script Identification Proc. of International Journal for Document Analysis and Recognition(IJDAR), 10(2), pp.55-68, 2007. [PDF]

    • Gopal Datt Joshi and Jayanthi Sivaswamy - A Computational Model for Boundary Detection, 5th Indian Conference on Computer Vision, Graphics and Image Processing, Madurai, India, LNCS 4338 pp.172-183, 2006. [PDF]

    • Gopal Datt Joshi, and Jayanthi Sivaswamy - A Simple Scheme for Contour Detection, Proceedings of International Conference on Computer Vision and Applications (VISAP 2006), Setubal. [PDF]

    • Gopal Datt Joshi , and Jayanthi Sivaswamy - A Multiscale Approach to Contour Detection, Proceedings of International Conference on Cognition and Recognition ,pp. 183-193, Mysore, 2005. [PDF]


    Downloads

    thesis

     ppt

    Layer Extraction, Removal and Completion of Indoor Videos: A Tracking Based Approach


    Vardhman Jain (homepage)

    Image segmentation and layer extraction in video refer to the process of segmenting the image or video frames into various constituent objects. Automatic techniques for these are not always suitable, as the objective is often difficult to describe. With the advent of interactive techniques in the field, these algorithms are now usable for selecting an object of interest in an image or video precisely with less efforts. Object segmentation brings up various other possibilities like cut and paste of objects from one image or video to another. Object removal in image and videos is another application of interest. As the name suggest the task is to eliminate an object from the image or video. This involves recovering the information of the background previously occluded by the object. Object removal in both image and videos have found interesting applications especially in the entertainment industry. The concept of filling-in of information from the surrounding region for images and surrounding frames for videos has been applied for recovering damaged images or clips. This thesis presents two new approaches. The first is for object segmentation or layer extraction from a video. This method allows segmenting complex objects in videos, which can have difficult motion model. The algorithm integrates a robust points tracking algorithm to a 3D graph cuts formulation. Tracking is used for propagating the user given seeds in key frames to the intermediate frames which helps to provide better initialization to the graph cuts optimization. The second is an approach for video completion in indoor scenes. We propose a novel method for video completion using multiview information without applying a full frame or complete motion segmentation. The heart of the algorithm is a method to partition the scenes into regions supporting multiple homographies based on a geometric formulation and thereby providing precise segmentation even at the points where the actual scene information is missing due to the removal of the object. We demonstrate our algorithms on a number of representative videos. We also present a few directions for future work that extends the work presented here.

     

    Year of completion:  2006
     Advisor :

    P. J. Narayanan


    Related Publications

    • Vardhman Jain and P.J. Narayanan - Layer Extraction Using Graph Cuts and Feature Tracking, The 3rd International Conference on Visual Information Engineering 26-28 September 2006 in Bangalore, India. [PDF]

    • Vardhman Jain and P. J. Narayanan - Video Completion for Indoor Scenes, 5th Indian Conference on Computer Vision, Graphics and Image Processing, Madurai, India, LNCS 4338 pp.409-420, 2006. [PDF]


    Downloads

    thesis

     ppt

    DGTk: A Data Generation Tool for CV and IBR


    V. Vamsi Krishna

    Computer Vision (CV) and Image Based Rendering (IBR) are the fields which have emerged in search of a means to make the computers understand the images like humans and the never ending pursuit of the Computer Graphics community to achieve photo realistic rendering. Though each of these fields deal with a completely different problems, both CV and IBR algorithms require high quality ground-truth information about the scenes they are applied on. Traditionally research groups have spent large amounts of resources on creating data using high-resolution equipment for qualitative analysis of CV and IBR algorithms. Such high quality data provided a platform for comparison of CV and IBR algorithms. Though these datasets have enabled comparison of algorithms, during the past decade, the development in the fields of CV and IBR have outpaced the ability of such standard datasets to differentiate among the best performing algorithms. All the resources invested for generating these datasets become wasted. To overcome this problem, researchers have resorted to creating synthetic datasets by extending existing 3D authoring tools, developing stand alone tools for generating synthetic data and developing novel methods of data acquisition for acquiring high quality real world data. The disadvantage of acquiring data using high resolution equipment include (1) Time required for setting up the configuration of equipment, (2) Errors in measuring devices due to physical limitations, (3) Repeatability of experiments due to un-controllable parameters like wind, fog, rain etc. Synthetic data is preferred for the early testing of algorithms, since they make qualitative and quantitative analysis possible. The performance of an algorithm on synthetic data generally provides a good indication of it's performance on the real world data.. (more...)

     

    Year of completion:  2006
     Advisor : P. J. Narayanan

    Related Publications

    • Vamsikrishna and P.J. Narayanan - Data Generation Toolkit for Image Based Rendering Algorithms , The 3rd International Conference on Visual Information Engineering 26-28 September 2006 in Bangalore, India. [PDF]


    Downloads

    thesis

     ppt

    More Articles …

    1. Robust Registration For Video Mosaicing Using Camera Motion Properties
    2. Enhancing Weak Biometric Authentication by Adaptation and Improved User-Discrimination
    3. Vision based Robot Navigation using an On-line Visual Experience
    4. Kernel Methods and Factorization for Image and Video Analysis
    • Start
    • Prev
    • 30
    • 31
    • 32
    • 33
    • 34
    • 35
    • 36
    • 37
    • 38
    • 39
    • Next
    • End
    1. You are here:  
    2. Home
    3. Research
    4. Thesis
    5. Thesis Students
    Bootstrap is a front-end framework of Twitter, Inc. Code licensed under MIT License. Font Awesome font licensed under SIL OFL 1.1.