Digital Media Forensics (08/14 - 08/17)
This project is funded by Department of Electronics and Information Technology (DEITY).
Digital Media Forensics can function both as a source of intelligence in carrying out investigation to aid us in identifying perpetrators, as well as evidence in a court of law. Digital media forensics is also useful under broadcasting scenarios. News channels receive multiple digital contents in the form of image or video captured by general public which may not be reliable always.
Forgery detection, source camera identification in image/video as well as frame tampering detection in video are some of the challenging problems which are targeted in this project.
Aerial Imagery Visual Tracking
The project aims at finding the optimal appearance models for visual tracking in aerial videos acquired from micro UAVs. Micro UAVs can be efficiently deployed for surveillance, traffic monitoring, human re-identification and crowd management. These UAVs can obtain the videos which can be further used for tracking of vehicles, individuals or group of people. Since the videos are obtained from a height and moving cameras, tracking poses a lot of challenges such as dynamic background, occlusion and illumination changes. In addition, the objects of interest may be very small due to low resolution and have a huge pose variation. In such a scenario, the popular appearance models are not useful for achieving a good tracking performance. Thus, finding optimal appearance models becomes a crucial task in tracking.
Completed Projects (2014 - 2015) - AUV Object Detection and Identification using Sonar
The primary aim of this proposal is to develop onboard object detection and identification capabilities for autonomous underwater vehicles. For object detection, sonar is used by the AUV. We use sonar image processing techniques to detect an object and identify the type of the object against a set of targets. Once a target has been identified, the AUV surfaces and communicates the location of the target to the base station. Such autonomous detection and identification capability will enable several naval applications like Mine Counter Measure and detection of underwater threat to be highly effectively. This project was funded by Naval Research Board.
Interested PhD candidates can directly send their CV to me.