Tespit ile görsel nesne takibi için sıradüzensel betimlemeler.

Deep learning is the discipline of training computational models that are composed of multiple layers and these methods have improved the state of the art in many areas such as visual object detection, scene understanding or speech recognition. Rebirth of these fairly old computational models is usually related to the availability of large datasets, increase in the computational power of current hardware and more recently proposed unsupervised training methods that exploit the internal structure of very large, unlabeled datasets. An exhausting search of good parameters that are usually on the order of thousands, or even millions, is nearly impossible to result in a meaningful model when available dataset is relatively small and this is the reason why deep architectures are barely used for visual object tracking, which is a challenging yet very important task in computer vision. In this thesis, we investigate the use of hierarchical representations within the tracking-by-detection framework, a common strategy in visual object tracking that regards tracking as a detection problem in still images where temporal information is handled within a Bayesian approach. Stacked autoencoders and convolutional neural networks are trained using auxiliary datasets and the resultant hierarchical representations are experimented both off-the-shelf and after fine-tuning the pre-trained models using the few samples available. Experiments are realized using a challenge toolkit, which not only enables a fair comparison of hierarchical representations with well-known and widely-used hand-crafted features by using the same tracking-by-detection setting, but also demonstrates the performance of utilized framework among all recent visual tracking algorithms. Test results show that exploiting the intricate structure in auxiliary dataset, even without fine-tuning, contributes to the solution of visual object tracking problem.M.S. - Master of Scienc