báo cáo hóa học:" Research Article Viewpoint Manifolds for Action Recognition"

Tuyển tập báo cáo các nghiên cứu khoa học quốc tế ngành hóa học dành cho các bạn yêu hóa học tham khảo đề tài:Research Article Viewpoint Manifolds for Action Recognition | Hindawi Publishing Corporation EURASIP Journal on Image and Video Processing Volume 2009 Article ID 738702 13 pages doi 2009 738702 Research Article Viewpoint Manifolds for Action Recognition Richard Souvenir and Kyle Parrigan Department of Computer Science University of North Carolina at Charlotte 9201 University City Boulevard Charlotte NC 28223 USA Correspondence should be addressed to Richard Souvenir souvenir@ Received 1 February 2009 Accepted 30 June 2009 Recommended by Yoichi Sato Action recognition from video is a problem that has many important applications to human motion analysis. In real-world settings the viewpoint of the camera cannot always be fixed relative to the subject so view-invariant action recognition methods are needed. Previous view-invariant methods use multiple cameras in both the training and testing phases of action recognition or require storing many examples of a single action from multiple viewpoints. In this paper we present a framework for learning a compact representation of primitive actions . walk punch kick sit that can be used for video obtained from a single camera for simultaneous action recognition and viewpoint estimation. Using our method which models the low-dimensional structure of these actions relative to viewpoint we show recognition rates on a publicly available dataset previously only achieved using multiple simultaneous views. Copyright 2009 R. Souvenir and K. Parrigan. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use distribution and reproduction in any medium provided the original work is properly cited. 1. Introduction Video-based human motion analysis and action recognition currently lags far behind the quality achieved using markerbased methods which have shown to be very effective for obtaining accurate body models and pose estimates. However marker-based studies can only be conducted reliably in a laboratory .

Không thể tạo bản xem trước, hãy bấm tải xuống
TÀI LIỆU LIÊN QUAN
TÀI LIỆU MỚI ĐĂNG
Đã phát hiện trình chặn quảng cáo AdBlock
Trang web này phụ thuộc vào doanh thu từ số lần hiển thị quảng cáo để tồn tại. Vui lòng tắt trình chặn quảng cáo của bạn hoặc tạm dừng tính năng chặn quảng cáo cho trang web này.