1. APSRA : Automatic Person identification from CCTV video feeds installed at Security Risk Areas

Recently the immense cost of successful terrorist attacks on soft targets such as mass transport systems has indicated that forensic analysis of video after the event is simply not an adequate response. Indeed, in the case of suicide bombings there is simply no possibility of prosecution after the event and thus no deterrent effect. A pressing need is emerging to monitor all surveillance cameras in an attempt to detect events and persons-of-interest. A solution may be found in advanced surveillance systems employing computer monitoring of all video feeds, delivering the alerts to human responders for triage. Indeed such systems may assist in maintaining the high level of vigilance required over many years to detect the rare events associated with terrorism. Because of this, there has been a significant need in both the industry and the research community to develop advanced surveillance systems, sometimes dubbed as Intelligent CCTV (ICCTV). In particular, developing total solutions for protecting critical infrastructure has been on the forefront of R&D activities in this field. Read more

2. Object detection and categorization in natural scenes

While imitating human performance, cognitive technical systems should have an automatic visual component. In order to be useful such a component should be able to recognize many different object classes, as usually many objects are visible in an observed scene, and as goals of the system may vary strongly. This is only possible with generic object detection methods which can be trained to detect specific objects in a short time period. Presently, the most promising approach to achieve this goal is the use of unsupervised object categorization. The procedure is started with the extraction of shift-, rotation- and scale-invariant features at the location of prominent points in the image. The extracted parameters include a description of the location relative to other features. Such graph-based information is utilized to identify previously unknown object categories. Research efforts are directed to enable systems to recognize new object classes with no or only few training samples acknowledging the fact that humans and particularly children have the ability to recognize new object classes and learn them with only one or two examples. Read more

3. Automatic Traffic Monitoring and Access Control on Public Highways

Auotmatic vehicle type recognition (make and model) is very useful in secure access and traffic monitoring applications.It compliments the number plate recognition systems by providing a higher level of security against fraudelent use of number plates in traffic crimes.The work done in this regard presents a simple but powerful probabilistic framework for vehicle type recognition that requires just a single representative car image in the database to recognize any incoming test image exhibiting strong appearance variations, as expected in outdoor image capture e.g. illumination, scale etc. (see related publication)

Tracking and automatic vehicle number plate detection and type (make and model) recognition is very useful in secure access and traffic monitoring applications. Vehicle make and model recognition, specifically compliments the number plate recognition systems by providing a higher level of security against fraudulent use of number plates in traffic crimes. The work in this direction aims to develop a complete automated solution for secure traffic monitoring, including vehicle tracking, number plate recognition and make and model recognition. The system may be employed on public highways for a number of applications.(see related publication)

4. Video Background Subtraction

The work presents robust background subtraction algorithm to segment motion based video scene in embedded platforms. Every machine or computer vision algorithm to be useful should be able to separate the different background and foreground information (e.g. objects) in the given scene. Therefore, it is essential to the success of any real time algorithm, the scene segmentation invariant to lighting conditions. We designed two main algorithms; Six frames (6-Frames) and Time Interval with Memory (TIME) to segment the video scene robustly based on motion detection in embedded platforms. The former uses the first six frames and the latter samples the frames at regular intervals of time with memory to generate a background reference frame. (see related publication)

Undergraduate Research Projects/Thesis

1. Automatic Vehicle License Plate Detection in Images (In progress)

2. Vision Based Car Make and Model Recognition (VCMR) (In progress)

3. Subtraction and Removal of Shadows in Video Sequence (In progress)

4. Detection and Tracking of Moving Objects (completed)

5. Security Mechanisim Using Iris Recognition (completed)

6. PC Based Automatic Gun Control System (completed)

7. 3D Model Aproximation of any Object (completed)

8. Finger Print Recognition (completed)

9. Traffic Guidance System Using Image Processing (completed)

10. Artificial Intellegent ROBOCOP Team (completed)

11. Optical Chracter Recognition (OCR) for Mobile Phone (completed)

12. Security System using Face Recognition (completed)