Weighted Directional 3 D Stationary Wavelet-based Action Classification

The aim of intelligent surveillance is to conceive reliable and efficient systems having the ability to detect moving objects in complicated real world scenes. These systems also, track the detected objects and analyze their actions and activities. Many applications are built on these operations such as advanced robotics and human computer interaction. This paper aims at proposing a framework for joint detection and recognition of human actions in a surveillance scenario. This objective is achieved in two main steps. First, a modern 3D stationary wavelet-based motion detection technique is used for detecting motion in the video sequence. The 3D technique fuses the spatial and temporal information achieving accurate detection results in real-world scene variations. The output of the detector is used to obtain a directional multi-scale representation for the action performed in the processed frames. This representation is described using local and global descriptors. The local descriptor combines the directional information contained in the wavelet coefficients in a weighted manner using an entropy value.The new local descriptor provides a discriminative local features for the human actions.The motion detection and the action recognition steps have been tested using benchmark datasets and compared to state-of-the-art methods.

[1]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[2]  Rafael C. González,et al.  Local Determination of a Moving Contrast Edge , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Stéphane Mallat,et al.  Singularity detection and processing with wavelets , 1992, IEEE Trans. Inf. Theory.

[4]  Mark J. Shensa,et al.  The discrete wavelet transform: wedding the a trous and Mallat algorithms , 1992, IEEE Trans. Signal Process..

[5]  Tim J. Ellis,et al.  Image Difference Threshold Strategies and Shadow Detection , 1995, BMVC.

[6]  A F Bobick,et al.  Movement, activity and action: the role of knowledge in the perception of motion. , 1997, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[7]  Majid Mirmehdi,et al.  Detection and Tracking of Very Small Low Contrast Objects , 1998, BMVC.

[8]  Ingrid Daubechies Recent results in wavelet applications , 1998, J. Electronic Imaging.

[9]  Andrew P. Bradley Shift-invariance in the Discrete Wavelet Transform , 2003, DICTA.

[10]  Arun Sharma,et al.  Moments and Wavelets for Classification of Human Gestures Represented by Spatio-Temporal Templates , 2004, Australian Conference on Artificial Intelligence.

[11]  Tieniu Tan,et al.  A survey on visual surveillance of object motion and behaviors , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[12]  B. Caputo,et al.  Recognizing human actions: a local SVM approach , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[13]  Arun Sharma,et al.  Wavelet directional histograms for classification of human gestures represented by spatio-temporal templates , 2004, 10th International Multimedia Modelling Conference, 2004. Proceedings..

[14]  J. E. Fowler,et al.  The redundant discrete wavelet transform and additive noise , 2005, IEEE Signal Processing Letters.

[15]  Ronen Basri,et al.  Actions as space-time shapes , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[16]  Ramakant Nevatia,et al.  3D Human Action Recognition Using Spatio-temporal Motion Templates , 2005, ICCV-HCI.

[17]  U. Knauer,et al.  THE STRUCTURE OF ROAD TRAFFIC SCENES AS REVEALED BY UNSUPERVISED ANALYSIS OF THE TIME AVERAGED OPTICAL FLOW , 2006 .

[18]  Adrian Hilton,et al.  A survey of advances in vision-based human motion capture and analysis , 2006, Comput. Vis. Image Underst..

[19]  Fang-Hsuan Cheng,et al.  Real time multiple objects tracking and identification based on discrete wavelet transform , 2006, Pattern Recognit..

[20]  Peter Lambert,et al.  Mixture Models Based Background Subtraction for Video Surveillance Applications , 2007, CAIP.

[21]  Mohamed-Jalal Fadili,et al.  The Undecimated Wavelet Decomposition and its Reconstruction , 2007, IEEE Transactions on Image Processing.

[22]  Liu Zhi Fang,et al.  A method to segment moving vehicle cast shadow based on wavelet transform , 2008, Pattern Recognit. Lett..

[23]  Rama Chellappa,et al.  Machine Recognition of Human Activities: A Survey , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[24]  Yannis Avrithis,et al.  Spatiotemporal saliency for video classification , 2009, Signal Process. Image Commun..

[25]  Mohamed-Jalal Fadili,et al.  Numerical Issues When Using Wavelets , 2009, Encyclopedia of Complexity and Systems Science.

[26]  Dubravko Culibrk,et al.  Optimal wavelet differencing method for robust motion detection , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[27]  Weihong Li,et al.  Robust pedestrian detection in thermal infrared imagery using the wavelet transform , 2010 .

[28]  Md. Atiqur Rahman Ahad,et al.  Motion history image: its variants and applications , 2012, Machine Vision and Applications.

[29]  Tianzhu Zhang,et al.  Human Action Recognition in Videos Using Hybrid Motion Features , 2010, MMM.

[30]  Ronald Poppe,et al.  A survey on vision-based human action recognition , 2010, Image Vis. Comput..

[31]  Andrew Beng Jin Teoh,et al.  Wavelet local binary patterns fusion as illuminated facial image preprocessing for face verification , 2011, Expert Syst. Appl..

[32]  Matti Pietikäinen,et al.  Computer Vision Using Local Binary Patterns , 2011, Computational Imaging and Vision.

[33]  Ling Shao,et al.  Transform based spatio-temporal descriptors for human action recognition , 2011, Neurocomputing.

[34]  Rémi Ronfard,et al.  A survey of vision-based methods for action representation, segmentation and recognition , 2011, Comput. Vis. Image Underst..

[35]  Xiaoqin Zhang,et al.  Adaptive learning codebook for action recognition , 2011, Pattern Recognit. Lett..

[36]  Shaogang Gong,et al.  Fusing appearance and distribution information of interest points for action recognition , 2012, Pattern Recognit..

[37]  Narciso García,et al.  An efficient multiple object detection and tracking framework for automatic counting and video surveillance applications , 2012, IEEE Transactions on Consumer Electronics.

[38]  Anupam Agrawal,et al.  A survey on activity recognition and behavior understanding in video surveillance , 2012, The Visual Computer.

[39]  Yang Zhao,et al.  Completed robust local binary pattern for texture classification , 2013, Neurocomputing.

[40]  Wen-Hui Chen,et al.  Research and Perspective on Local Binary Pattern , 2013 .

[41]  Shiv Ram Dubey,et al.  Human Activity Recognition Using Gait Pattern , 2013, Int. J. Comput. Vis. Image Process..

[42]  Naseer Al-Jawad,et al.  Fusing Local Binary Patterns with Wavelet Features for Ethnicity Identification , 2013 .

[43]  Mohamed F. Tolba,et al.  Directional Stationary Wavelet-Based Representation for Human Action Classification , 2014, AMLTA.

[44]  Eun-Soo Kim,et al.  Video-Based Human Activity Recognition Using Multilevel Wavelet Decomposition and Stepwise Linear Discriminant Analysis , 2014, Sensors.

[45]  Hala Mousher Ebied,et al.  Action Recognition Using Stationary Wavelet-Based Motion Images , 2014, IEEE Conf. on Intelligent Systems.

[46]  Mohamed F. Tolba,et al.  Human action recognition via multi-scale 3D stationary wavelet analysis , 2014, 2014 14th International Conference on Hybrid Intelligent Systems.

[47]  Mohamed F. Tolba,et al.  Spatio-Temporal Motion Detection for Intelligent Surveillance Applications , 2015 .