Pelacakan Objek Bergerak Berdasarkan Pendekatan Adaptive Threshold untuk Alpha Matting Menggunakan Metode K-Means

Rofiq Harun

Abstract


Pelacakan objek merupakan kegiatan penting dalam bidang computer vision yang memiliki banyak aplikasi bidang interaksi manusia dan komputer, pengawasan, ruang yang cerdas dan pencitraan medis. Dalam bentuk yang paling sederhana, pelacakan dapat didefinisikan sebagai masalah memperkirakan lintasan objek dalam bidang gambar ketika bergerak di sekitar scene. Pelacakan obyek udah banyak dilakukan oleh para peneliti sebelumnya, baik menggunakan representasi obyek, feature selection. Maka peneliti mengusulkan penelitian baru yaitu pencarian nilai threshold menggunakan metode kmeans. Kemudian di lanjutkan dengan proses matting. Dari percobaan menggunakan 15 data indoor dan 15 data outdoor, didapatkan nilai threshold menggunakan metode kmeansuntuk matting terbukti lebih baik dibandingkan dengan metode Otsu, FCM, maupun metode manual. Dimana nilai akurasi metode Otsu didapatkan nilai MSE sebesar 3,13E+02 pixel, nilai MSE untuk FCM didapat sebesar 5,22E+01 pixel, metode kmeans sebesar 4,00E+01 pixeldari beberapa frame yang dijadikan latihanmenggunakan metode kmeans menggunakan fungsi matting. Dan untuk dataset outdoor nilai rata-rata yang di dapat dengan metode Otsu didapatkan nilai MSE sebesar 1,38E+02 pixel, nilai MSE untuk FCM didapat sebesar 1,89E+02 pixel, metode kmeans sebesar 1,27E+02 pixel

Full Text:

PDF

References


REFERENSI

A. Yilmaz, O. Javed, and M. Shah, “Object tracking,” ACM Computing Surveys, vol. 38, no. 4, p. 13–es, Dec. 2006.

B. Zhong, H. Yao, S. Chen, R. Ji, X. Yuan, S. Liu, and W. Gao, “Visual tracking via weakly supervised learning from multiple imperfect oracles,” 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1323–1330, Jun. 2010.

C. J. Veenman, M. J. T. Reinders, and E. Backer, “Resolving motion correspondence for densely moving points,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 1, pp. 54–72, 2001.

D. Comaniciu, S. Member, and V. Ramesh, “Kernel-Based Object Tracking,” vol. 25, no. 5, pp. 564–577, 2003.

B. Zhong, Y. Chen, Y. Chen, R. Ji, Y. Chen, D. Chen, and H. Wang, “Background subtraction driven seeds selection for moving objects segmentation and matting,” Neurocomputing, vol. 103, pp. 132–142, Mar. 2013.

S. Cho and H. Byun, “Dynamic curve color model for image matting,” Pattern Recognition Letters, vol. 33, no. 7, pp. 920–933, May 2012.

L. Cinque, P. Dondi, and L. Lombardi, “Automatic selection of regions of interest in a video by a depth-color image matting,” Proceedings of the International Workshop on Video and Image Ground Truth in Computer Vision Applications - VIGTA ’13, pp. 1–8, 2013.

R. S. Basuki, “ADAPTIVE THRESHOLD UNTUK ALPHA MATTING,” vol. 2012, no. Semantik, pp. 398–403, 2012.

R. S. Basuki, “FUZZY C-MEANS ALGORITHM FOR ADAPTIVE THRESHOLD ON ALPHA MATTING,” no. July, pp. 177–180, 2012.

H.-F. Ng, “Automatic thresholding for defect detection,” Pattern Recognition Letters, vol. 27, no. 14, pp. 1644–1649, Oct. 2006.

G. Williams, “Overview Data Mining Algorithms Cluster Analysis What is Cluster Analysis ? What is Cluster Analysis ? What Is Good Clustering ? Clustering Caveats Similarity and Dissimilarity Between Objects Minkowski distance,” 2006.

D.-H. Kim, H.-K. Kim, and S.-J. Ko, “Spatial color histogram based center voting method for subsequent object tracking and segmentation,” Image and Vision Computing, vol. 29, no. 12, pp. 850–860, Nov. 2011.

Z. Liu, H. Shen, G. Feng, and D. Hu, “Tracking objects using shape context matching,” Neurocomputing, vol. 83, pp. 47–55, Apr. 2012.

Z. S. Siddique, “FINGERPRINT IDENTIFICATION FOR CYRIX MEDIAGX BASED EMBEDDED SYSTEM,” 2010.

S. G. Wu, F. S. Bao, E. Y. Xu, Y. Wang, Y. Chang, and Q. Xiang, “A Leaf Recognition Algorithm for Plant Classification Using Probabilistic Neural Network,” pp. 1–6.

and P. N. R. J. C. Bezdek, K. James, R. Krisnapuram, “FUZZY MODELS AND ALGORITHMS FOR PATTERN RECOGNITION AND IMAGE PROCESSING,” vol. 4. Springer US, 2005.

R. C. Gonzales, R. E. Woods, and S. L. Eddins, “Digital image processing using matlab.” Prentice Hall, 2009.

Y. Wen, Y. Lu, J. Yan, and Z. Zhou, “An algorithm for license plate recognition applied to intelligent transportation system,” Transportation, vol. 12, no. 3, pp. 830–845, 2011.


Refbacks

  • There are currently no refbacks.