An improved procedure for the extraction of temporal motion strength signals from video recordings of neonatal seizures

Authors:
Nicolaos B. Karayiannis;Guozhi Tao
Affiliations:
Department of Electrical and Computer Engineering, University of Houston, N308 Engineering Building 1, Houston, TX 77204-4005, USA;Department of Electrical and Computer Engineering, University of Houston, N308 Engineering Building 1, Houston, TX 77204-4005, USA
Venue:
Image and Vision Computing
Year:
2006

Citing 5
Cited 2

Feature selection for pattern classification with Gaussian mixture models: a new objective criterion

Pattern Recognition Letters
A noise robust method for 2D shape estimation of moving objects in video sequences considering a moving camera

Signal Processing - Video segmentation for content-based processing manipulation
Spatio-temporal segmentation based on motion and static segmentation

ICIP '95 Proceedings of the 1995 International Conference on Image Processing (Vol. 1)-Volume 1 - Volume 1
Quantifying motion in video recordings of neonatal seizures by regularized optical flow methods

IEEE Transactions on Image Processing
Spatio-temporal video segmentation using a joint similarity measure

IEEE Transactions on Circuits and Systems for Video Technology

Joint wavelet video denoising and motion activity detection in multimodal human activity analysis: application to video-assisted bioacoustic/psychophysiological monitoring

EURASIP Journal on Advances in Signal Processing
Vision-based motion detection, analysis and recognition of epileptic seizures-A systematic review

Computer Methods and Programs in Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a procedure developed to extract quantitative motion information from video recordings of neonatal seizures in the form of temporal motion strength signals. Temporal motion strength signals are obtained from a sequence of video frames by measuring the displacement areas of the infants' moving body part(s) from frame to frame of the video sequence. The proposed motion segmentation procedure relies on the application of non-linear filtering, vector clustering, and morphological filtering to the differences between adjacent frames. The experiments indicate that temporal motion strength signals constitute a satisfactory representation of videotaped clinical events and may be used for automated seizure recognition.