基於Kinect之三維即時指尖追蹤演算法

人機互動領域中，指尖追蹤技術扮演著相當重要的角色，因為此技術可同時應用於手勢辨識及手部動作的偵測，且被廣泛應用於虛擬實境、手語辨識和智慧型裝置，這也使指尖追蹤技術成為近年的熱門研究主題。縱然先前已有許多手勢辨識相關之研究，但傳統以視覺為基礎的手勢辨識方法距滿足現今生活需要仍有一段距離。在此論文中，將講述一個使用Microsoft Kinect for Xbox One來進行指尖追蹤技術的方法，且使用Microsoft Visual Studio 2013來實行此即時指尖追蹤系統。此系統將能偵測到使用者的手，並辨別手指，進而顯示各個指尖的相對座標與深度座標於螢幕上。此即時指尖追蹤系統的準確度約為 97.1%.。由於Kinect所使用的深度感測器為紅外線照相機，所以此系統的表現將受到光線及背景等因素所造成的些微影響。此系統的準確度及完善度使之成為一個在日常生活中，能被整合成各種不同應用的多功能的要素。

關鍵字

人機互動；手勢辨識；指尖追蹤；電腦視覺；模式識別；影像處理；手語辨識； Kinect

並列摘要

Fingertips tracking is of great importance for human-computer interaction (HCI), because it can be applied both in the hand gesture recognition (HGR) and hand movement detection. And its extensive applications in virtual reality, sign language recognition, and smart device makes it a hot research topic in recent years. Despite lots of previous work, traditional vision-based hand gesture recognition methods are still far from satisfactory for real-life applications. In this thesis, a novel method for fingertips tracking using the Microsoft Kinect for Xbox One is described, and a real-time fingertips tracking system is implemented with Microsoft Visual Studio 2013. The system is able to detect the hand of the user, to identify fingers, and to display the relative axis and depth axis information of fingertips on screen. The overall accuracy of the real-time fingertips tracking system is about 97.1%. Because the depth sensor of the Kinect is an infrared camera, the lighting conditions and background have little impact on the performance of this system. The accuracy and robustness make this system a versatile component that can be integrated in a variety of applications in daily life.

並列關鍵字

Human Computer Interaction (HCI) ； Hand Gesture Recognition (HGR) ； Fingertips Tracking ； Computer Vision ； Pattern Recognition ； Image Processing ； Sign language Gesture recognition ； Kinect

參考文獻

[3] Yeo, Hui-Shyong, Byung-Gook Lee, and Hyotaek Lim. "Hand tracking and gesture recognition system for human-computer interaction using low-cost hardware." Multimedia Tools and Applications 74.8 (2013): 2687-2715.

[5] Trapero Cerezo, F. "3D Hand and Finger Recognition using Kinect." University of Granada (UGR), Spain (2012).

[7] Hasan, Haitham, and S. Abdul-Kareem. "Static hand gesture recognition using neural networks." Artificial Intelligence Review 41.2 (2014): 147-181.

[8] Bouchrika, Tahani, et al. "Neural solutions to interact with computers by hand gesture recognition." Multimedia Tools and Applications 72.3 (2014): 2949-2975.

[9] Lockton, Ray. "Hand gesture recognition using computer vision." 4th Year Project Report (2002): 1-69.

國際替代計量

基於Kinect之三維即時指尖追蹤演算法

全文下載

主題瀏覽