step 1
主元素分析法PCA初始化B样条曲面
step 2
拟合B样条曲面
step 3
循环初始化B样条曲线
step 4
拟合B样条曲线
step 5
三角化B样条曲面
Gestalt principles
Monte Carlo particle filter (MCPF)蒙特卡洛粒子滤波
tracking-state-detection(TSD)This allows to learn or extend a
probabilistic motion model.
一些符号约定
S
——savings of a surface model hypothesis
Ξ
—— knot vector
ξ
—— parameter of a B-spline curve
Ω
——parameter space of a B-spline curve or surface
Mj,p
——j-th B-spline basis function of p-th order
c
——B-spline curve
S
——B-spline surface
p
——point
t
——tangent vector
e
——error function
w
——weighting factor or -function
ρ
——curvature of the B-spline curve
ε
——threshold
K
——stiffness matrix
t
——time steps
I
——colour image
t
——translation
i,j,k
——imaginary units
q
——quaternion
θx,y,z
——imaginary value of quaternion
θ
——vector of imaginary values of quaternion, i.e. rotation
x~
——posterior particle
N
——normal distributed noise
c
——confidence
P
——discrete probability
N
——number of particles
y
——observation
M
——object model projected to image space
s
——normalizing factor
δ(x)
——delta-Dirac mass located in x
u,v
——pixel coordinates in image space
Xft
——set of fixed particles
o
——detection success
e
——tracking error
第一章 介绍
认知机器人的子任务:
• Knowledge representation: Represent knowledge that allows for extension and
modification over time.
• Reasoning: Reason about the world using and updating the current knowledge.
• Autonomous robot: Integrate knowledge about the embodiment of the robot
and consider its possibilities.
• Dynamic world: Detect and observe changes in the environment as well as in
the present state of knowledge.
• Incomplete world: Identify knowledge gaps, i.e. missing information.
1.1Problem statement: modelling objects
建模的要求:
shape
colour颜色对环境光照比较敏感,但是颜色的梯度信息A strong cue is provided by the gradients of a colour image
since colour itself strongly depends on the lighting conditions. A more suitable way is to use histograms of colour and gradients of image patches.
一个更合适的方法是使用颜色和图像块的梯度直方图。 SIFT和SURF
Physical behaviour
系统的抓取在模型建立不完全的时候也能工作。这就暗示了模型的建立不能是一步一步的,而应该是平行建立的。
第二章 分割与重建
收敛的时候使某些距离最小。
point distance(PD)
tangent distance(TD)
squared distance (SD)