A dynamic conditional random field model for foreground and shadow segmentation.

This paper proposes a dynamic conditional random field (DCRF) model for foreground object and moving shadow segmentation in indoor video scenes. Given an image sequence, temporal dependencies of consecutive segmentation fields and spatial dependencies within each segmentation field are unified by a dynamic probabilistic framework based on the conditional random field (CRF). An efficient approximate filtering algorithm is derived for the DCRF model to recursively estimate the segmentation field from the history of observed images. The foreground and shadow segmentation method integrates both intensity and gradient features. Moreover, models of background, shadow, and gradient information are updated adaptively for nonstationary background processes. Experimental results show that the proposed approach can accurately detect moving objects and their cast shadows even in monocular grayscale video sequences.

Spatiotemporal video segmentation based on graphical models.

This paper proposes a probabilistic framework for spatiotemporal segmentation of video sequences. Motion information, boundary information from intensity segmentation, and spatial connectivity of segmentation are unified in the video segmentation process by means of graphical models. A Bayesian network is presented to model interactions among the motion vector field, the intensity segmentation field, and the video segmentation field. The notion of the Markov random field is used to encourage the formation of continuous regions. Given consecutive frames, the conditional joint probability density of the three fields is maximized in an iterative way. To effectively utilize boundary information from the intensity segmentation, distance transformation is employed in local objective functions. Experimental results show that the method is robust and generates spatiotemporally coherent segmentation results. Moreover, the proposed video segmentation approach can be viewed as the compromise of previous motion based approaches and region merging approaches.

Effective learning in recurrent max-min neural networks.

Max and min operations have interesting properties that facilitate the exchange of information between the symbolic and real-valued domains. As such, neural networks that employ max-min activation functions have been a subject of interest in recent years. Since max-min functions are not strictly differentiable, we propose a mathematically sound learning method based on using Fourier convergence analysis of side-derivatives to derive a gradient descent technique for max-min error functions. We then propose a novel recurrent max-min neural network model that is trained to perform grammatical inference as an application example. Comparisons made between this model and recurrent sigmoidal neural networks show that our model not only performs better in terms of learning speed and generalization, but that its final weight configuration allows a deterministic finite automation (DFA) to be extracted in a straightforward manner. In essence, we are able to demonstrate that our proposed gradient descent technique does allow max-min neural networks to learn effectively.