Center for Visual Information Technology

Center for Visual Information Technology (CVIT) focuses on basic and advanced research in image processing, computer vision, computer graphics and machine learning. This center deals with the generation, processing, and understanding of primarily visual data as well as with the techniques and tools required doing so efficiently. The activity of this center overlaps the traditional areas of Computer Vision, Image Processing, Computer Graphics, Pattern Recognition and Machine Learning. CVIT works on both theoretical as well as practical aspects of visual information processing. Center aims to keep the right balance between the cutting edge academic research and impactful applied research.

360 Degree Stereo Video Camera

Research Area
Computer Vision
Panaromic View, Single Camera, Virtual and augmented Reality
Technology Description
This unique technology can use a Single camera to capture panoramic videos, presents a practical solution for generating 360 degree stereo panoramic videos using a single camera. Current approaches either use a moving camera that captures multiple images of a scene, which are then stitched together to form the final panorama, or use multiple cameras that are synchronized. A moving camera limits the solution to static scenes, while multi-camera solutions require dedicated calibrated setups. This technology enhances the existing solutions significantly: It solves the problem using a single camera, thus minimizing the calibration problem and providing us the ability to convert any digital camera into a panoramic stereo capture device. It captures all the light rays required for stereo panoramas in a single frame using a compact custom designed mirror, thus making the design practical to manufacture and easier to use.
Type of Work
System design, though NOT a software
Current State of work
Technology designed and implemented, Technology thoroughly tested Startup (DreamVu) is currently working on taking this technology to the market
Potential Applications
1. Low cost panoramic images 2. Virtual Telepresence 3. Robot / Drone Navigation 4. Event Telecast
Related Publications
1. Panoramic Stereo Videos With a Single Camera, IEEE Conference on Computer Vision and Pattern Recognition, 2016
360 Degree Stereo Video Camera

Person Detection and Recognition in the Wild

Automatic Image Annotation

Mobile Cameras for 3D Structure Estimation

SynCam: Multi-Mobile Synchronized Media Capture

Analytics and understanding broadcast sports videos

OCR for Indian Languages

Scene Text Understanding

Context Aware Human Assistance with Vision and Language

Mobile and Wearable Computer Vision

Understanding Handwriting

Detecting Duplicates and Plagiarisms

A Support Vector Approach for Cross-Modal Search of Images and Texts

Image Annotation by Propagating Labels from Semantic Neighbourhoods

Cross-specificity: Modelling data semantics for cross-modal matching and retrieval

Optical Fingerprint Acquisition using Mobile Devices

Effcient and Accurate Binary Deep Networks

Iterative Shadow Removal in Document Images

Head pose estimation by locating facial keypoints

Unsupervised visual grounding through self supervision

Long-Term Visual Object Tracking

Automatic Document Quality Analysis

Zooming On All Actors: Automatic Focus and Context Split Screen Video Generation

Automated Top View Registration of Broadcast Football Videos

3D Shape Analysis

Automatic Image Annotation and Visual Question Answering

Anatomical landmark detection from retinal images

Glaucoma detection from fundus images

Anatomical structure identification from OCT volumes

Detection of abnormalities from OCT images

Assistive lesion detection and enhancement for diabetic retinopathy

Style transfer solution for low cost fundus imaging

Indian Brain Atlas