Penerapan Metode K-Means Berbasis Jarak untuk Deteksi Kendaraan Bergerak

Penulis

Yuslena Sari, Andreyan Rizky Baskara, Puguh Budi Prakoso

Abstrak

Deteksi kendaraan bergerak adalah salah satu elemen penting dalam aplikasi Intelligent Transport System (ITS). Deteksi kendaraan bergerak juga merupakan bagian dari pendeteksian benda bergerak. Metode K-Means berhasil diterapkan pada piksel cluster yang tidak diawasi untuk mendeteksi objek bergerak. Secara umum, K-Means adalah algoritma heuristik yang mempartisi kumpulan data menjadi K cluster dengan meminimalkan jumlah kuadrat jarak di setiap cluster. Dalam makalah ini, algoritma K-Means menerapkan jarak Euclidean, jarak Manhattan, jarak Canberra, jarak Chebyshev dan jarak Braycurtis. Penelitian ini bertujuan untuk membandingkan dan mengevaluasi implementasi jarak tersebut pada algoritma clustering K-Means. Perbandingan dilakukan dengan basis K-Means yang dinilai dengan berbagai parameter evaluasi yaitu MSE, PSNR, SSIM dan PCQI. Hasilnya menunjukkan bahwa jarak Manhattan memberikan nilai MSE = 1.328 , PSNR = 21.14, SSIM = 0.83 dan PCQI = 0.79 terbaik dibandingkan dengan jarak lainnya. Sedangkan untuk waktu pemrosesan data memperlihatkan bahwa jarak Braycurtis memiliki keunggulan lebih yaitu 0.3 detik.

 

Abstract

Detection moving vehicles is one of important elements in the applications of Intelligent Transport System (ITS). Detection moving vehicles is also part of the detection of moving objects. K-Means method has been successfully applied to unsupervised cluster pixels for the detection of moving objects. In general, K-Means is a heuristic algorithm that partitioned the data set into K clusters by minimizing the number of squared distances in each cluster. In this paper, the K-Means algorithm applies Euclidean distance, Manhattan distance, Canberra distance, Chebyshev distance and Braycurtis distance. The aim of this study is to compare and evaluate the implementation of these distances in the K-Means clustering algorithm. The comparison is done with the basis of K-Means assessed with various evaluation paramaters, namely MSE, PSNR, SSIM and PCQI. The results exhibit that the Manhattan distance delivers the best MSE = 1.328 , PSNR = 21.14, SSIM = 0.83 and PCQI = 0.79 values compared to other distances. Whereas for data processing time exposes that the Braycurtis distance has more advantages

 


Teks Lengkap:

PDF

Referensi


ABRAMOV, K.V., SKRIBTSOV, P.V. dan KAZANTSEV, P.A., 2015. Image Segmentation Method Selection for Vehicle Detection Using Unmanned Aerial Vehicle. 9(5), hal.295–303.

BACHIR, B.M., TAREK, B., SENLIN, L. dan HOCINE, L., 2014. Weighted Samples Based Background Modeling for the Task of Motion Detection in Video Sequences. TELKOMNIKA, 12(11), hal.7778–7784.

CHACON-MURGUIA, M.I., GUZMAN-PANDO, A., RAMIREZ-ALONSO, G. dan RAMIREZ-QUINTANA, J.A., 2019. A novel instrument to compare dynamic object detection algorithms ☆. Image and Vision Computing, [daring] 88, hal.19–28. Tersedia pada: .

CHAURASIA, K. dan SHARMA, N., 2015. Performance Evaluation and Comparison of Different Noise , apply on PNGImage Format used in Deconvolution Wiener filter ( FFT ) Algorithm. Evolving Trends in Engineering and Technology, 4, hal.8–14.

CHRISTODOULOU, L., KASPARIS, T. dan MARQUES, O., 2011. Advanced statistical and adaptive threshold techniques for moving object detection and segmentation. 2011 17th International Conference on Digital Signal Processing DSP, hal.1–6.

DEV, S., MEMBER, S., LEE, Y.H. dan MEMBER, S., 2016. Color-based Segmentation of Sky / Cloud Images From Ground-based Cameras. XX(Xx), hal.1–12.

DHANACHANDRA, N., MANGLEM, K. DAN CHANU, Y.J., 2015. Image Segmentation Using K -means Clustering Algorithm and Subtractive Clustering Algorithm. Procedia Computer Science, 54, hal.764–771.

GAO, S., ZHANG, C. DAN CHEN, W.B., 2012. An improvement of color image segmentation through projective clustering. Proceedings of the 2012 IEEE 13th International Conference on Information Reuse and Integration, IRI 2012, hal.152–158.

GUIDO, G., VITALE, A., SACCOMANNO, F.F., ASTARITA, V. DAN GIOFRÈ, V., 2014. Vehicle Tracking System based on Videotaping Data. Procedia - Social and Behavioral Sciences, 111, hal.1123–1132.

JACHNER, S., VAN DEN BOOGAART, K.G. DAN PETZOLDT, T., 2007. Statistical Methods for the Qualitative Assessment of Dynamic Models with Time Delay (R Package qualV). Journal of Statistical Software, [daring] 22(8), hal.1–30. Tersedia pada: .

KALIRAJAN, K. DAN SUDHA, M., 2015. Moving Object Detection for Video Surveillance. 2015.

KEPUSKA, V., GONZALES, R. dan et al, 2012. Vector & Matrix Operations: Digital Image Processing.

KHAN, A., SAAD, S., ALI, A., ANWER, A., ADIL, S.H. dan MERIAUDEAU, F., 2018. Subsea Pipeline Corrosion Estimation by Restoring and Enhancing Degraded Underwater Images. IEEE Access, 6, hal.40585–40601.

LARKIN, K.G., 2015. Structural Similarity Index SSIMplified : (1), hal.1–4.

MAHARAJ, M.R. dan NAIDOO, B., 2018. An Analysis of Objective and Human Assessments in Contrast Enhancement. 13(22), hal.15843–15859.

MENG, X., LV, J. dan MA, S., 2020. Applying improved K-means algorithm into official service vehicle networking environment and research. Soft Computing, [daring] 24(11), hal.8355–8363. Tersedia pada: .

MOU, L., MEMBER, S., ZHU, X.X. dan MEMBER, S., 2018. Vehicle Instance Segmentation from Aerial Image and Video Using a Multi-Task Learning Residual Fully Convolutional Network. IEEE

TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, hal.1–14.

NASIR, I.S., 2018. The Proposed Image Segmentation Method Based On Adaptive K-Means Algorithm. 96(21), hal.7054–7064.

NO, I. DAN SINGH, S.P., 2013. Study of K-Means and Enhanced K-Means Clustering Algorithm. International Journal of Advanced Research in Computer Science, 4(10).

PAMBUDI, E.A., ANDONO, P.N. dan PRAMUNENDAR, R.A., 2018. Image Segmentation Analysis Based On K-Means PSO By Using Three Distance Measures. 9102(August), hal.1821–1826.

PREEDANAN, W., KONDO, T., BUNNUN, P., KUMAZAWA, I. dan IMAGES, A.V., 2018. A Comparative Study of Image Quality Assessment. hal.2–5.

QIN, L., SNOUSSI, H. dan ABDALLAH, F., 2014. Object tracking using adaptive covariance descriptor and clustering-based model updating for visual surveillance. Sensors (Switzerland), 14(6), hal.9380–9407.

RAFSANJANI, M.K., VARZANEH, Z.A., CHUKANLO, N.E., RAFSANJANI, M.K., VARZANEH, Z.A. dan CHUKANLO, N.E., 2012. A survey of Hierarchical Clustering Algorithms. The Journal of Mathematics and COmputer Science, 5(3), hal.229–240.

REALIZATION, D., FUTSUHARA, K., ZHANG, Y., WANG, J., YANG, X., IWASAKI, Y., KAWATA, S. dan NAKAMIYA, T., 2018. Multiple Vehicle Detection and Segmentation in Malaysia Traffic Flow. IOP Conference Series: Materials Science and Engineering PAPER.

RODRIGUEZ, M.Z., ID, C.H.C., CASANOVA, D., BRUNO, O.M., AMANCIO, D.R., COSTA, L.F. dan RODRIGUES, F.A., 2019. Clustering algorithms : A comparative approach. hal.1–34.

SINDHU, R., NANDAL, R., DHAMIJA, P., SEHRAWAT, H. dan SCIENCE, C., 2017. A Review On K-mean Algorithm And It ’ S Different Distance. 9(2), hal.1423–1430.

SPAGNOLO, P., ORAZIO, T.D., LEO, M. dan DISTANTE, A., 2006. Moving object segmentation by background subtraction and temporal analysis. 24, hal.411–423.

TANG, C., HU, H., ZHANG, M., WANG, W., WANG, X., CAO, F. dan LI, W., 2018. Real-time detection of moving objects in a video sequence by using data fusion algorithm. Transactions ofthe Institute ofMeasurement and Control, hal.1–12.

WANG, C.-T.A.T., 2010. MATLAB for Image Processing.

WOLF, S. dan PINSON, M., 2009. Reference Algorithm for Computing Peak Signal to Noise Ratio (PSNR) of a Video Sequence with a Constant Delay. hal.1–18.

ZHANG, C., REN, J., FAN, L. dan YU, C., 2017. A Novel Method of Preceding Vehicle Detection and Vehicle Distance Measurement Based on Monocular Vision. Revista de la Facultad de Ingeniería U.C.V., 32, hal.92–98.

ZHENG, S., n.d. Methods of Evaluating Estimators Mean Square Error (MSE) of an Estimator. In: Statistical Theory II Methods. hal.1–11.




DOI: http://dx.doi.org/10.25126/jtiik.2022945768