We present a computer vision system for robust object tracking in 3D by combining evidence from multiple calibrated cameras. This kernel-based 3D tracker is automatically bootstra...
Ambrish Tyagi, Mark A. Keck, James W. Davis, Geras...
In this paper we present a method for learning a curve model for detection and segmentation by closely integrating a hierarchical curve representation using generative and discrim...
Adrian Barbu, Vassilis Athitsos, Bogdan Georgescu,...
While feature point recognition is a key component of modern approaches to object detection, existing approaches require computationally expensive patch preprocessing to handle pe...
This paper proposes a general framework called Markov stationary features (MSF) to extend histogram based features. The MSF characterizes the spatial co-occurrence of histogram pa...
Monocular SLAM has the potential to turn inexpensive cameras into powerful pose sensors for applications such as robotics and augmented reality. However, current implementations l...