Sistem Finding Choreography HipHop Basic Menggunakan MediaPipe Body Pose Estimation Untuk Dancer
Abstract
The evaluation of pose suitability in performing dance choreography, particularly in the hip-hop genre, is still conducted subjectively, making it difficult for novice dancers to obtain objective feedback on their choreography. This study aims to develop a model of a finding choreography system capable of evaluating the accuracy of beginner dancer’s pose against basic hiphop choreography movements. The system utilizes the MediaPipe framework to extract 33 body landmarks in (x, y, z) coordinates and visibility values. The extracted date are normalized using Min-Max Normalization to ensure uniform feature scaling before being classified with a Support Vector Machine (SVM) algorithm using the Radial Basis Function (RBF) kernel. The dataset, consisting of 791 pose images from the AIST Dance Video Database, is divided into 80% training and 20% testing. System evaluation is conducted using a Confusion Matrix including accuracy, precision, recall, f1-score to assess classification, performance. The results demonstrate that the model achieves excellent performance with an average accuracy of 99.01%, precision of 99.22%, recall of 98.75%, and f1-score of 98.98%
Keywords: Body Pose Estimation; Classification; HipHop Basic; MediaPipe; Support Vector Machine
Abstrak
Evaluasi kesesuaian pose dalam melakukan koreografi dance khususnya genre hiphop masih dilakukan secara subjektif, sehingga dancer pemula kesulitan dalam mendapatkan feedback yang objektif dari koreo yang dilakukan. Penelitian ini bertujuan untuk mengembangkan model sistem finding choreography yang mampu mengevaluasi kesesuaian pose dancer pemula terhadap gerakan dasar koreografi untuk genre hiphop. Sistem ini dibangun dengan memanfaatkan framework MediaPipe untuk mengekstraksi 33 titik tubuh (landmark) dalam bentuk koordinat (x, y, z) dan visibility. Data hasil ekstraksi kemudian akan dinormalisasi menggunakan teknik Min-Max Normalization agar setiap fitur berada pada skala yang seragam, sebelum diklasifikasikan menggunakan algoritma Support Vector Machine (SVM) dengan kernel Radial Basis Function (RBF). Dataset yang digunakan bersumber dari website AIST Dance Video Database sebanyak 791 data gambar yang dibagi menjadi 80% data training dan 20% data testing. Evaluasi model sistem dilakukan menggunakan Confusion Matrix dengan accuracy, precision, recall, dan f1-score untuk mengukur kinerja klasifikasi pose. Hasil penelitian menunjukkan bahwa model sistem mencapai performa tinggi dengan rata-rata accuracy 99.01%, precision 99.22%, recall 98.75%, dan f1-score 98.98%.
Keywords
References
N. Sato, "Improving reliability and validity in hip-hop dance assessment: Judging standards that elevate the sport and competition," Frontiers in Psychology, vol. 13, Oct. 2022, pp. 1-8. doi: 10.3389/fpsyg.2022.934158
R. Romindo, O. P. Barus, J. J. Pangaribuan, Y. A. Pratama, and E. Wiliem, "Implementasi Algoritma Support Vector Machine Terhadap Klasifikasi Pose Balet," Building of Informatics, Technology and Science (BITS), vol. 4, no. 3, pp. 1558-1566, 2022. doi: 10.47065/bits.v4i3.2647
Y. Effendi, Y. Kristian, L. Z. P.C.S.W, and H. Yutanto, "Pemanfaatan Mediapipe Body Pose Estimation dan Dynamic Time Warping untuk Pembelajaran Tari Remo," Jurnal Teknologi Dan Manajemen Informatika, vol. 9, no. 2, pp. 183-190, 2023. doi: 10.26905/jtmi.v9i2.10408
D. L. Setra, A. Novianty, and C. Setianingsih, "Pengimplementasian AI Body Language Decoder Menggunakan MediaPipe Dan Python pada Aplikasi Latihan Kognisi Berbahasa Indonesia," Jurnal Telkom University, vol. 11, no. 3, pp. 1645-1651, 2024.
S. A. Kaffah and Y. Ramdhani, "Gesture Recognition untuk Deteksi Bahasa Isyarat BISINDO: Pendekatan Mediapipe dan Random Forest," JOINTECS (Journal of Information Technology and Computer Science), vol. 8, no. 3, pp. 105, 2023. doi: 10.31328/jointecs.v8i3.4813
P. Lee, T. B. Chen, H. Y. Lin, L. R. Yeh, C. H. Liu, and Y. L. Chen, "Integrating OpenPose and SVM for Quantitative Postural Analysis in Young Adults: A Temporal-Spatial Approach," Bioengineering, vol. 11, no. 6, pp. 1-15, 2024. doi: 10.3390/bioengineering11060548
M. M. Ali and S. I. Mohamed, "A pose estimation for motion tracking of infants cerebral palsy," Multimedia Tools and Applications, vol. 84, no. 10, pp. 8261-8286, 2024. doi: 10.1007/s11042-024-19198-5
T. N. Laily and N. Pratiwi, "Klasifikasi Ukuran Baju Berdasarkan Pengukuran Tubuh Menggunakan MediaPipe dan Support Vector Machine," Jurnal Media Teknologi Informasi dan Komputer (METIK), vol. 9, no. 2, pp. 427-438, 2025. doi: 10.47002/metik.v9i2.1069
K. R. K. Dyansyah, S. D. Purwantoro, M. Ilmi, and R. Wulaningrum, "Penggunaan Computer Vision untuk Estimasi Pose Squat sebagai Solusi Alternatif Latihan Kebugaran di Gym," Prosiding Seminar Nasional Teknologi dan Sains (STains), vol. 4, pp. 199-207, 2025.
K. A. Tanjaya, M. F. Naufal, and H. Arwoko, "Pilates Pose Classification Using MediaPipe and Convolutional Neural Networks with Transfer Learning," Jurnal Ilmiah Teknik Elektro Komputer Dan Informatika, vol. 9, no. 2, pp. 212-222, 2023. doi: 10.26555/jiteki.v9i2.25975
K. Esaki and K. Nagao, "An Efficient Immersive Self-Training System for Hip-Hop Dance Performance with Automatic Evaluation Features," Applied Sciences (Switzerland), vol. 14, no. 14, 2024. doi: 10.3390/app14145981
A. L. Kalua, J. R. Kaplale, N. K. R. Mapalie, I. S. Iriansu, and E. Ketaren, "Pengembangan Alat Tes Kesamaptaan TNI/POLRI Berbasis Teknologi Computer Vision dan IoT dengan Metode Pose Estimation Menggunakan Python," Jurnal Technology Informatics & Computer System (TIMES), vol. 13, no. 2, pp. 294-299, 2024.
S. Dill, A. Ahmadi, M. Grimmer, D. Haufe, M. Rohr, Y. Zhao, M. Sharbafi, and C. Hoog Antink, "Accuracy Evaluation of 3D Pose Reconstruction Algorithms Through Stereo Camera Information Fusion for Physical Exercises with MediaPipe Pose," Sensors, vol. 24, no. 23, pp. 1-18, 2024. doi: 10.3390/s24237772
P. C. Panataagama, R. Wulanningrum, and S. Rochana, "Identifikasi Biometrik Gaya Berjalan Penyandang Disabilitas Menggunakan KNN," Prosiding Seminar Nasional Inovasi Teknologi, vol. 9, pp. 1284-1293, 2025.
S. Tsuchida, S. Fukayama, M. Hamasaki, and M. Goto, "AIST Dance Video Database," [Online]. Tersedia: https://aistdancedb.ongaaccel.jp/ [Diakses: 29 November 2025].
How To Cite This :
Refbacks
- There are currently no refbacks.
