Sökning: "Visual object tracking"

Visar resultat 1 - 5 av 39 avhandlingar innehållade orden Visual object tracking.

1. 1. Stochastic Modeling for Video Object Tracking and Online Learning: manifolds and particle filters

   Författare :Zulfiqar Hasan Khan; Chalmers tekniska högskola; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; anisotropic mean shift; online learning of reference object; covariance tracking; consensus point feature correspondences; Bayesian tracking; Gabor features; Visual object tracking; Grassmann manifold.; Riemannian manifold; particle filters;

   Sammanfattning : 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. LÄS MER

3. 2. Visual Object Tracking and Classification Using Multiple Sensor Measurements

   Författare :Yixiao Yun; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; sensor fusion; Riemannian manifold; visual pattern classification; multiple view geometry; Visual object tracking; boosting; multiple sensor measurement;

   Sammanfattning : Multiple sensor measurement has gained in popularity for computer vision tasks such as visual object tracking and visual pattern classification. The main idea is that multiple sensors may provide rich and redundant information, due to wide spatial or frequency coverage of the scene, which is advantageous over single sensor measurement in learning object model/feature and inferring target state/attribute in complex scenarios. LÄS MER

4. 3. Learning visual perception for autonomous systems

   Författare :Gustav Häger; Michael Felsberg; Per-Erik Forssén; Fahad Shahbaz Khan; Roman Pflugfelder; Linköpings universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; computer vision; visual object tracking; tracking; machine learning; deep learning;

   Sammanfattning : In the last decade, developments in hardware, sensors and software have made it possible to create increasingly autonomous systems. These systems can be as simple as limited driver assistance software lane-following in cars, or limited collision warning systems for otherwise manually piloted drones. LÄS MER

5. 4. Robust Visual Object Tracking mean shift, particle filters and point features

   Författare :Zulfiqar Hasan Khan; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; PF; MSEPF; mean shift; visual object tracking; RANSAC; SIFT; SURF;

   Sammanfattning : Visual object tracking has been identified as a promising technique for many computer vision applications like surveillance, flight navigation, video compression and driver assistance. The main idea is to find the state ofthe object and how it changes over time, in recursive video frames. LÄS MER

7. 5. Learning Object Properties From Manipulation for Manipulation

   Författare :Püren Güler; Danica Kragic; Jeremy L. Wyatt; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; robotics; manipulation; object properties; simulation; machine learning; object tracking; active exploration; sensory integration; Computer Science; Datalogi;

   Sammanfattning : The world contains objects with various properties - rigid, granular, liquid, elastic or plastic. As humans, while interacting with the objects, we plan our manipulation by considering their properties. For instance, while holding a rigid object such as a brick, we adapt our grasp based on its centre of mass not to drop it. LÄS MER