Detection Based on A Robust Line Tracker Using Multiple Kalman Models
Hung Kwun, Hung Kwun Fung, Kin Hong Wong · 2013
Quadrangle and line tracking are essential for many real world applications of computer vision. In this paper, we propose a computationally ef ficient line tracker that can robustly and accuratel y track lines in an image. We use a multiple-model tracking accurately and r filters in parallel. Each filter is configured to use a different state transition model. All the filters are updated by the measurement at the same t ime following the conventional Kalman combination of outputs from all the Kalman detected, we developed a scheme to merge the lines together to become suitable quadrangles. The experimental result shows that the proposed system can lines and quadrangle robustly in real time. The res ult is useful in shape detection and should be suitable for building many mobile pro jector applications. Quadrangle and line tracking are essential for many real world applications of computer vision. In this paper, we propose a computationally ficient line tracker that can robustly and accuratel y track lines in an image. We model -Kalman filter (MMKF) scheme, which can handle line tracking accurately and r obustly. The basic idea is to run N multiple sub- Kalman filters in parallel. Each filter is configured to use a different state transition filters are updated by the measurement at the same t ime following the conventional Kalman filter update process. The final prediction is a combination of outputs from all the Kalman filter modules. After lines are detected, we developed a scheme to merge the lines together to become suitable quadrangles. The experimental result shows that the proposed system can lines and quadrangle robustly in real time. The res ult is useful in shape detection and should be suitable for building many mobile pro jector applications. Quadrangle and line tracking are essential for many real world applications of computer vision. In this paper, we propose a computationally ficient line tracker that can robustly and accuratel y track lines in an image. We filter (MMKF) scheme, which can handle line Kalman filters in parallel. Each filter is configured to use a different state transition filters are updated by the measurement at the same t ime following final prediction is a filter modules. After lines are detected, we developed a scheme to merge the lines together to become suitable quadrangles. The experimental result shows that the proposed system can track lines and quadrangle robustly in real time. The res ult is useful in shape detection