Quadrangle Detection Based on A Robust Line Tracker Using Multiple Kalman Models  

Oleh:

Fung, Hung Kwun ; Wong, Kin Hong

Jenis: Article from Journal - ilmiah nasional - terakreditasi DIKTI
Dalam koleksi: Journal of ICT Research and Applications vol. 7C no. 2 (2013), page 137-150.
Topik: hough transform; line tracking; multiple kalman ?lter; quadrangle detection.
Fulltext: C13385.pdf (463.96KB)

Isi artikel

Quadrangle and line tracking are essential for many real world applications of computer vision. In this paper, we propose a computationally ef?cient line tracker that can robustly and accurately track lines in an image. We use a multiple-model-Kalman ?lter (MMKF) scheme, which can handle line tracking accurately and robustly. The basic idea is to run N multiple sub-Kalman ?lters in parallel. Each ?lter is con?gured to use a different state transition model. All the ?lters are updated by the measurement at the same time following the conventional Kalman ?lter update process. The ?nal prediction is a combination of outputs from all the Kalman ?lter 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 result is useful in shape detection and should be suitable for building many mobile projector applications.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali