1. Trang chủ
  2. » Luận Văn - Báo Cáo

Luận văn thạc sĩ Công nghệ thông tin: Feature extraction and human-human interaction recognition for video surveillance

88 1 0
Tài liệu đã được kiểm tra trùng lặp

Đang tải... (xem toàn văn)

Tài liệu hạn chế xem trước, để xem đầy đủ mời bạn chọn Tải xuống

THÔNG TIN TÀI LIỆU

Thông tin cơ bản

Tiêu đề Feature Extraction and Human-Human Interaction Recognition for Video Surveillance
Tác giả Nguyen, Thuy Ngoc
Người hướng dẫn Associate Professor Atsuo Yoshitaka
Trường học Japan Advanced Institute of Science and Technology
Chuyên ngành Information Science
Thể loại Doctoral Dissertation
Năm xuất bản 2016
Định dạng
Số trang 88
Dung lượng 54,43 MB

Các công cụ chuyển đổi và chỉnh sửa cho tài liệu này

Cấu trúc

  • 4.2 Independent Subspace Analysis (ISA) for image data (41)
  • 4.3 Three-layer convolutional ISA network .................00 (46)
    • 4.3.1 Video block extraction .. 2... 0.0.0... 002000 eee 41 (49)
    • 4.3.2 Hierarchical invariant features........... . co 41 (49)
    • 4.3.3 Poolng........ . . cu ng ng kg kg va 44 (0)
  • 4.4 Classification 2... 6ẻ.HA...a.. ee 46 (54)
  • 44.1 Bag-of-features representation ............. 0000 000- 46 (54)
    • 4.4.2 Support vector machine ........... 2.002.000 eee 46 (54)
    • 4.5.1 Experimental setID....... . . . cà 00000. eee 47 (55)
    • 4.5.2 Classification results .......... . . ee 48 (56)
    • 4.5.3 Analysis of parameter settingS........ . . . . QC 52 (60)
  • 4.6 Summary of interaction recognition ........ ... . . co 55 (63)
  • 5.1 Introduction... 2... . gà gà kg va 56 5.2_ Interaction localization based on temporal sliding window (64)
    • 5.2.1 Temporal sliding window. ..................0.000. 59 5.2.2. Extraction of hierarchical invariant features (67)
    • 5.2.3 Classification .. 2... NI a< a 60 (68)
    • 5.2.4 Non-maximum suppression... .......0.. 00000000004 61 (69)
  • 5.3 Experimental results ......... . . cv va 62 (70)
    • 5.3.1 Experimental setup... ... . cv vo 62 (70)
    • 5.3.2 Localization results... 2 0. ee 62 (70)
  • 5.4 Summary of interaction temporal localization (71)

Nội dung

This dissertation addresses human activity recognition, espe-cially human-human interactions in realistic video material, such as movies, surveillance videos.. Besides, we believe that o

Independent Subspace Analysis (ISA) for image data

Definition of the ISA and it’s algorithm

Independent Component Analysis (ICA) [37] is a statistical model, which is defined by a linear transformation of latent independent variables In particular, let x‘ denote the grey- scale values in a small image patch, the ICA model expresses x’ as a linear superposition

33 of some features A: x'= As (4.1) where s is a vector whose elements are components (or coefficients) Note that s is different from patch to patch The matrix A is the same for all patches.

The basic assumption in the ICA model is that the components s are nongaussian and statistically independent Given a sufficient number of observations of image patches, the problem is then to estimate the values of A without knowing the values of latent components s This problem is restricted to the basic case where A is an invertible matrix Hence, estimation of A in Eq (4.1) is equivalent to determining the values of W in Eq (4.2): s = Wx' (4.2) where W is obtained by inverting the matrix A.

Independent Subspace Analysis (ISA) [35] is an interesting generalization of the basic ICA, and has the same model as in Eq (4.1) In contrast to the ICA, the components s are not assumed to be statistically independent In the ISA model, s can be divided into couple, triplet, or in general ô-tuples where ô is the dimension of subspace The ISA model assumes that the components inside a given ô-tuple may be dependent on each other, but dependencies among different ô-tuples are not allowed.

Figure 4.1 represents the ISA as a two-layer network, where the elements of the matrix

W in Eq (4.2) are weights in the first layer In this figure, the dimension of subspace is

2 (kK = 2) The objective of the ISA is to learn the weights W while the weights V in the second layer are fixed to represent the subspace structure of the units in the first layer.

Let x’ € R"*! again denote the input patch, the response of /—th unit in the first layer is defined by Eq (4.3): er = (> Wyx;')? (4.3) where W € R**” is the connection weights of the first layer; n and k are the input dimension and number of units in the first layer.

As illustrated in Figure 4.1, each unit of the second layer pools over a small neighbor- hood of adjacent first layer units Hence, the response of each second layer unit is defined by Eq (4.4): k k n filx's W,V) = | Viner =.) 35 Val 95 Wix;")? (4.4) l=1 l=1 j=l

Figure 4.1: The neural network architecture of an ISA network The blue and red bubbles represent units in the first and second layer respectively In this figure, the dimension of subspace is 2: each red bubble looks at 2 blue bubbles. where V € RTM** is the weights connecting units of the first layer to units of the second layer, and m is the number of units in the second layer The matrix V represents the subspace structure of the units in the first layer, and is defined by Eq (4.5):

1, if(@-De+1

Ngày đăng: 08/11/2024, 17:07

TỪ KHÓA LIÊN QUAN

TÀI LIỆU CÙNG NGƯỜI DÙNG

TÀI LIỆU LIÊN QUAN

🧩 Sản phẩm bạn có thể quan tâm

w