Alfian Abdul Halin

Multiple Moving Object Detection From UAV Videos Using Trajectories of Matched Regional Adjacency Graphs

Image registration has been long used as a basis for the detection of moving objects. Registration techniques attempt to discover correspondences between consecutive frame pairs based on image appearances under rigid and affine transformations. However, spatial information is often ignored, and different motions from multiple moving objects cannot be efficiently modeled. Moreover, image registration is not well suited to handle occlusion that can result in potential object misses. This paper proposes a novel approach to address these problems. First, segmented video frames from unmanned aerial vehicle captured video sequences are represented using region adjacency graphs of visual appearance and geometric properties. Correspondence matching (for visible and occluded regions) is then performed between graph sequences by using multigraph matching. After matching, region labeling is achieved by a proposed graph coloring algorithm which assigns a background or foreground label to the respective region. The intuition of the algorithm is that background scene and foreground moving objects exhibit different motion characteristics in a sequence, and hence, their spatial distances are expected to be varying with time. Experiments conducted on several DARPA VIVID video sequences as well as self-captured videos show that the proposed method is robust to unknown transformations, with significant improvements in overall precision and recall compared to existing works.

Automatic Overlaid Text Detection, Extraction and Recognition for High Level Event/Concept Identification in Soccer Videos

Overlaid text appears frequently in broadcast sports video. They provide supplementary information regarding the happenings of a particular game. Examples include important events of interest such as bookings and substitutions in a soccer match. Furthermore, overlaid-text is displayed when a particular concept of interest is happening or has happened. This paper presents a technique to automatically detect only video frames that contain valid overlaid text. Experiments have shown reliable detection, extraction and recognition, whose results have been successfully used for domain concept understanding via matching with a soccer term database.

Shot view classification for playfield-based sports video

In this paper, we propose a technique for classifying shots of playfield-based sports video into their respective view classes. Based on common broadcasting style, a shot can be classified as a far-view or a closeup-view. The technique considers the frame-wise color values of each pixel in the HSV color space, while at the same time calculating the assumed object size within the segmented playfield region. Based on our experiments, it is shown that this technique can greatly reduce the number of misclassified shots, while at the same time maintain a good level of accuracy. At the moment, we have tested our approach on soccer videos but believe that it can be applied to other playfield-based sports as well.

Visual and semantic context modeling for scene-centric image annotation

Automatic image annotation enables efficient indexing and retrieval of the images in the large-scale image collections, where manual image labeling is an expensive and labor intensive task. This paper proposes a novel approach to automatically annotate images by coherent semantic concepts learned from image contents. It exploits sub-visual distributions from each visually complex semantic class, disambiguates visual descriptors in a visual context space, and assigns image annotations by modeling image semantic context. The sub-visual distributions are discovered through a clustering algorithm, and probabilistically associated with semantic classes using mixture models. The clustering algorithm can handle the inner-category visual diversity of the semantic concepts with the curse of dimensionality of the image descriptors. Hence, mixture models that formulate the sub-visual distributions assign relevant semantic classes to local descriptors. To capture non-ambiguous and visual-consistent local descriptors, the visual context is learned by a probabilistic Latent Semantic Analysis (pLSA) model that ties up images and their visual contents. In order to maximize the annotation consistency for each image, another context model characterizes the contextual relationships between semantic concepts using a concept graph. Therefore, image labels are finally specialized for each image in a scene-centric view, where images are considered as unified entities. In this way, highly consistent annotations are probabilistically assigned to images, which are closely correlated with the visual contents and true semantics of the images. Experimental validation on several datasets shows that this method outperforms state-of-the-art annotation algorithms, while effectively captures consistent labels for each image.

Overlaid Text Recognition for Matching Soccer-Concept Keywords

Overlaid-text appears frequently in broadcast sports video. They provide a plethora of information regarding the goings-on of a particular game. Examples include important events and video segments of interest such as bookings and half-time analysis, respectively. Furthermore, it is common that overlaid text is displayed when a particular concept is happening or has happened. This paper presents a concept identification framework, based on matched keywords from overlaid-text extraction and recognition. Possible occurrences of overlaid-text in soccer programs are extracted and recognized, and then matched against a soccer-term database. Preliminary experiments show reliable character extraction, whose recognition has been successfully matched with keywords within the database.

Long Lamai Community ICT4D E-Commerce System Modelling: An Agent Oriented Role-Based Approach

This paper presents the post‐mortem report upon completion of the Long Lamai e‐commerce development project. Some weaknesses with regards to the current software modelling approach are identified and an alternative role‐based approach is proposed. We argue that the existing software modelling technique is not suitable for modelling, making it difficult to establish a good contract between stakeholders causing delays in the project delivery. The role‐based approach is able to explicitly highlight the responsibilities among stakeholders, while also forming the contract agreement among them leading towards sustainable ICT4D.

Machining process classification using PCA reduced histogram features and the Support Vector Machine

Being able to identify machining processes that produce specific machined surfaces is crucial in modern manufacturing production. Image processing and computer vision technologies have become indispensable tools for automated identification with benefits such as reduction in inspection time and avoidance of human errors due to inconsistency and fatigue. In this paper, the Support Vector Machine (SVM) classifier with various kernels is investigated for the categorization of machined surfaces into the six machining processes of Turning, Grinding, Horizontal Milling, Vertical Milling, Lapping, and Shaping. The effectiveness of the gray-level histogram as the discriminating feature is explored. Experimental results suggest that the SVM with the linear kernel provides superior performance for a dataset consisting of 72 workpiece images.

Multi-View Human Action Recognition Using Wavelet Data Reduction and Multi-Class Classification☆

Human action recognition from video has several potential to apply in different real-life applications, but the most cases in this field suffer from the variation in viewpoint. Most of published methods in this area are considered the performance of each single camera, therefore the change in the viewpoints significantly decrease the recognition rate. In this paper, multiple views are considered together and a method has proposed to recognize human action depicted in multi-view image sequences. In the first step, the border of the human bodys silhouette is extracted and distance signal is calculated. In the next step, the wavelet transform is applied to extract coefficients of single-view features, and then the extracted features are combined to compose multi-view features. Finally a hierarchical classifier using support vector machine and Naive Bayes classifiers is implemented to classify the actions. The average of overall action recognition accuracy for 12 actions using 5 different angles of views on the IXMAS dataset is 88.22. The results of experiments on the popular multi-view dataset have shown the proposed method achieves high and state-of-the-art success rates. In other word, combination of single-view extracted features from the wavelet approximation coefficients and composing the multi-view features can be used as the multi-view features. Further, the hierarchical classifier can be applied to recognize actions in multi-view human action recognition area.

Silhouette-based multi-view human action recognition in video

In this paper, a human action recognition method is presented where pose features are represented using contour points of the human silhouette, and actions are learned by using sequences of multi-view contour points. The differences and divergences among actors performing the same action are handled by considering variations in shape and speed. Experimental results on the IXMAS dataset show promising success rates, exceeding that of existing multi-view human action recognition state-of-the-art techniques.

Image Abstraction Using Anisotropic Diffusion Symmetric Nearest Neighbor Filter

Image abstraction is an increasingly important task in various multimedia applications. It involves the artificial transformation of photorealistic images into cartoon-like images. To simplify image content, the bilateral and Kuwahara filters remain popular choices to date. However, these methods often produce undesirable over-blurring effects and are highly susceptible to the presence of noise. In this paper, we propose an image abstraction technique that balances region smoothing and edge preservation. The coupling of a classic Symmetric Nearest Neighbor SNN filter with anisotropic diffusion within our abstraction framework enables effective suppression of local patch artifacts. Our qualitative and quantitative evaluation demonstrate the significant appeal and advantages of our technique in comparison to standard filters in literature.