Video Research

Face Tracking and Video

Super-Resolution for Face Recognition Under Changing Pose and Illumination

First row: Low resolution input Video

Second row: Super resolution output Video

Third row: Low resolution input Video

Fourth row: Super resolution output Video

  We propose a new method for enhancing the resolution of low-resolution facial image by handling the facial image non-uniformly. We segment facial image into different regions corresponding to different motion models and estimate the motions non-uniformly of tracked regions in the consecutive frames. The experimental results provide a proof of the concept for our method and show that our method gives better results than handling the face uniformly.  

Gait Recognition

Fusion of Side Face and Gait for Human Recognition

Audio-Video Sensor Fusion

Moving Shadow Detection

3D Modeling of Vehicles from Video

A psychological Adaptive Model for Video


Anomalous Activity Detection