Motion estimation, segmentation and separation, using hypercomplex phase correlation, clustering techniques and graph-based optimization

Alexiadis, Dimitrios S.; Sergiadis, George D.

doi:10.1016/j.cviu.2008.08.013

Cited by 12 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another techniques for segmenting motion using parametric and nonparametric machine learning approaches can be found in [23], [3]. Alexiadis and Sergiadis (2009) [1] use a weighted fuzzy c-means clustering procedure to obtain the velocity estimates for color sequences. Bugeau and Peréz (2008) [7] use a thermal infrared camera mounted on an autonomous mobile robot to a human detection application.…”

Section: Related Workmentioning

confidence: 99%

An architecture for visual motion perception of a surveillance-based autonomous robot

Pinto

Costa

Moreira

2014

2014 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)

View full text Add to dashboard Cite

This research presents an innovative mobile robotic system designed for active surveillance operations. This mobile robot moves along a rail and is equipped with a monocular camera. Thus, it enhances the surveillance capability when compared to conventional systems (mainly composed by multiple static cameras). In addition, the paper proposes a technique for multi-object tracking called MTMP (Multi-Tracking of Motion Profiles). The MTMP resorts to a formulation based on the Kalman filter and tracks several moving objects using motion profiles. A motion profile is characterized by the dominant flow vector and is computed using the optical flow signature with removal of outliers. A similarity measure based on the Mahalanobis distance is used by the MTMP for associating the moving objects over frames. The experiments conducted in realistic environments have proved that the static perception mode of the proposed robot is able to detect and track multiple moving objects in a short period of time and without using specialized computers. In addition, the MTMP exhibits a good computational performance since it takes less than 5 milliseconds to compute. Therefore, results show that the estimation of motion profiles is suitable for analyzing motion on image sequences.

show abstract

Section: Related Workmentioning

confidence: 99%

An architecture for visual motion perception of a surveillance-based autonomous robot

Pinto

Costa

Moreira

2014

2014 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)

View full text Add to dashboard Cite

show abstract

“…The fractional phase correlation function is a generalization of the phase correlation function [7], and both functions can determine the measure of image similarity. The phase correlation method can be used in the various problems of image processing like image registration [8], image mosaicking [9], biometrics [10], [11], motion estimation [12], [13], etc. If two images are similar to each other, then the phase correlation function has a strong peak.…”

Section: Introductionmentioning

confidence: 99%

Fractional Fourier Transform Phase for Image Matching

Protsenko

Pavelyeva

2022

Proceedings of the 32nd International Conference on Computer Graphics and Vision

View full text Add to dashboard Cite

Fractional Fourier transform is the generalization of the Fourier transform. In this article the synthesis of phase and magnitude of fractional Fourier transform is demonstrated. The influence of phase and magnitude on the synthesis results is shown. The fractional phase correlation function using fractional Fourier transform is calculated, and it is used for image matching. The use of fractional phase correlation can achieve better results compared to the use of the classical phase correlation. The comparison between phase correlation and fractional phase correlation for biometric iris images is given. The selection of optimal parameter for fractional phase correlation is proposed.

show abstract

“…Such as, quaternionic Gabor filters are designed to combine the color channels and the orientations in the image plane [6]. Quaternionic phase correlation based motion estimation approach is studied [5].…”

Section: Hypercomplex Numbermentioning

confidence: 99%

“…The relationship between right-side quaternion Fourier transform and left-side quaternion Fourier transform is established [4]. Based on hypercomplex Fourier transform, effective algorithms for motion estimation in color image sequences are studied [5]. Quaternionic Gabor filters are designed to combine the color channels and the orientations in the image plane [6].…”

Section: Introductionmentioning

confidence: 99%

Fast Hypercomplex Polar Fourier Analysis for Image Processing

Yang

Kamata

2011

Advances in Image and Video Technology

View full text Add to dashboard Cite

Abstract. Hypercomplex polar Fourier analysis treats a signal as a vector field and generalizes the conventional polar Fourier analysis. It can handle signals represented by hypercomplex numbers such as color images. It is reversible that can reconstruct image. Its coefficient has rotation invariance property that can be used for feature extraction. With these properties, it can be used for image processing applications like image representation and image understanding. However in order to increase the computation speed, fast algorithm is needed especially for image processing applications like realtime systems and limited resource platforms. This paper presents fast hypercomplex polar Fourier analysis that based on symmetric properties and mathematical properties of trigonometric functions. Proposed fast hypercomplex polar Fourier analysis computes symmetric eight points simultaneously that significantly reduce the computation time.

show abstract

Motion estimation, segmentation and separation, using hypercomplex phase correlation, clustering techniques and graph-based optimization

Cited by 12 publications

References 29 publications

An architecture for visual motion perception of a surveillance-based autonomous robot

An architecture for visual motion perception of a surveillance-based autonomous robot

Fractional Fourier Transform Phase for Image Matching

Fast Hypercomplex Polar Fourier Analysis for Image Processing

Contact Info

Product

Resources

About