|
View-invariant Recognition of Human Actions
Recognition of human motion and action is an important
area of research in computer vision that plays a crucial
role in various applications such as surveillance, human-computer
interaction, ergonomics, etc. Depending on the
nature and the scale of the problem, understanding of human
motion is usually studied at four levels of granularity:
pose, movement, action, and activity. The
challenges being addressed include perspective distortions,
differences in viewpoints, unknown camera parameters, anthropometric
variations, and the large degrees of freedom
of articulated bodies. Action can be regarded as a
collection of 4D space-time data observed by a perspective
video camera. After image projection, the 3D Euclidean
information is lost and projectively distorted, which makes
action recognition rather challenging, especially for varying
viewpoints. Another source of challenge is the irregularities
of human actions due to a variety of factors such as age,
gender, circumstances, etc. The timeline of action is another
important issue in action recognition. The execution
rates of the same action in different videos may vary due
to different actors or variable camera frame rates. Therefore,
the mapping between same actions in different videos
is usually highly non-linear.
Related papers:
- Nazim Ashraf, Yuping Shen and Hassan Foroosh, View-Invariant Action Recognition Using Rank Constraint, International Conference on Pattern Recognition (ICPR), to appear, 2010.
- Yuping Shen, Nazim Ashraf, and Hassan Foroosh, Action Recognition
based on Homography Constraints, International Conference on Pattern
Recognition (ICPR), 2008. - Best
Scientific Paper Award - (PDF)
|