This article deals with the problem of classification of human activities from video. Our approach uses motion features that are computed very efficiently, and subsequently projected into a lower dimensional space where matching is performed. Each action is represented as a manifold in this lower dimensional space and matching is done by comparing these manifolds. To demonstrate the effectiveness of this approach, it was used on a large data set of similar actions, each performed by many different actors. Classification results were very accurate and show that this approach is robust to challenges such as variations in performers ’ physical attributes, color of clothing, and style of motion. An important result of this article is that the recovery of the three-dimensional properties of a moving person, or even the two-dimensional tracking of the person’s limbs need not precede action recognition.
|
1744
|
Eigenfaces for Recognition
– Turk, Pentland
- 1991
|
|
739
|
Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection,” Proc
– Belhumeur, Hespanha, et al.
- 1997
|
|
720
|
Pfinder: Realtime tracking of the human body
– Wren, Azarbayejani, et al.
- 1997
|
|
310
|
The Visual Analysis of Human Movement: A Survey
– Gavrila
- 1999
|
|
263
|
Using discriminant eigenfeatures for image retrieval
– Swets, Weng
- 1996
|
|
261
|
Tracking People with Twists and Exponential Maps
– Bregler, Malik
- 1998
|
|
217
|
Learning and Recognizing Human Dynamics in Video Sequences
– Bregler
- 1997
|
|
216
|
3-D Model-Based Tracking of Humans in Action: A Multi-View Approach
– Gavrila, Davis
|
|
187
|
Visual perception of biological motion and a model for its analysis
– Johansson
- 1973
|
|
166
|
Recognizing human action in time-sequential images using hidden Markov model
– Yamato, Ohya, et al.
- 1992
|
|
134
|
Cardboard People: A parameterized Model of Articulated Image Motion
– Ju, Black, et al.
- 1996
|
|
110
|
Parameterized Modeling and Recognition of Activities
– Yacoob, Black
- 1998
|
|
98
|
Recognition of Human Body Motion Using Phase Space Constraints
– Campbell, Bobick
- 1995
|
|
87
|
Real-time selfcalibrating stereo person tracking using 3-D shape estimation from blob features
– Azarbayejani, Pentland
- 1996
|
|
79
|
The representation and recognition of human movement using temporal templates
– Davis, Bobick
- 1997
|
|
79
|
Detecting activities
– Polana, Nelson
- 1994
|
|
67
|
Motion-Based Recognition: A Survey
– Cedras, Shah
- 1995
|
|
61
|
Real-time 100 object recognition system
– Nayar, Nene, et al.
- 1996
|
|
60
|
Image Sequence Analysis of Real World Human Motion
– Akita
- 1984
|
|
57
|
Recognizing friends by their walk:gait perception without familiarity cues
– Cutting, Kozlowski
- 1977
|
|
54
|
Visiual motion perception
– Johansson
- 1975
|
|
51
|
Detection and recognition of periodic, nonrigid motion
– Polana, Nelson
- 1997
|
|
35
|
Tracking Human Motion Using Multiple Cameras
– Cai, Aggarwal
- 1996
|
|
33
|
Understanding human motion patterns
– Guo, Xu, et al.
|
|
33
|
Recognizing the sex of a walker from dynamic point-light display
– Kozlowski, Cutting
- 1977
|
|
27
|
Human gait recognition in canonical space using temporal templates
– Huang, Harris, et al.
- 1999
|
|
21
|
Matching motion trajectories using scale-space
– Rangarajan, Allen, et al.
- 1993
|
|
19
|
Impact of dynamic model learning on the classification of human motion
– Pavlovic, Rehg
- 2000
|
|
17
|
Motion-based recognition of people in eigengait space, in: Automatic Face and Gesture Recognition 2002
– Ben-Abdelkader, Cutler, et al.
- 2002
|
|
17
|
Action categories and the perception of biological motion
– Dittrich
- 1993
|
|
17
|
Motion of Disturbances: Detection and Tracking of Multi-Body Non-Rigid Motion
– Havely, Weinshall
- 1997
|
|
15
|
Incremental model-based discrimination of articulated movement direct from motion features
– Goddard
- 1994
|
|
14
|
Analysis of Human Motion: A Model-Based Approach
– Wang, Lorette, et al.
- 1991
|
|
9
|
Towards a unified framework for tracking and analysis of human motion
– Krahnstover, Yeasin, et al.
- 2001
|
|
7
|
A novel method for tracking and counting pedestrians in real-time using a single camera
– Masoud, Papanikolopoulos
- 2001
|
|
5
|
Rehg.: Reconstruction of 3D figure motion from 2D correspondences
– DiFranco, Cham, et al.
- 2001
|
|
5
|
Tracking and Analysis of Articulated Motion with an Application to Human Motion,” Doctoral Thesis
– Masoud
- 2000
|
|
1
|
New area based metrics for automatic gate recognition
– Foster, Nixon, et al.
|
