Open AccessProceedings Article
Recognizing activities
R. Polana,R. Nelson +1 more
- 01 Jan 1994
TL;DR: A general computational method for recognizing repetitive movements characteristic of walking people, galloping horses, or flying birds in real image sequences is demonstrated using what is essentially template matching in a motion feature space coupled with a technique for detecting and normalizing periodic activities.
read more
Abstract: The recognition of repetitive movements characteristic of walking people, galloping horses, or flying birds is a routine function of the human visual system. It has been demonstrated that humans can recognize such activity solely on the basis of motion information. We demonstrate a general computational method for recognizing such movements in real image sequences using what is essentially template matching in a motion feature space coupled with a technique for detecting and normalizing periodic activities. This contrasts with earlier model-based approaches for recognizing such activities.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Low level recognition of human motion (or how to get your man without finding his body parts)
R. Polana,Randal C. Nelson +1 more
- 11 Nov 1994
TL;DR: It is demonstrated that repetitive motion is such a strong cue, that the moving actor can be segmented, normalized spatially and temporally, and recognized by matching against a spatiotemporal template of motion features.
View-based interpretation of real-time optical flow for gesture recognition
Ross Cutler,Matthew Turk +1 more
- 14 Apr 1998
TL;DR: The authors have developed a real-time, view-based gesture recognition system that has been applied to create an interactive environment for children.
285
Human activity recognition using multidimensional indexing
TL;DR: A novel method for view-based recognition of human action/activity from videos that uses a sequence-based voting approach to recognize the activity invariant to the activity speed and finds that the probability of false alarm drops exponentially with the increased number of sampled body poses.
Ghost: a human body part labeling system using silhouettes
Ismail Haritaoglu,David Harwood,Larry S. Davis +2 more
- 16 Aug 1998
TL;DR: Experimental results demonstrate robustness and real-time performance of the proposed algorithm.
261
Model based extraction of articulated objects in image sequences for gait analysis
D. Meyer,Joachim Denzler,Heinrich Niemann +2 more
- 26 Oct 1997
TL;DR: This paper describes an approach to the extraction of articulated objects which will be used for gait analysis, and monotony operators which compute the displacement vector field are used to initialize a contour based tracking algorithm called active rays-for several body parts which are important for gact analysis.
139
References
Visual perception of biological motion and a model for its analysis
TL;DR: The kinetic-geometric model for visual vector analysis originally developed in the study of perception of motion combinations of the mechanical type was applied to biological motion patterns and the results turned out to be highly positive.
Change Detection and Tracking Using Pyramid Transform Techniques
Charles H. Anderson,Peter J. Burt,G. van der Wal +2 more
- 11 Dec 1985
TL;DR: A pyramid based image preprocessor has been constructed that can compute frequency tuned "change energy" measures in real time and follows a foveal search strategy to isolate moving objects for tracking or for more detailed analysis.
193
Recognition of motion from temporal texture
R. Polana,Randal C. Nelson +1 more
- 15 Jun 1992
TL;DR: It is shown that certain statistical spatial and temporal features that can be derived from approximations to the motion field have invariant properties, and can be used to classify regional activities such as windblown trees, ripples on water, or chaotic fluid flow, that are characterized by complex, non-rigid motion.
79
Cyclic motion detection using spatiotemporal surfaces and curves
M. Allmen,Charles R. Dyer +1 more
- 16 Jun 1990
TL;DR: The successful detection of cyclic motion in two data sets is presented and curvature scale-space of the ST curves is used to detect intervals of repeating curvature values.
The trajectory primal sketch: a multi-scale scheme for representing motion characteristics
K. Gould,Mubarak Shah +1 more
- 04 Jun 1989
TL;DR: A different approach is proposed for the use of motion in a computer vision system which uses the motion characteristics of moving objects without actually recovering the structure, and the extended trajectories followed by the objects are considered.
59