Teknik Rektifikasi Citra dan Tapis Kalman Dalam Mengestimasi Kecepatan Kendaraan

Rika Favoria Gusa

Abstract


Estimating is a challenging task when the image sequence from a camera are directly processed because there is perspective projection that causes length and area ratio of objects in the image are not preserved. In this paper, it was used image rectification technique and Kalman filter algorithm to overcome the problems encountered in order to obtain accurate vehicle velocity estimation. Rectified images as result of image rectification were processed, then Kalman filter algorithm was executed based on the processing result of the rectified images. The result of the tests showed that geometric distortion on the objects in the image sequence could be corrected well by using image rectification. Kalman filter algorithm was also good enough in estimating vehicle velocity. The error of average velocity estimation was ±3 km/hour.

Keywords : Estimation, Vehicle velocity, Image rectification, Kalman filter.

 

Abstrak

Estimasi kecepatan akan sulit dilakukan dengan langsung mengolah runtun citra kendaraan yang diperoleh dengan menggunakan kamera. Hal ini dikarenakan panjang maupun luas objek-objek di dalam citra mengalami perubahan akibat adanya proyeksi perspektif.Dalam penelitian ini, distorsi geometrik objek di dalam runtun citra akan diperbaiki dengan melakukan rektifikasi citra. Selanjutnya, algoritma tapis Kalman dijalankan guna mengolah informasi dari rectified images yang merupakan hasil rektifikasi runtun citra sehingga kecepatan kendaraan yang diamati dapat diperkirakan.Distorsi geometrik objek di dalam runtun citra yang diakibatkan oleh proyeksi perspektif pada kamera dapat dikoreksi dengan baik menggunakan rektifikasi citra yang dilakukan dengan menerapkan matriks transformasi proyektif yang dihitung berdasarkan kondisi (panjang maupun besar sudut) sebenarnya dari garis-garis objek di dalam runtun citra.Galat estimasi kecepatan rata-rata kendaraan ialah sebesar ±3 km/jam (saat kendaraan bergerak lurus).

Kata Kunci : Estimasi, Kecepatan kenderaan, Rektifikasi citra dan Filter Kalman

  

Full Text:

PDF

References


Brown, R. G., Hwang, P. Y. C. Introduction to Random Signals and Applied Kalman Filtering. 3rd ed.Canada: John Wiley and Sons.1997.

Cathey, F. W., Dailey, D. J. A Novel Technique to Dynamically Measure Vehicle Speed using Uncalibrated Roadway Cameras. Proceedings of IEEE.2005.

Liebowitz, D., Zisserman, A.Metric Rectification for Perspective Images of Planes. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.1998.

Maduro, C., Batista, K., Peixoto, P., Batista, J.Estimation of Vehicle Velocity and Traffic Intensity using Rectified Images. Proceedings of the 2008 IEEE International Conference on Image Processing.2008:777-780.

Grammatikopoulos, L., Karras, G., Petsa, E.Automatic Estimation of Vehicle Speed from Uncalibrated Video Sequences.International Archives of Photogrammetry and Remote Sensing.2002.

Marslin, R., Sullivan, G. D., Baker, K. D. Kalman Filters in Constrained Model Based Tracking. Department of Computer Science University of Reading.2008.

Rezaei, S.,Sengupta, R. Kalman Filter Based Integration of DGPS and Vehicle Sensors for Localization.IEEE Transactions on Control Systems Technology.2007; 15 (6).

Simon, D.Kalman Filtering. Department of Electrical and Computer Engineering Cleveland State University.2001.

Gusa, R., Favoria. Estimasi Kecepatan Kendaraan Menggunakan Rektifikasi Citra dan Tapis Kalman. Tesis Pascasarjana Teknik Elektro Universitas Gadjah Mada. 2010.




DOI: https://doi.org/10.25077/jnte.v3n1.50.2014

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

        

 

.
 Statistic and Traffic