Hand-Raise Detection Pada Kelas Cendekia Menggunakan Kamera RGB Dan Depth

Muhammad Fajar Khairul Auni (Prodi Elektronika dan Instrumentasi, DIKE, FMIPA, UGM, Yogyakarta, Indonesia)
Muhammad Idham Ananta Timur (Departemen Ilmu Komputer dan Elektronika, FMIPA UGM, Yogyakarta)
Ika Candradewi (Departemen Ilmu Komputer dan Elektronika, FMIPA UGM, Yogyakarta)

Indonesian Journal of Electronics and Instrumentation Systems
Vol 8, No 1 (2018): April

The requisite of intelligent classroom’s to perform the quickest speaker lift determination of speakers in the classroom using the concept of ubiquitous computing where the technology exists but does not feel around. The classroom concept requires several capabilities such as knowing the ideal distance from the camera, performing real-time hand-lifted movements from the speaker using the AdaBoost method, and determining the fastest hand lift from the speaker in real-time. The camera's ideal distance to speakers is about 250 cm. the system has a detection accuracy of 97.485497% and accuracy using coordinates joint point of 98%. The system is also capable of determining the fastest time using AdaBoost with 93.5% accuracy and the accuracy of the fastest hands lifting using coordinates joint point of 95%.