Ismail Oner Sebe

Learn More
Recent advances in sensing and computing technologies have inspired a new generation of data analysis and visualization systems for video surveillance applications. We present a novel visualization system for video surveillance based on an Augmented Virtual Environment (AVE) that fuses dynamic imagery with 3D models in a real-time display to help observers(More)
An Augmented Virtual Environment (AVE) fuses dynamic imagery with 3D models. An AVE provides a unique approach to visualizing spatial relationships and temporal events that occur in real-world environments. A geometric scene model provides a 3D substrate for the visualization of multiple image sequences gathered by fixed or moving image sensors. The(More)
An intuitive and easy-to-use 3D modeling system has become more crucial with the rapid growth of computer graphics in our daily lives. Image-based modeling (IBM) has been a popular alternative to pure 3D modelers (e.g. 3D Studio Max, Maya) since its introduction in the late 1990s. However, IBM techniques are inherently very slow and rarely user friendly.(More)
Object-tracking is one of the most popular areas of video processing; most of the methods so far are object-dependent and concentrates only on one constraint of the object. In this report, I tried to combine multiple constraints for a faster and more robust tracking algorithm. Dynamic use of multiple constraints is the ultimate goal of the project, for the(More)
In this paper, we illustrate an image-based modeling system that uses polyhedral convex hull representation of its input images. Our algorithm develops over Matusik [1] as a special case of convex objects. Although the formulation is same, convex objects have a lot of symmetric properties that general silhouettes do not have, such as rays cross a convex(More)
We present a video-based rendering (VBR) method that creates arbitrary views of the scene from images captured by a single un-calibrated camera. The system is model-based and focused on a single object class, specifically vehicles in this paper. The procedure has three main steps. First, the object is rapidly modeled from a single image using a simple(More)
  • 1