Thursday, September 5, 2013


Ideas Seminar: Richard Souvenir
Date: August 23, 2013

 
Prof. Richard Souvenir and his students focused on computer vision and machine learning in particular, exploring ways to coordinate multiple cameras, processing the information in one or more computers to understand human motion and behavior.

First of all, Computer vision is concerned with modeling and replicating human vision using computer software and hardware. It seems combines knowledge in computer science, and many other disciplines such as electrical engineering, mathematics, physiology, biology, and cognitive science. It needs knowledge from all these fields in order to understand and simulate the operation of the human vision system. I think Images and movies are everywhere, computer vision is becoming more popular as the power of computers increase. Computer vision is concerned with the automatic extraction, analysis and understanding of useful information from a single image or a sequence of image. It involves the development of a theoretical and algorithmic basis to achieve automatic visual understanding. And they have been studying how to reconstructed, interpret and understand a 3D scene from its 2D images in terms of the properties of the structure present in the scene

Especially, during the lecture, they showed us to present computer vision to detect and track the face and hands of a human being in real time from a video sequence captured by a webcam. Tracking people in video enables applications in surveillance, traffic monitoring, and video conferencing. They said, recent multi-camera methods have helped to overcome some of the issues associated with object tracking, such as drift and occlusion that arise in the single-camera case. However, the integration of multiple cameras introduces new challenges in terms of resource consumption and algorithm complexity. Moreover, while tracking accuracy tends to increase with the number of cameras, the potential also increases for poor measurements from individual cameras to negatively act aggregate tracking estimates. Of course computer vision and machine learning will be definitely helpful to understand spatial cognition and people reaction.

No comments: