Training Video Sequences Research Articles

A lattice-based neuro-computing methodology for real-time human action recognition

This work describes a computational approach for a typical machine-vision application, that of human action recognition from video streams. We present a method that has the following advantages: (a) no human intervention in pre-processing stages, (b) a reduced feature set, (c) modularity of the recognition system and (d) control of the model’s complexity in acceptable for real-time operation levels. Representation of each video frame and feature extraction procedure are formulated in the lattice theory context. The recognition system consists of two components: an ensemble of neural network predictors which correspond to the training video sequences and one classifier, based on the PREMONN approach, capable of deciding at each time instant which known video source has potentially generated a new sequence of frames. Extensive experimental study on three well known benchmarks validates the flexibility and robustness of the proposed approach.

환경에 적응적인 얼굴 추적 및 인식 방법

ABSTRACT Face tracking and recognition are difficult problems because the face is a non-rigid object. The main reasons for the failure to track and recognize the faces are the changes of a face pose and environmental illumination. To solve these problems, we propose a nonlinear manifold framework for the face pose and the face illumination normalization processing. Specifically, to track and recognize a face on the video that has various pose variations, we approximate a face pose density to single Gaussian density by PCA(Principle Component Analysis) using images sampled from training video sequences and then construct the GMM(Gaussian Mixture Model) for each person. To solve the illumination problem for the face tracking and recognition, we decompose the face images into the reflectance and the illuminance using the SSR(Single Scale Retinex) model. To obtain the normalized reflectance, the reflectance is rescaled by histogram equalization on the defined range. We newly approximate the illuminance by the trained manifold since the illuminance has almost variations by illumination. By combining these two features into our manifold framework, we derived the efficient face tracking and recognition results on indoor and outdoor video. To improve the video based tracking results, we update the weights of each face pose density at each frame by the tracking result at the previous frame using EM algorithm. Our experimental results show that our method is more efficient than other methods.Keywords:Face recognition, Face tracking, Manifold, Retinex

A pose-wise linear illumination manifold model for face recognition using video

The objective of this work is to recognize faces using video sequences both for training and novel input, in a realistic, unconstrained setup in which lighting, pose and user motion pattern have a wide variability and face images are of low resolution. There are three major areas of novelty: (i) illumination generalization is achieved by combining coarse histogram correction with fine illumination manifold-based normalization; (ii) pose robustness is achieved by decomposing each appearance manifold into semantic Gaussian pose clusters, comparing the corresponding clusters and fusing the results using an RBF network; (iii) a fully automatic recognition system based on the proposed method is described and extensively evaluated on 600 head motion video sequences with extreme illumination, pose and motion pattern variation. On this challenging data set our system consistently demonstrated a very high recognition rate (95% on average), significantly outperforming state-of-the-art methods from the literature.

Visual tracking and recognition using probabilistic appearance manifolds

This paper presents an algorithm for modeling, tracking, and recognizing human faces in video sequences within one integrated framework. Conventional video-based face recognition systems have usually been embodied with two independent components: the tracking and recognition modules. In contrast, our algorithm emphasizes an algorithmic architecture that tightly couples these two components within a single framework. This is accomplished through a novel appearance model which is utilized simultaneously by both modules, even with their disparate requirements and functions. The complex nonlinear appearance manifold of each registered person is partitioned into a collection of submanifolds where each models the face appearances of the person in nearby poses. The submanifold is approximated by a low-dimensional linear subspace computed by principal component analysis using images sampled from training video sequences. The connectivity between the submanifolds is modeled as transition probabilities between pairs of submanifolds, and these are learned directly from training video sequences. The integrated task of tracking and recognition is formulated as a maximum a posteriori estimation problem. Within our framework, the tracking and recognition modules are complementary to each other, and the capability and performance of one are enhanced by the other. Our approach contrasts sharply with more rigid conventional approaches in which these two modules work independently and in sequence. We report on a number of experiments and results that demonstrate the robustness, effectiveness, and stability of our algorithm.