Maryam N. Al-Berry

Fusing directional wavelet local binary pattern and moments for human action recognition

Recently, transformation-based methods have been widely used in many computer vision areas because of their powerful representation ability. One of the most widely used transforms is the wavelet transform that has proved to be very useful in many applications. In this study, a new method for human action representation and description is proposed. This method combines the advantages of local and global descriptions. The method works by fusing the Hu invariant moments as global descriptors with a new local descriptor that is based on three-dimensional stationary wavelet transform and the concept of local binary patterns. The performance of the new method was examined in two different ways. The first one is by fusing the proposed directional global and local features in one feature vector, while the other is using the features of different directional bands separately to train multiple classifiers and then using a voting scheme to vote for the best match. The performance of the proposed method is verified using standard datasets, achieving high accuracy in comparison with state-of-the-art methods. In addition, the proposed method is proved to be robust to the changes in lighting and scale variations, but it exhibits limitations towards dynamic backgrounds.

Spatio-Temporal Motion Detection for Intelligent Surveillance Applications

Intelligent surveillance aims at conceiving reliable and efficient systems that are able to detect and track moving objects in complicated real world scenes. This paper proposes an innovative 3D stationary wavelet-based motion detection technique that fuses spatial and temporal analysis in a single 3D transform. This single transform is composed of applying a 2D transform in the spatial domain followed by 1D transform in the time domain. The results of the proposed technique are compared favorably with those of the recently used stationary wavelet-based technique. In addition of being accurate and has reasonable complexity of O(N2log N), the proposed technique is robust to real world scene variations, including nonuniform and time-varying illumination.

Action Recognition Using Stationary Wavelet-Based Motion Images

Human action recognition is one of the most important fields in computer vision, because of the large number of applications that employ action recognition. Many techniques have been proposed for representing and classifying actions; yet these tasks are still non-trivial due to a number of challenges and characteristics. In this paper, a new action representation method is proposed. The proposed method utilizes the 3D Stationary Wavelet Analysis to encode the spatio-temporal characteristics of the motion available in the video sequences in a way similar to motion history images. The proposed representation was tested using Weizmann dataset, exhibiting promising results when compared to the existing state – of – the – art methods.

Human action recognition via multi-scale 3D stationary wavelet analysis

Multi-scale methods, especially wavelets, are being used in various computer vision applications, including surveillance, robotics, and human-centered computing. Human action recognition is one of the core areas that dominate the aforementioned applications. In this paper, the 3D multi-scale stationary wavelet analysis is used to build a view-based multi-scale spatio-temporal representation of the human actions. The proposed representation benefits from the ability of the 3D stationary wavelet transform to fuse the spatio-temporal information highlighted at different scales and orientations. Experimental results using Weizmann and KTH datasets revealed a good performance in various scenarios with different conditions.

Directional Stationary Wavelet-Based Representation for Human Action Classification

This paper proposes a directional wavelet-based representation of natural human actions in realistic videos. This task is very important for human action recognition, which has become one of the most important fields in computer vision. Its importance comes from the large number of applications that employ human action classification and recognition. The proposed method utilizes the 3D Stationary Wavelet Analysis to encode the directional spatio-temporal characteristics of the motion available in video sequences. It was tested using the Weizmann dataset, and produced promising preliminary results (92.47 % classification accuracy) when compared to existing state–of–the–art methods.

Motion detection using wavelet-enhanced accumulative frame differencing

Detecting and tracking moving objects in complicated real world scenes is a fundamental component for a wide variety of applications, including intelligent surveillance, advanced robotics, and human computer interaction. Based on this fundamental step, the subsequent processing is shaped up. Many standard algorithms are known for detecting moving objects, with different performances and time complexities, including optical flow, background subtraction, frame difference and wavelet filters. Existing frame differencing has a limited capability in detecting slowly moving objects, especially in the presence of illumination variations. In this paper, an innovative technique is proposed for the detection of moving objects in scenes with non-uniform illumination. The proposed technique is based on the idea of accumulative frame differencing and is enhanced using 2-D Discrete Wavelet Transform (DWT). Evaluation and comparison of the proposed technique with the different existing ones demonstrate the efficiency of using the 2-D DWT in the process of motion detection.

Deep Learning for Satellite Image Classification.

Nowadays, large amounts of high resolution remote-sensing images are acquired daily. However, the satellite image classification is requested for many applications such as modern city planning, agriculture and environmental monitoring. Many researchers introduce and discuss this domain but still, the sufficient and optimum degree has not been reached yet. Hence, this article focuses on evaluating the available and public remote-sensing datasets and common different techniques used for satellite image classification. The existing remote-sensing classification methods are categorized into four main categories according to the features they use: manually feature-based methods, unsupervised feature learning methods, supervised feature learning methods, and object-based methods. In recent years, there has been an extensive popularity of supervised deep learning methods in various remote-sensing applications, such as geospatial object detection and land use scene classification. Thus, the experiments, in this article, carried out on one of the popular deep learning models, Convolution Neural Networks (CNNs), precisely AlexNet architecture on a standard sounded dataset, UC-Merceed Land Use. Finally, a comparison with other different techniques is introduced.

3D Visualization of Brain Tumors Using MR Images: A Survey

BACKGROUND Three-Dimensional visualization of brain tumors is very useful in both diagnosis and treatment stages of brain cancer. DISCUSSION It helps the oncologist/neurosurgeon to take the best decision in Radiotherapy and/or surgical resection techniques. 3D visualization involves two main steps; tumor segmentation and 3D modeling. CONCLUSION In this article, we illustrate the most widely used segmentation and 3D modeling techniques for brain tumors visualization. We also survey the public databases available for evaluation of the mentioned techniques.

Action Classification Using Weighted Directional Wavelet LBP Histograms

The wavelet transform is one of the widely used transforms that proved to be very powerful in many applications, as it has strong localization ability in both frequency and space. In this paper, the 3D Stationary Wavelet Transform (SWT) is combined with a Local Binary Pattern (LBP) histogram to represent and describe the human actions in video sequences. A global representation is obtained and described using Hu invariant moments and a weighted LBP histogram is presented to describe the local structures in the wavelet representation. The directional and multi-scale information encoded in the wavelet coefficients is utilized to obtain a robust description that combine global and local descriptions in a unified feature vector. This unified vector is used to train a standard classifier. The performance of the proposed descriptor is verified using the KTH dataset and achieved high accuracy compared to existing state-of-the-art methods.