A kernel-based metric measuring tracking reliability that is based on discriminative components of a kernel target model and kernel mutual information is presented. The discriminative components of the kernel target model are selected by computing the log-likelihood ratios of classconditional sample densities of these components from a target region and background sampled region. The components...

In this contribution we describe a visual marker-less realtime tracking system for Augmented Reality applications. The system uses a fisheye lens mounted on a firewire camera with 10 fps for visual tracking of 3D scene points without any prior scene knowledge. All visual-geometric data is acquired online during the tracking using a structure-frommotion approach. 2D Image features in the hemisph...

Convolutional Neural Networks (CNNs) have demonstrated its great performance in various vision tasks, such as image classification [18] and object detection [8]. However, there are still some areas that are untouched, such as visual tracking. We believe that the biggest bottleneck of applying CNN for visual tracking is lack of training data. The power of CNN usually relies on huge (possible mil...

Object tracking quality usually depends on video context (e.g. object occlusion level, object density). In order to decrease this dependency, this paper presents a learning approach to adapt the tracker parameters to the context variations. In an offline phase, satisfactory tracking parameters are learned for video context clusters. In the online control phase, once a context change is detected...

Classical visual object tracking techniques provide effective methods when parameters of the underlying process lie in a vector space. However, various parameter spaces commonly occurring in visual tracking violate this assumption. This thesis is an attempt to investigate robust visual object tracking and online learning methods for parameter spaces having vector or manifold structures. For vec...

Object detection and tracking in videos represent essential computationally demanding building blocks for current future visual perception systems. In order to reduce the efficiency gap between available methods computational requirements of real-world applications, we propose re-think one most successful image object detection, Faster R-CNN, extend it video domain. Specifically, framework lear...