Unified framework for human behaviour recognition: An approach using 3D Zernike moments
نویسندگان
چکیده
In this paper, we present a unified framework for the analysis of video databases by using Markov spatio-temporal random walks on graph. The framework provides an efficient approach for both clustering, data organization, dimension reduction and recognition. The aim is to develop a visionbased approach for human behaviour recognition. Our contribution lies in three aspects. First, we employ 3D Zernike moments to encode the object of interest in a video clip. Then, we propose a new method to represent the video database as a weighted undirected graph where each vertex is a video clip. The weight of an edge between two video clips is defined by a Gaussian kernel on their 3D Zernike moments and their respective neighbourhoods in the feature space. Our objective is to obtain a robust low-dimensional space through spectral graph embedding which provides efficient keypoints Corresponding author : [email protected] Email addresses: [email protected] (A. Bouziane ), [email protected] (Y. Chahir), [email protected] (M. Molina), [email protected] (F. Jouen) Preprint submitted to Neurocomputing September 28, 2011 transcription into an euclidean manifold, and allows to achieve higher classification accuracy through agglomerative categorization. Finally, we describe a variational framework for manifold denoising based on p-Laplacian, thereby lessening the negative impact of outliers, enhancing keypoints classification and thus, boosting the recognition accuracy. The proposed method is tested on the Weizmann and KTH human action datasets and on a hand gesture dataset. The retrieved results using the 3D Zernike moments prove that the proposed method can effectively capture the form of the behaviours with low order moments. Moreover, our framework allows to classify various behaviours and achieves a significant recognition rate.
منابع مشابه
An efficient approach for video action classification based on 3d Zernike moments
Action recognition in video and still image is one of the most challenging research topics in pattern recognition and computer vision. This paper proposes a new method for video action classification based on 3D Zernike moments. These last ones aim to capturing both structural and temporal information of a time varying sequence. The originality of this approach consists to represent actions in ...
متن کامل3d Zernike Moments and Zernike Aane Invariants for 3d Image Analysis and Recognition
Guided by the results of much research work done in the past on the performance of 2D image moments and moment invariants in the presence of noise, suggesting that by using orthogonal 2D Zernike rather than regular geometrical moments one gets many advantages regarding noise eeects, information suppression at low radii and redundancy , we have worked out and introduce a complete set of 3D polyn...
متن کاملTranslation invariants of Zernike moments
Moment functions de0ned using a polar coordinate representation of the image space, such as radial moments and Zernike moments, are used in several recognition tasks requiring rotation invariance. However, this coordinate representation does not easily yield translation invariant functions, which are also widely sought after in pattern recognition applications. This paper presents a mathematica...
متن کاملA face recognition approach using Zernike Moments for video surveillance
In this paper, a face recognition approach using Zernike moments is presented for the main purpose of detecting faces in surveillance cameras. Zernike moments are invariant to rotation and scale and these properties make them an appropriate feature for automatic face recognition. A Viola-Jones detector based on the Adaboost algorithm is employed for detecting the face within an image sequence. ...
متن کاملObject Classification via Geometrical, Zernike and Legendre Moments
In many applications, different kinds of moments have been utilized to classify images and object shapes. Moments are important features used in recognition of different types of images. In this paper, three kinds of moments: Geometrical, Zernike and Legendre Moments have been evaluated for classifying 3D object images using Nearest Neighbor classifier. Experiments are conducted using ETH-80 da...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Neurocomputing
دوره 100 شماره
صفحات -
تاریخ انتشار 2013