The motion history image (MHI) approach is a view-based temporal template method which is simple but robust in representing movements and is widely employed by various research groups for action recognition, motion analysis and other related applications. In this paper, we provide an overview of MHI-based human motion recognition techniques and applications. Since the inception of the MHI template for motion representation, various approaches have been adopted to improve this basic MHI technique. We present all important variants of the MHI method. This paper points some areas for further research based on the MHI method and its variants.

Motion history image: its variants and applications

Frame difference energy image for gait recognition with incomplete silhouettes

Human identification by gait has created a great deal of interest in computer vision community due to its advantage of inconspicuous recognition at a relatively far distance. This paper provides a comprehensive survey of recent developments on gait recognition approaches. The survey emphasizes on three major issues involved in a general gait recognition system, namely gait image representation, feature dimensionality reduction and gait classification. Also, a review of the available public gait datasets is presented. The concluding discussions outline a number of research challenges and provide promising future directions for the field.

/pdf/a-review-of-vision-based-gait-recognition-methods-for-human-3dcnqtrtup.pdf

A Review of Vision-Based Gait Recognition Methods for Human Identification

http://people.csail.mit.edu/wachinger/articles/MedIA-Structural-2012.pdf

Entropy and Laplacian Images: Structural Representations for Multi-Modal Registration

Accurate estimation of Gaussian noise level is of fundamental interest in a wide variety of vision and image processing applications as it is critical to the processing techniques that follow. In this paper, a new effective noise level estimation method is proposed on the basis of the study of singular values of noise-corrupted images. Two novel aspects of this paper address the major challenges in noise estimation: 1) the use of the tail of singular values for noise estimation to alleviate the influence of the signal on the data basis for the noise estimation process and 2) the addition of known noise to estimate the content-dependent parameter, so that the proposed scheme is adaptive to visual signals, thereby enabling a wider application scope of the proposed scheme. The analysis and experiment results demonstrate that the proposed algorithm can reliably infer noise levels and show robust behavior over a wide range of visual content and noise conditions, and that is outperforms relevant existing methods.

Additive White Gaussian Noise Level Estimation in SVD Domain for Images

Affine iterative closest point algorithm for point set registration

In this paper, an improved temporal template called gait history image (GHI) is proposed for human gait representation and recognition. Comparing with other temporal template methods, GHI models gait more comprehensively: Static and dynamic characteristics, as well as spatial and temporal variations, can be represented. The time duration of the GHI template is controlled by a finer period resolution (1/4 of a gait cycle). We use statistical approach to learn the discriminating features from GHIs, and gait recognition experiments were performed on the CASIA and USF gait databases. The methods using GHI template presented better recognition performances than the baseline algorithm and gait energy image (GEI) method.

Gait History Image: A Novel Temporal Template for Gait Recognition

http://lxduan.info/papers/LiuSignalProcessing2014.pdf

Fast communication: Hybrid constraint SVR for facial age estimation

Face recognition under variable pose and illumination is a challenging problem in computer vision tasks. In this paper, we solve this problem by proposing a new residual based deep face reconstruction neural network to extract discriminative pose-and-illumination-invariant (PII) features. Our deep model can change arbitrary pose and illumination face images to the frontal view with standard illumination. We propose a new triplet-loss training method instead of Euclidean loss to optimize our model, which has two advantages: a) The training triplets can be easily augmented by freely choosing combinations of labeled face images, in this way, overfitting can be avoided; b) The triplet-loss training makes the PII features more discriminative even when training samples have similar appearance. By using our PII features, we achieve 83.8% average recognition accuracy on MultiPIE face dataset which is competitive to the state-of-the-art face recognition methods.

Jianyi Liu

Papers

Affine iterative closest point algorithm for point set registration

Gait History Image: A Novel Temporal Template for Gait Recognition

Fast communication: Hybrid constraint SVR for facial age estimation

Pose-and-illumination-invariant face representation via a triplet-loss trained deep reconstruction model

Silhouette quality quantification for gait sequence analysis and recognition