Kalman Filtering and Neural Networks P3

LEARNING SHAPE AND MOTION FROM IMAGE SEQUENCES Gaurav S. Patel Department of Electrical and Computer Engineering, McMaster University, Hamilton, Ontario, Canada Sue Becker and Ron Racine Department of Psychology, McMaster University, Hamilton, Ontario, Canada (beckers@) INTRODUCTION In Chapter 2, Puskorius and Feldkamp described a procedure for the supervised training of a recurrent multilayer perceptron – the nodedecoupled extended Kalman filter (NDEKF) algorithm. We now use this model to deal with high-dimensional signals: moving visual images. Many complexities arise in visual processing that are not present in onedimensional prediction problems: the scene may be cluttered with backKalman Filtering and Neural Networks, Edited by Simon Haykin. | Kalman Filtering and Neural Networks Edited by Simon Haykin Copyright 2001 John Wiley Sons Inc. ISBNs 0-471-36998-5 Hardback 0-471-22154-6 Electronic 3 LEARNING SHAPE AND MOTION FROM IMAGE SEQUENCES Gaurav S. Patel Department of Electrical and Computer Engineering McMaster University Hamilton Ontario Canada Sue Becker and Ron Racine Department of Psychology McMaster University Hamilton Ontario Canada beckers@ INTRODUCTION In Chapter 2 Puskorius and Feldkamp described a procedure for the supervised training of a recurrent multilayer perceptron-the nodedecoupled extended Kalman filter NDEKF algorithm. We now use this model to deal with high-dimensional signals moving visual images. Many complexities arise in visual processing that are not present in onedimensional prediction problems the scene may be cluttered with back- 69 70 3 LEARNING SHAPE AND MOTION FROM IMAGE SEQUENCES ground objects the object of interest may be occluded and the system may have to deal with tracking differently shaped objects at different times. The problem we have dealt with initially is tracking objects that vary in both shape and location. Tracking differently shaped objects is challenging for a system that begins by performing local feature extraction because the features of two different objects may appear identical locally even though the objects differ in global shape . squares versus rectangles . However adequate tracking may still be achievable without a perfect three-dimensional model of the object using locally extracted features as a starting point provided there is continuity between image frames. Our neural network model is able to make use of short-term continuity to track a range of different geometric shapes circles squares and triangles . We evaluate the model s abilities in three experiments. In the first experiment the model was trained on images of two different moving shapes where each shape had its own characteristic movement trajectory. In the second .

Không thể tạo bản xem trước, hãy bấm tải xuống
TÀI LIỆU LIÊN QUAN
31    942    42
TỪ KHÓA LIÊN QUAN
TÀI LIỆU MỚI ĐĂNG
145    17    4    01-12-2022
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.