Research
Audio-Visual Signal Processing focuses on areas such as Automatic Speech Recognition (ASR) and Biometrics. Our most recent research includes facial tracking and feature extraction algorithms, information fusion across the audio and visual modalities, and ASR system architectures using dynamic Bayesian networks (DBNs).
Compressive sensing is an emerging new paradigm for signal sensing and many related fields in signal processing, where signal acquisition and compression are merged together with the use of prior knowledge about the signals.
Image and Video Analysis aims to extract semantics from digital images and video streams, such as object detection/tracking, multimedia information search/summarization, intelligent surveillance and remote monitoring.
Our work in watermarking, digital rights management, and surveillance applications.
Image and Video Recovery are the problems of uncovering with digital signal processing approaches the information lost due a number of reasons in the acquisition process. Typical applications are blur removal, denoising, increasing the resolution (super resolution).
Exploring the interface between signal processing and life sciences. Efforts in:
- DNA-based Digital Signal Processing
- Computational Biology and Biotechnology
- Medical imaging
- Molecular and Nanoscale Imaging
Many multimedia communication applications require transporting of compressed video data over lossy channels that can exhibit wide variability in throughput, delay, and packet loss. Providing acceptable video quality in such environments is a demanding task for both the video encoder/decoder as well as the communication and networking infrastructure.
At IVPL we are working towards the development of cutting-edge video compression techniques which are to deliver HD quality video under parsimonious transmission and storage requirements. Projects we are involved include advancement of the current video encoding standard H.264 and development of pre-and-post processing algorithms for video.
To retrieve information from the enormous mass of today's multimedia data, users require tools that automatically understand and manipulate the image/video content in the same structured way as a traditional database manages numeric and textual data. This problem is both important and challenging.