- Title Information
- Title
- Physically Plausible Human Pose and Control Estimation from Video
- Name:
Personal
- Name Part
- Vondrak, Marek
- Role
- Role Term:
Text
- creator
- Origin Information
- Copyright Date
- 2013
- Physical Description
- Extent
- 20, 229 p.
- digitalOrigin
- born digital
- Note
- Thesis (Ph.D. -- Brown University (2013)
- Name:
Personal
- Name Part
- Jenkins, Odest
- Role
- Role Term:
Text
- Director
- Name:
Personal
- Name Part
- Sigal, Leonid
- Role
- Role Term:
Text
- Reader
- Name:
Personal
- Name Part
- Hodgins, Jessica
- Role
- Role Term:
Text
- Reader
- Name:
Personal
- Name Part
- Fleet, David
- Role
- Role Term:
Text
- Reader
- Name:
Personal
- Name Part
- Hays, James
- Role
- Role Term:
Text
- Reader
- Name:
Corporate
- Name Part
- Brown University. Computer Science
- Role
- Role Term:
Text
- sponsor
- Genre (aat)
- theses
- Abstract
- We propose a new paradigm for vision-based human motion capture. This paradigm
extends the traditional capture of poses by providing guarantees of physical
plausibility for the motion reconstructions and mechanisms for adaptation of
the estimated motions to new environments. We achieve these benefits by
estimating control programs for simulated physics-based characters from
(potentially monocular) images. The control programs encode motions implicitly,
based on their ``underlying physical principles'' and reconstruct the motions
through simulation. Feedback within the control allows application of the
principles in modified environments, providing an ability to adapt the motion
to external events and perturbations. We explore two control models:
trajectory control and state-space control. The trajectory control model
encodes the desired behavior of the character as a sequence of per-frame target
poses tracked by the controller. We can recover this sequence incrementally and
produce pose estimates that do not suffer from common visual artifacts.
However, the inference process is prone to overfitting. To address this
limitation, we then explore a more compact model that is less sensitive to the
quality of observations. State-space controllers allow concise representation
of motion dynamics through a sparse set of target poses and control parameters,
in essence allowing a key-frame-like representation of the original motion. We
represent state-space controllers using state machines that characterize the
character behavior in terms of motion phases (states) and physical events that
cause the phases to switch (transitions, e.g., a foot contact). Parameters of
the controller encode the control programs that reproduce the individual phases
in simulation. Because this control representation is sparse, we are able to
integrate information locally from multiple (tens of) image frames in
inference, inducing smoothness in the resulting motion, resolving some of the
ambiguities that arise in monocular video-based capture and enabling inference
with weak likelihoods. We demonstrate our approach by capturing sequences of
walking, jumping, and gymnastics. We evaluate our methods quantitatively and
qualitatively and illustrate that we can produce motion interpretations that go
beyond state-of-the-art in pose tracking and are physically plausible.
- Subject
- Topic
- motion capture
- Subject
- Topic
- control
- Subject
- Topic
- physics-based characters
- Subject
- Topic
- physical simulation
- Subject
- Topic
- controller estimation
- Subject
- Topic
- optimal control
- Subject (FAST)
(authorityURI="http://id.worldcat.org/fast", valueURI="http://id.worldcat.org/fast/872687")
- Topic
- Computer vision
- Record Information
- Record Content Source (marcorg)
- RPB
- Record Creation Date
(encoding="iso8601")
- 20131219
- Language
- Language Term:
Code (ISO639-2B)
- eng
- Language Term:
Text
- English
- Identifier:
DOI
- 10.7301/Z0XP737C
- Access Condition:
rights statement
(href="http://rightsstatements.org/vocab/InC/1.0/")
- In Copyright
- Access Condition:
restriction on access
- Collection is open for research.
- Type of Resource (primo)
- dissertations