Recognition and velocity computation of large moving objects in images

Mahmoud, Sabri A.; Afifi, M.; Green, R.J.

doi:10.1109/29.9020

Cited by 29 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The objective is the determination of the accelerated-motion planes expressed by (11), using the 3-D data points in (12). For this reason, we use a variant of the proposed clustering strategy described in [9].…”

Section: B Estimating Accelerated Motion Planes Using Fuzzy C-planesmentioning

confidence: 99%

“…4) Generally Varying Motions: Long, real video sequences are expected to be governed by more general time-varying motions than the accelerated motion. Yet, the violation of our model can be avoided, dividing long image sequences into shorter (overlapping or not) subsequences, where the motion can be plausibly approximated as accelerated, exactly as in time-constant models [8]- [12], where it is assumed that for small time scales the motion is well approximated as constant. However, we expect that in the case of relatively fast time-varying motion, the linear (accelerated) model can robustly produce more accurate results than the constant model, for the following reasons.…”

Section: Additional Issuesmentioning

confidence: 99%

“…2) Fuzzy Fitting: In our methodology, the described probabilistic FCP is applied only to the frequency data points of (12). The points are indirectly grouped by clustering initially , given that each point is paired with a point .…”

Section: B Estimating Accelerated Motion Planes Using Fuzzy C-planesmentioning

confidence: 99%

See 2 more Smart Citations

Estimation of Multiple Accelerated Motions Using Chirp-Fourier Transform and Clustering

Alexiadis

Sergiadis

2007

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Motion estimation in the spatiotemporal domain has been extensively studied and many methodologies have been proposed, which, however, cannot handle both time-varying and multiple motions. Extending previously published ideas, we present an efficient method for estimating multiple, linearly time-varying motions. It is shown that the estimation of accelerated motions is equivalent to the parameter estimation of superpositioned chirp signals. From this viewpoint, one can exploit established signal processing tools such as the chirp-Fourier transform. It is shown that accelerated motion results in energy concentration along planes in the 4-D space: spatial frequencies-temporal frequency-chirp rate. Using fuzzy c-planes clustering, we estimate the plane/motion parameters. The effectiveness of our method is verified on both synthetic as well as real sequences and its advantages are highlighted.

show abstract

Section: B Estimating Accelerated Motion Planes Using Fuzzy C-planesmentioning

confidence: 99%

Section: Additional Issuesmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of Multiple Accelerated Motions Using Chirp-Fourier Transform and Clustering

Alexiadis

Sergiadis

2007

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Moving objects analysis in consecutive video frames denotes to apply specific algorithms to achieve object identification plus to compute objects velocities [1] [3]. Object identification denotes to detect an object among others within a surrounding background (BG) in order to create a foreground (FG) pixel map, then to apply some specific algorithm to extract the features of each of them [2].…”

Section: Introductionmentioning

confidence: 99%

“…Gradientbased methods compute velocity by using spatial and temporal derivatives of image intensity function depending on the optical flow field. Whereas correlation-based methods try to establish correspondences between object points across successive frames aiming to estimate motion [3].…”

Section: Introductionmentioning

confidence: 99%

Modified dynamic threshold system with DFT multifarious motion analysis

Al-Sudani

2010

2010 Second International Conference on Computing, Communication and Networking Technologies

View full text Add to dashboard Cite

This paper is concerned with investigat-ing, experiencing, and validating a dynamic threshold system with multifarious motion analysis. The motivation here is to introduce a method for analyzing moving objects in outdoor/indoor video frames with respect to: movement detection, objects segmentation, features extraction besides DFT-based velocity computation. The underlying methodology believes in cross-fertilizing the two independent segmentation approaches of back-ground subtraction and temporal frames differencing through a single correlation exhibiting the behavioral-mathematical model of the examined image sequences. This has been interpreted through identifying the image as time-varying functions applicable for processing through 2D Discrete Fourier Transform (DFT). The justification of this method has been revealed through output data, human visual perceptual inspection, plus histogramming; showing appreciable accuracy, lower level of noise, and shorter segmentation time in comparison with some availa-ble standard techniques. The horizon of applications of the presented method may involve: security control, industry and traffic control, athletic and dancing performance evaluation, surveillance, and general civil and military fields.

show abstract

Use of fourier and hartley transforms in motion estimation: A comparative study

Mahmoud

1991

Int J Imaging Syst Tech

View full text Add to dashboard Cite

A comparison between the use of Fourier and Hartley transforms for motion estimation of multiple moving objects in image sequences is presented. The spectrum of the two transforms show that the temporal frequencies at the peaks (of the spectrum) is related to the velocity of the moving objects. The analysis shows that the Hartley technique is faster and requires less memory space than the Fourier technique. However, it gives the velocity of the moving objects but not the direction. The Fourier spectrum, on the other hand, gives the velocity and direction. An efficient implementation is possible by using the Hartley transform to estimate the temporal frequencies of the peaks and hence the velocities. The fast Fourier transform is then used to compute the spectrum at those peaks. The direction is easily found from the Fourier spectrum by reversing the sign of the temporal frequency corresponding to the peak.

show abstract

Recognition and velocity computation of large moving objects in images

Cited by 29 publications

References 10 publications

Estimation of Multiple Accelerated Motions Using Chirp-Fourier Transform and Clustering

Estimation of Multiple Accelerated Motions Using Chirp-Fourier Transform and Clustering

Modified dynamic threshold system with DFT multifarious motion analysis

Use of fourier and hartley transforms in motion estimation: A comparative study

Contact Info

Product

Resources

About