Gaussian Mixture Model based Video Modeling
نویسنده
چکیده
In this project report, we have investigated the video modeling techniques and realized a statistical video representation and modeling scheme [1], which could be used for later video retrieval and content extraction task. This method utilizes Gaussian mixture model (GMM) to segment video content into coherent space-time segments within the video frames and across frames. It treats space and time uniformly and analyzes the video input as a single entity, which is called global GMM in the report. Then this global space-time video representation scheme is extended to a piecewise GMM framework. A succession of Gaussian mixture models are extracted for the video sequence, instead of a single global model for the entire sequence. This piecewise GMM framework can conquer the disadvantage of global GMM for describing nonlinear and non-convex motion patterns. The extracted space-time regions could detect and recognize video events, and also could implement retrieval in the parameter space given a video database. Experimental results show that this method can segment video content into homogeneous regions, but the result are different for different videos and still has some problems for real application.
منابع مشابه
Traffic Video Segmentation Using Adaptive-K Gaussian Mixture Model
Video segmentation is an important phase in video based traffic surveillance applications. The basic task of traffic video segmentation is to classify pixels in the current frame to road background or moving vehicles, and casting shadows should be taken into account if exists. In this paper, a modified online EM procedure is proposed to construct Adaptive-K Gaussian Mixture Model (AKGMM) in whi...
متن کاملA Background Modeling Algorithm Based on Improved Adaptive Mixture Gaussian
For better background modeling in scenes with nonstationary background, a background modeling algorithm based on adaptive parameter adjustment of the Mixture Gaussian is proposed. Mixture Gaussians is applied to learn the distribution of per-pixel in the temporal domain and to control adaptive adjustment of number K of Gaussian components through in increasing, deleting or merging similar Gauss...
متن کاملUnsupervised Posture Modeling and Recognition based on Gaussian Mixture Model and EM Estimation
In this paper, we proposed an unsupervised posture modeling method based on Gaussian Mixture Model (GMM). Specifically, each learning posture is described based on its movement features by a set of spatial-temporal interest points (STIPs), salient postures are then clustered from these training samples by an unsupervised algorithm, here we give the comparison of four candidate classification me...
متن کاملSpeech Enhancement using Laplacian Mixture Model under Signal Presence Uncertainty
In this paper an estimator for speech enhancement based on Laplacian Mixture Model has been proposed. The proposed method, estimates the complex DFT coefficients of clean speech from noisy speech using the MMSE estimator, when the clean speech DFT coefficients are supposed mixture of Laplacians and the DFT coefficients of noise are assumed zero-mean Gaussian distribution. Furthermore, the MMS...
متن کاملEvaluation and Application of the Gaussian-Log Gaussian Spatial Model for Robust Bayesian Prediction of Tehran Air Pollution Data
Air pollution is one of the major problems of Tehran metropolis. Regarding the fact that Tehran is surrounded by Alborz Mountains from three sides, the pollution due to the cars traffic and other polluting means causes the pollutants to be trapped in the city and have no exit without appropriate wind guff. Carbon monoxide (CO) is one of the most important sources of pollution in Tehran air. The...
متن کامل