完整後設資料紀錄
DC 欄位語言
dc.contributor.author李啟銘en_US
dc.contributor.authorChi-Ming Leeen_US
dc.contributor.author廖弘源en_US
dc.contributor.authorHong-Yuan Mark Liaoen_US
dc.date.accessioned2014-12-12T02:55:17Z-
dc.date.available2014-12-12T02:55:17Z-
dc.date.issued2005en_US
dc.identifier.urihttp://140.113.39.130/cdrfb3/record/nctu/#GT009317591en_US
dc.identifier.urihttp://hdl.handle.net/11536/78801-
dc.description.abstract對一個成功的人類行為分析系統而言,人類姿勢辨識是其中最重要的一部分。在本篇論文中,我們提出以輪廓及機器學習為基礎的方法,以發展出一個有效率且正確性高的人體姿勢辨識系統。在所提出的系統中,我們首先由人體輪廓抽取出其中具有高度識別性的特徵,並利用名為AdaBoost的機器學習方法來建構我們的辨識系統。我們根據人類姿勢中獨有的特性來選擇並修改AdaBoost所使用的特徵。藉由我們所使用的特徵所具的高度描述能力,我們將呈現此系統會較使用傳統步驟的方法有更高的效能。使用者可藉由我們所提出的架構來達到一個快速且有效的人類姿勢辨識。zh_TW
dc.description.abstractHuman posture analysis is one of the most important steps towards successful human behavior analysis. In this thesis, a silhouette-based learning approach is proposed to develop an efficient and effective human posture recognizing system. Discriminating features from human body silhouette are first extracted and then AdaBoost algorithm is employed for training a recognition system. The features in AdaBoost are selected and modified according to the specific characteristics of human postures. Depending on the describing ability of our features, we demonstrate that our system operates higher performance than the traditional approaches. Users can recognize human postures in an efficient and effective manner using the proposed framework.en_US
dc.language.isoen_USen_US
dc.subject姿勢辨識zh_TW
dc.subject輪廓zh_TW
dc.subjectHuman posture recognitionen_US
dc.subjectsilhouetteen_US
dc.subjectLearningen_US
dc.title以輪廓特徵學習之人類姿勢辨識zh_TW
dc.titleSilhouette Feature Detection Using AdaBoost with Applications to Human Posture Recognitionen_US
dc.typeThesisen_US
dc.contributor.department資訊科學與工程研究所zh_TW
顯示於類別:畢業論文


文件中的檔案:

  1. 759101.pdf

若為 zip 檔案,請下載檔案解壓縮後,用瀏覽器開啟資料夾中的 index.html 瀏覽全文。