Home > Search Results: Kremel, Tomáš
Search:
 
Search Tips :: Simple Search
Search collections:
Sort by: Display results: Output format:
National Repository of Grey Literature 2 records found  Search took 0.00 seconds. 
Point Cloud Rendering Approaches for Camera Pose Verification
 Kremel, Tomáš ; Pajdla, Tomáš (advisor) ; Guba, Peter (referee)
Visual localization is the problem of estimating the 6 degrees of freedom camera pose from which a query image was taken relative to a known reference scene representation. It is the key for applications such as Augmented, Mixed, and Virtual Reality, as well as autonomous robotics such as drones or self-driving cars. This thesis focuses on a visual localization pipeline, especially on its pose verification and reranking step. The pipeline uses 3D point clouds and 2D-3D correspondences be- tween the query image and 3D scene points for candidate camera poses estimations. The thesis explores point cloud rendering approaches as they are utilized in the pipeline and the verification step-the render of the discretized scene from a given candidate position is compared to the actual query image to asses if the given couple depicts the same place. One of the main challenges of such rendering is occlusion handling. Due to the sparsity of points employed for otherwise continuous real world representation, information about what lies in the front and what is hidden can be easily lost when projected to the 2D image. Rendering approaches explored in this thesis focus on the challenge directly or as a component of a novel view synthesis DNN-based renderer. Rendering influence on localization performance is investigated. 1
Detailed record
Camouflage pattern generator
 Kremel, Tomáš ; Šejnoha, Jiří (advisor) ; Neruda, Roman (referee)
The thesis focuses on the visual camouflage generation problem characterised by cre- ating a colored pattern that, when printed on an object, has concealment capabilities. A good concealment can save lives of military personnel and protect important facilities. We approach the problem by devising a genetic algorithm with problem-specific ge- netic operators. The complexity of the algorihm lies in innovative utilization of the saliency predicting tool in the fitness operator. The construction of the operator con- nects human vision, image processing, deep learning and evolutionary computation. Along the computaionally costly fitness operator we suggest fast and simple concep- tually related trial operator we use for exploring characterics of the costly one. Then, we use this knowledge for generation of a camouflage pattern for forest environment. 1
Detailed record

Interested in being notified about new results for this query?
Subscribe to the RSS feed.
Digital Repository :: Search :: Submit :: Personalize :: Help
Powered by Invenio v1.1.2
Maintained by admin.invenio@techlib.cz
This site is also available in the following languages:
Česky  English