Главная
Study mode:
on
1
Intro
2
What Im interested in
3
Goals
4
Why is it hard
5
History of the field
6
Posttalk
7
Relaxation Labelling
8
Computer Vision
9
Kinematic Tree
10
The Lost Decade
11
The Basic Paradigm
12
Sandy Pentland
13
Dario Gavrila
14
The Human Body
15
Stochastic Search
16
Simulated annealing
17
Particle filtering
18
Priors
19
Priors are a crutch
20
Graphical models
21
Early graphical models
22
Higher dimensional models
23
The basic idea
24
The problem
25
Cyberware scanner
26
Why are bodies hard
27
The Cesar dataset
28
The Skate Model
29
The First Paper
30
Virtual Humans
31
Scanning the Human Body
32
Collecting Existing Data
33
Professional Models
34
Mesh
35
Shape Identity
36
Scanning
37
Body Shape
38
Poses
39
Template Mesh
40
Shape Blend
41
Pose
42
Linear Blend Skinning
43
Pose Blend Shapes
44
Deformation
45
RGBD
46
Track Infants
47
Interpersonal Interaction
48
Simple Body Model
49
Simple X
Description:
Explore the evolution and challenges of estimating human motion in this comprehensive lecture by Michael Black. Delve into the historical context, key concepts, and technological advancements in the field of human motion estimation. Learn about various techniques such as relaxation labelling, kinematic trees, stochastic search, and graphical models. Discover the complexities of modeling the human body, including shape identity, scanning methods, and deformation processes. Gain insights into the development of virtual humans, the importance of body shape and pose estimation, and the application of these concepts in tracking infants and analyzing interpersonal interactions. Understand the progression from simple body models to more complex representations, and explore the potential future directions in this fascinating area of research.

Estimating Human Motion: Past, Present, and Future

Andreas Geiger
Add to list
0:00 / 0:00