Bayesian Clustering of Optical Flow Fields
نویسندگان
چکیده
We present a method for unsupervised learning of classes of motions in video. We project optical flow fields to a complete, orthogonal, a-priori set of basis functions in a probabilistic fashion, which improves the estimation of the projections by incorporating uncertainties in the flows. We then cluster the projections using a mixture of feature-weighted Gaussians over optical flow fields. The resulting model extracts a concise probabilistic description of the major classes of optical flow present. The method is demonstrated on a video of a person’s facial expressions.
منابع مشابه
Classifying Large-Scale Environment Shapes with Linear Optical Flow Templates
In this paper we deal with classifying coarse, large-scale environment shapes using image motion observed by a moving camera or robot. We apply approximate Bayesian model selection over a set of learned linear optical flow templates to explain the motion between adjacent video frames. Each template is a learned probabilistic model of the flow fields that may be observed in a large-scale environ...
متن کاملIdentifying Flow Units Using an Artificial Neural Network Approach Optimized by the Imperialist Competitive Algorithm
The spatial distribution of petrophysical properties within the reservoirs is one of the most important factors in reservoir characterization. Flow units are the continuous body over a specific reservoir volume within which the geological and petrophysical properties are the same. Accordingly, an accurate prediction of flow units is a major task to achieve a reliable petrophysical description o...
متن کاملClassifying Environment Shape from Image Motion for Mobile Robot Path Following
For a high-speed mobile robot following a road, hallway, or other type of path, modern robot motion controllers must know the coarse shape of the path, such as whether it curves left or right, or on which sides it is bounded by dangerous obstacles such as walls. In this paper, towards addressing the perceptual needs of high-speed mobile robot controllers, we classify these coarse shapes directl...
متن کاملUncertainty Modeling of a Group Tourism Recommendation System Based on Pearson Similarity Criteria, Bayesian Network and Self-Organizing Map Clustering Algorithm
Group tourism is one of the most important tasks in tourist recommender systems. These systems, despite of the potential contradictions among the group's tastes, seek to provide joint suggestions to all members of the group, and propose recommendations that would allow the satisfaction of a group of users rather than individual user satisfaction. Another issue that has received less attention i...
متن کاملVision Data Fusion for Target Tracking
This paper proposes a novel approach and a system for object detection and tracking using video sensors. Optical Flow technique is used to derive the dynamic scene properties from the image sequences captured from stereo CCD cameras. Here, it is proposed to use the K-means clustering algorithm along with a template matching algorithm to identify the target from the 2D optical flow fields. Visua...
متن کامل