小提琴姿勢變化即時偵測分析

dc.contributor李忠謀zh_TW
dc.contributorLee, Chung-Mouen_US
dc.contributor.author胡雯zh_TW
dc.contributor.authorHu, Wenen_US
dc.date.accessioned2022-06-08T02:43:37Z
dc.date.available2021-10-08
dc.date.available2022-06-08T02:43:37Z
dc.date.issued2021
dc.description.abstract小提琴的音色雖然優美,但對於初學者而言,一開始的學習是既枯燥又乏味的,拉奏出的琴音也十分不悅耳,需要長時間練習,才能慢慢掌握到正確的演奏姿勢。小提琴教師除了在課堂中教導音樂知識,也會即時糾正學生錯誤的姿勢。然而,初學者在自我練習時,若無老師或陪練員在身旁指教引導,大多無法做到接近標準的動作,更難意識到自己的錯誤,一旦習慣使用錯誤的姿勢練習,不僅對提升演奏技巧造成阻礙,也容易加大肌肉跟骨骼的傷害。本研究使用人體姿勢偵測方法進行小提琴姿勢正確度判定,使用攝影鏡頭拍攝記錄初學者練習時的狀態,以每秒30幀的取樣速率轉換成圖像,採用OpenPose開放式函式庫,在每張影像幀中擷取人體各部位的關節位置,偵測其人體骨架,同時計算人體關節角度,藉以判定小提琴拉奏姿勢,將這些資料進行滑動窗口的連續影像處理,系統結果呈現練習期間各種拉奏狀態出現的時間點,並依照狀態百分比給予評語。透過聲音回饋語音播放錯誤之姿勢,讓學生可以在練習時即時得知需要修正之處,練習結束後能通過紀錄了解自身的拉奏狀態。在課堂外的練習時間,使用自動化系統減輕家長陪練的負擔,也能隨時通過紀錄了解孩子的拉奏狀態,同時,導師可查看學員練習紀錄做分析與判斷,進而對學生的學習給予指導,進行長期的規劃和調整。zh_TW
dc.description.abstractAlthough violin has a beautiful tone, for novices, the learning at the beginning is both boring and tedious. The sound of the violin is also very unpleasant. It takes a long time to practice to slowly master the correct playing posture. In addition to teaching music knowledge in class, violin teachers will also immediately correct student’s wrong postures. However, when novices practice themselves, if there is no teacher or practice partner to teach and guide, most of them cannot achieve standard postures, and it is more difficult to realize their own mistakes. Once accustomed to using the wrong posture to practice, it will not only impede the improvement of playing skills, but also easily increase the damage to the muscles and bones.This research uses the human pose estimation detection method to determine the correctness of the violin posture, use the camera to record the status of novices during practice, converts into image at a sampling rate of 30 frames per second, use OpenPose to capture the joint positions of various parts of the human body in each image frame, detect the human skeleton, and calculate the joint angle of the human body to determine the violin playing posture. These data are processed in a sliding window of continuous images. The system results show the time points of various states during the practice, and give comments according to the state percentage.The wrong posture is playing by voice feedback, so that students can instantly know what needs to be corrected during the practice. After the practice, they can understand their own playing status through the record. Practice time outside the classroom, the automated system is used to reduce the burden of the parents to accompany the practice, and to understand the child's playing status through the record at any time. Furthermore, the teacher can view the student's practice record for analysis, to teach students and make long-term planning.en_US
dc.description.sponsorship資訊工程學系zh_TW
dc.identifier60847083S-40359
dc.identifier.urihttps://etds.lib.ntnu.edu.tw/thesis/detail/c36ab6ce333afafa3f2ff933dd06aa93/
dc.identifier.urihttp://rportal.lib.ntnu.edu.tw/handle/20.500.12235/117344
dc.language中文
dc.subject人體姿態估計zh_TW
dc.subject動作分析zh_TW
dc.subject小提琴演奏姿勢zh_TW
dc.subject教學系統zh_TW
dc.subject即時回饋系統zh_TW
dc.subjectHuman Pose Estimationen_US
dc.subjectMotion Analysisen_US
dc.subjectViolin Playing Postureen_US
dc.subjectTeaching Systemen_US
dc.subjectReal-Time Feedback Systemsen_US
dc.title小提琴姿勢變化即時偵測分析zh_TW
dc.titleReal-Time Violin Gesture Detection and Analysisen_US
dc.type學術論文

Files

Original bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
60847083S-40359.pdf
Size:
2.95 MB
Format:
Adobe Portable Document Format
Description:
學術論文

Collections