Stochastic Filtering for Motion Trajectory in Image Sequences Using a Monte Carlo Filter with Estimation of Hyper-Parameters
نویسنده
چکیده
False matching due to errors in feature extraction and changes in illumination between frames may occur in feature tracking in image sequences. False matching leads to outliers in feature motion trajectory. One way of reducing the effect of outliers is stochastic filtering using a state space model for motion trajectory. Hyper-parameters in the state space model, e.g., variances of noise distributions, must be determined appropriately to control tracking motion and outlier rejection properly. Likelihood can be used to estimate hyper-parameters, but it is difficult to apply online tracking due to computational cost. To estimate hyper-parameters online, we include hyper-parameters in state vector and estimate feature coordinates and hyperparameters simultaneously. A Monte Carlo filter is used in state estimation, because adding hyper-parameters to state vector makes state space model nonlinear. Experimental results using synthetic data show that the proposed method can estimate appropriate hyper-parameters for tracking motion and reducing the effect of outliers.
منابع مشابه
3-D head pose estimation from video by nonlinear stochastic particle filtering
Current methods for automatic facial expression recognition assume images are collected in controlled environments in which the subjects deliberately face the camera. Since people often nod or turn their heads, automatic recognition of spontaneous facial behavior requires methods for handling out-of-image-plane head rotations. We approached this problem by developing a front-end system that joi...
متن کاملA PRACTICAL APPROACH TO REAL-TIME DYNAMIC BACKGROUND GENERATION BASED ON A TEMPORAL MEDIAN FILTER
In many computer vision applications, segmenting and extraction of moving objects in video sequences is an essential task. Background subtraction, by which each input image is subtracted from the reference image, has often been used for this purpose. In this paper, we offer a novel background-subtraction technique for real-time dynamic background generation using color images that are taken fro...
متن کاملAn Adaptive Hierarchical Method Based on Wavelet and Adaptive Filtering for MRI Denoising
MRI is one of the most powerful techniques to study the internal structure of the body. MRI image quality is affected by various noises. Noises in MRI are usually thermal and mainly due to the motion of charged particles in the coil. Noise in MRI images also cause a limitation in the study of visual images as well as computer analysis of the images. In this paper, first, it is proved that proba...
متن کاملComparison of Sequential Monte Carlo Filtering with Kalman Filtering for Nonlinear State Estimation
In this paper different filtering techniques for nonlinear state estimation are explored and compared. We distinguish between approaches that approximate the nonlinear function (extended Kalman filter) and other approaches approximating the distribution of measurements and state (unscented Kalman filter and sequential Monte Carlo filter). The paper is showing both, the algorithms and simulated ...
متن کاملOn Filtering the Noise from the Random Parameters in Monte Carlo Rendering (lo-res pdf)
Monte Carlo (MC) rendering systems can produce spectacular images but are plagued with noise at low sampling rates. In this work, we observe that this noise occurs in regions of the image where the sample values are a direct function of the random parameters used in the Monte Carlo system. Therefore, we propose a way to identify MC noise by estimating this functional relationship from a small n...
متن کامل