Unsual Behavior Analysis and Its Application to Surveillance Systems

1
Unsual Behavior Analysis and Its Application to
Surveillance Systems

• Yung-Tai Hsu(???)
• Jun-Wei Hsieh(???)
• Hong-Yuan Mark Liao(???)

2
Introduction

• Deformable Triangulations
• Skeleton-based Posture Recognition
• Posture Recognition Using the Centroid Context
• Experiment Results

3
Deformable Triangulations

• P is a posture extracted in binary form by image
  subtraction(fig.1)
• B is the set of boundary points along the contour
  of P(fig.2)
• Extract some high curvature points from B(fig.3)
• a(p) is the angle of a point p in B. It can be
  determined by two specified points p and
  p-.(fig.4)

fig.1 fig.2
fig.3 fig.4
4
Deformable Triangulations
Dmin B / 30, Dmax B / 20

• If a is larger than a threshold Ta (here we set
  it at 150), p is selected as a control point.
• If two candidates, p1 and p2 are close to each
  other, i.e., p1 p2ltdmin, the candidate
  with smaller a angle is chosen as a control
  point.

5
Deformable Triangulations
Vi
Vj
Va
Vb
Vk
6
Triangulation-based Skeleton Extraction

• P is decomposed into a set of triangle meshes Op
• OpTii0,1,2,,NTP-1
• Each triangle mesh Ti in Op has a centroid CTi

• H is defined as the head of P and it is the
  highest node among all the nodes.
• All the leaf nodes Li correspond to different
  limbs of P
• The branching nodes Bi are the key points used to
  decompose P into different body parts, such as
  the hands, feet, or torso.

7
Posture Recognition Using a Skeleton

• Assume SP and SD are two skeletal images
  extracted from a posture P and D.
• Assume DTSP is the distance map of SP.
• The value of a pixel r in DTSP is its shortest
  distance to all foreground pixels in SP.
• d(r, q) is the Euclidian distance between r and q.

• DTSP represents the image size of DTSP.
• SP and SD must be normalized to a unit size and
  their centers must be set to the origins of DTSP
  and DTSD.

8
Posture Recognition Using a Skeleton

1. Shows the original posture.
2. It is the result of skeleton extraction.
3. Shows the resultant distance map based on (b)

9
Centroid Context-based Description of Postures

• Assume all postures are normalized to a unit
  size.
• We project a sample onto a log-polar coordinate
  and label each mesh.
• Use m to represent the number of shells used to
  quantize the radial axis and
• use n to represent the number of sectors that we
  would like to quantize each shell.
• The total number of bins used to construct the
  centroid context is mn.
• For each centroid r of a triangle mesh of a
  posture, we construct a vector histogram hr.

• hr(k) is the number of triangle mesh centroids in
  the kth bin by considering r as the origin

• bink is the kth bin of the log-polar coordinate.

10
Centroid Context-based Description of Postures

• Given two histograms hri(k) and hrj(k), the
  distance between them can be measured by a
  normalized intersection

11
Centroid Context-based Description of Postures

• VP is the number of elemetns in VP.

12
Centroid Context-based Description of Postures

• Give two postures P and Q, the distance between
  their centroid contexts is measured by

• Where w and w are the area ratios of the ith and
  jth body parts residing in P and Q.

13
Centroid Context-based Description of Postures
14
Posture Recognition Using the Skeleton and the
Centroid Context

• Ti is the ith normal behavior with the training
  threshold.
• q is the query posture.
• ri,j is the jth key posture of the ith normal
  behavior with length N.

15
Experiment Results