Recognition of human actions
Action Database
The current video database containing six
types of human actions (walking, jogging, running, boxing,
hand waving and hand clapping) performed several times by 25 subjects in
four different scenarios: outdoors s1, outdoors with scale variation s2,
outdoors with different clothes s3 and indoors s4 as illustrated below.
Currently the database contains 2391 sequences.
All sequences were taken over homogeneous backgrounds with a static camera
with 25fps frame rate.
The sequences were downsampled to the spatial resolution of 160x120 pixels
and have a length of four seconds in average.
In our experiments reported in
ICPR'04
ICPR'04
all sequences were divided with respect to the subjects into a training set
(8 persons), a validation set (8 persons) and a test set (9 persons).
The classifiers were trained on a training set while the validation set was used
to optimize the parameters of each method.
The recognition results were obtained on the test set.
All sequences are stored using AVI file format and are available on-line (DIVX-compressed version).
Uncompressed version is available on demand.
There are 25x6x4=600 video files for each combination of 25 subjects, 6 actions and 4 scenarios.
Each file contains about four subsequences used as a sequence in our experiments.
The subdivision of each file into sequences in terms start_frame and end_frame
as well as the list of all sequences is given in
Sample sequences for each action (DivX-compressed)
Action database in zip-archives (DivX-compressed)
Note: The database is publicly available for non-commercial use.
Please refer to
[Schuldt, Laptev and Caputo, Proc. ICPR'04, Cambridge, UK ]
if you use this database in your publications.
Related publications
"Recognizing Human Actions: A Local SVM Approach",
Christian Schuldt, Ivan Laptev and Barbara Caputo;
in Proc. ICPR'04, Cambridge, UK.
[Abstract
[Abstract
PDF]
"Local Spatio-Temporal Image Features for Motion Interpretation",
Ivan Laptev;
PhD Thesis, 2004, Computational Vision and
Active Perception Laboratory (CVAP), NADA, KTH, Stockholm
[Abstract,
[Abstract,
PDF]
"Local Descriptors for Spatio-Temporal Recognition",
Ivan Laptev and Tony Lindeberg;
ECCV Workshop "Spatial Coherence for Visual Motion Analysis"
[Abstract,
[Abstract,
PDF]
"Velocity adaptation of space-time interest points",
Ivan Laptev and Tony Lindeberg;
in Proc. ICPR'04, Cambridge, UK.
[Abstract,
[Abstract,
PDF]
"Space-Time Interest Points",
I. Laptev and T. Lindeberg;
in Proc. ICCV'03, Nice, France, pp.I:432-439.
[Abstract,
[Abstract,
PDF]
Contact
Latest update 18-01-2005
nada.kth.se>
Ivan Laptev <laptev