Thông tin chung
  English
  Đề tài NC khoa học
  Bài báo, báo cáo khoa học
  Hướng dẫn Sau đại học
  Sách và giáo trình
  Các học phần và môn giảng dạy
  Giải thưởng khoa học, Phát minh, sáng chế
  Khen thưởng
  Thông tin khác
  Tài liệu tham khảo
  Hiệu chỉnh
 
Số người truy cập: 107,109,829

 Human Activity Recognition Based on Weighted Sum Method and Combination of Feature Extraction Methods
Tác giả hoặc Nhóm tác giả: Nang Hung Van NGUYEN, Minh Tuan PHAM, Nho Dai UNG, Kanta TACHIBANA
Nơi đăng: International Journal of Intelligent Information Systems; Số: ISSN: 2328-7675 (Print); ISSN: 2328-7683 (Online);Từ->đến trang: 43 - 50;Năm: 2018
Lĩnh vực: Chưa xác định; Loại: Bài báo khoa học; Thể loại: Quốc tế
TÓM TẮT
Human Activity Recognition (HAR) is one of the most important areas of computer vision research. The biggest difficulty for HAR system is that the camera could only film in one direction, leading to a shortage of data and low recognition results. This paper focuses on researching and building new models of HAR, including Principal Components Analysis (PCA), Linear discriminant Analysis (LDA) is to reduce the dimensionality and size of data, contributing to high recognition accuracy. First, from the 3D motion data, we conducted a pretreatment and feature extraction of objects. Next, we built a recognition model corresponding to each feature extraction method and we used Support Vector Machine (SVM) model to train. Finally, we used weighted methods to combine the results of the model to train and give the final results. The paper experiment on CMU MOCAP database and the percentage receiving proposed method is higher than that from the previous method.
ABSTRACT
Human Activity Recognition (HAR) is one of the most important areas of computer vision research. The biggest difficulty for HAR system is that the camera could only film in one direction, leading to a shortage of data and low recognition results. This paper focuses on researching and building new models of HAR, including Principal Components Analysis (PCA), Linear discriminant Analysis (LDA) is to reduce the dimensionality and size of data, contributing to high recognition accuracy. First, from the 3D motion data, we conducted a pretreatment and feature extraction of objects. Next, we built a recognition model corresponding to each feature extraction method and we used Support Vector Machine (SVM) model to train. Finally, we used weighted methods to combine the results of the model to train and give the final results. The paper experiment on CMU MOCAP database and the percentage receiving proposed method is higher than that from the previous method.
© Đại học Đà Nẵng
 
 
Địa chỉ: 41 Lê Duẩn Thành phố Đà Nẵng
Điện thoại: (84) 0236 3822 041 ; Email: dhdn@ac.udn.vn