Finding periodicity in space and time

Liu, F.; Picard, Rosalind W.

doi:10.1109/iccv.1998.710746

Cited by 96 publications

(61 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, we attempted to extract the distribution of the various frequencies included in the motion of every part of a walking body. Our proposed approach creates 3D spatio-temporal volume from an image sequence, which is similar to Niyogi's [6] and Liu's [9] methods. Spatio-temporal volume data, here called gait volume, contain information not only of spatial individuality such as features of the torso and face, but also the movement of the body with its unique rhythm.…”

Section: Introductionmentioning

confidence: 99%

“…Little and Boyd [8] recognized individuals by frequencies and phases computed by extracting optical flows. Liu and Picard [9] used a spatio-temporal volume and detected the periodicity in a motion by 1D Fourier analysis for each pixel of the image. BenAbdelkader et al [10] used self-similarity plots, in which each pixel had correlations with the frames of an image sequence.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Matching Gait Image Sequences in the Frequency Domain for Tracking People at a Distance

Sagawa

Makihara

Echigo

et al. 2006

Computer Vision – ACCV 2006

View full text Add to dashboard Cite

Abstract. This paper describes a new method to track people walking by matching their gait image sequences in the frequency domain. When a person walks at a distance from a camera, that person often appears and disappears due to being occluded by other people and/or objects, or by going out of the field of view. Therefore, it is important to track the person by taking correspondence of the image sequences between before and after the disappearance. In the case of tracking, the computational time is more crucial factor than that in the case of identification. We create a three-dimensional volume by piling up an image sequence of human walking. After using Fourier analysis to extract the frequency characteristics of the volume, our method computes the similarity of two volumes. We propose a method to compute their correlation of the amplitude of the principal frequencies to improve the cost of comparison. Finally, we experimentally test our method and validate that the amplitude of principal frequencies and spatial information are important to discriminate gait image sequences.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Matching Gait Image Sequences in the Frequency Domain for Tracking People at a Distance

Sagawa

Makihara

Echigo

et al. 2006

Computer Vision – ACCV 2006

View full text Add to dashboard Cite

show abstract

“…In [22], Liu and Picard, presented an algorithm for simultaneous detection, segmentation, and characterization of spatiotemporal periodicity. The algorithm may be applied to find the periodicity in the images which can be used for the object detection and classification.…”

Section: Appearance Based Gait Recognitionmentioning

confidence: 99%

Human Gait Recognition a Review

2018

IJAERD

View full text Add to dashboard Cite

Abstract--The I. INTRODUCTIONHuman recognition by gait was motivated by the psychological studies of the motion perception by Johansson [1]. Johansson used Moving Light Display (MLD) to study the motion perception. Light bulbs were attached to the person"s joints in MLD experiments. Subjects were then filmed performing different types of motion activity such as dancing, walking and running in dark background. These films only show the collection of bright spots in a two dimensional plane and carry no structural information because the bright spots were not connected. The images of the bright spots were shown to different observers and it was noted that these scattered spots were meaningless to them. But when the films were played, the movement of the spots created impressions of a person walking, dancing and running etc. This shows that the relative movements of certain joints in the human body carry information about personal walking styles and dynamics. The position of light bulbs and corresponding point display is shown in Figure 1 for walking and running movement. It was also noted that the familiarity of an observer with a particular type of motion plays an important role in its recognition. The inverted MLDs were not recognized by observers as a walking or dancing pattern. Figure 1. Contours of (a) Walking and (b) Running subject with point configuration.

show abstract

“…stride) [11], spatio-temporal patterns [28], and HMMs [9]. With no part tracking, a different approach is to use spatio-temporal templates derived from the image sequence directly, including generic layered templates [6] and other periodic template representations [10,25,26,30].…”

Section: Related Work On Action Recognitionmentioning

confidence: 99%

Minimal-latency human action recognition using reliable-inference

Davis

Tyagi

2006

Image and Vision Computing

View full text Add to dashboard Cite

We present a probabilistic reliable-inference framework to address the issue of rapid detection of human actions with low error rates. The approach determines the shortest video exposures needed for low-latency recognition by sequentially evaluating a series of posterior ratios for different action classes. If a subsequence is deemed unreliable or confusing, additional video frames are incorporated until a reliable classification to a particular action can be made. Results are presented for multiple action classes and subsequence durations, and are compared to alternative probabilistic approaches. The framework provides a means to accurately classify human actions using the least amount of temporal information. q

show abstract

Finding periodicity in space and time

Cited by 96 publications

References 8 publications

Matching Gait Image Sequences in the Frequency Domain for Tracking People at a Distance

Matching Gait Image Sequences in the Frequency Domain for Tracking People at a Distance

Human Gait Recognition a Review

Minimal-latency human action recognition using reliable-inference

Contact Info

Product

Resources

About