Research Area
Multimedia Data Analytics and Processing Research Unit is focusing on Computer Vision Techniques in Surveillance Applications.
We are working on the deep artificial intelligence and advanced machine learning solution for multimedia data analytics.
Anomaly detection
Anomaly detection refers to the process of identifying unusual and abnormal behavior or events in a video sequence that indicate suspicious activity. It involves using deep-learning algorithms to analyze the video data and detect any deviations from expected patterns. It is used in applications such as surveillance systems, healthcare systems, and traffic monitoring.
Digital Video Coding
Video coding is the process of exploiting redundancies present in video signals to achieve efficient data representation while maintaining a certain level of visual quality. The purpose is to compress the video data for transmission over a network with limited bandwidth, store it in limited storage, and stream on-demand over the internet. The most common video coding standards include MPEG, H.264/AVC, and H.265/HEVC.
Digital Image and video super-resolution technique
Digital Image and Video Super-resolution is a technique used to increase the resolution of low-resolution images and videos while maintaining as much visual quality as possible by recovering high-frequency information. Super-resolution is used in various applications, such as medical imaging, satellite imaging, surveillance, astronomy, and the military.
Face recogition and emotional expression
Face recognition and emotional expression are the technology that uses deep learning algorithms. The algorithm aims to identify or verify human identity and recognize and classify human emotions based on facial expressions. The applications are utilized in security and surveillance systems, marketing, and healthcare systems.
We Take Pride in Our Numbers
21
Years of Experience
20
Scopus-indexed publications
100+
conferences proceedings
2
Patents pending
5
Industry Awards
