Action recognition has been a growing research topic in computer vision due to its great potentials for real-world applications. In this paper, we develop an effective action recognition approach based on salient obje...
详细信息
Action recognition has been a growing research topic in computer vision due to its great potentials for real-world applications. In this paper, we develop an effective action recognition approach based on salient object detection and propose a new feature descriptor to represent the changes of edge orientation. Firstly, we detect salient objects from each frame of a video sequence and generate edge maps for those detected salient objects. Then, we extract features on developed edge maps, using a combination of proposed Histogram of Changing Edge Orientation (HCEO) feature descriptor and existing Histogram of Optical Flow (HOF) feature descriptor. Finally, supervised multi-class support vector machine (SVM) classifier is used for recognizing various actions. The experiments were carried out on the standard UCF-Sports action dataset. As experimental results, our proposed action recognition approach is achieved with a significant improvement in recognition accuracy.
Flexible based Dye Sensitized Solar Cells (DSSCs) in nanotechnology revolution have always been in the thick of things where fabrication method and achieving good performances are concerned. Such concerns were adjudic...
Flexible based Dye Sensitized Solar Cells (DSSCs) in nanotechnology revolution have always been in the thick of things where fabrication method and achieving good performances are concerned. Such concerns were adjudicated by improvising four(4) innate DSSCs structures composed of photoanode, semiconductor, electrolyte and counter electrode. This paper aims to observe the impact of changing Platinum(Pt) volumes on the counter electrodes of DSSCs by conducting tests on 0.2mm Titanium (Ti) foil based photoanode DSSCs. The deposition of Pt was varied into 70µl, 50µl and 30µl accordingly by spin coating technique at 1500 rpm. All samples were synthesized, deposited with Pt and assembled before being tested under solar light simulator of 1000W/cm2. Samples with 70µl Pt deposition indicated a higher efficiency (Ƞ) of 2.83%, even though it allowed less light penetration, while the 30µl Pt deposition sample provided efficiency (Ƞ) of 0.88% with more light penetration.
A flame combustion method enables the synthesis of diamond using acetylene-oxygen gas flame combustion in ambient air. Recently, tungsten carbide (WC) has been used as cutting tools in the machining industry. To obtai...
详细信息
computer and web security system is an attempt to avoid attacks from crackers because a form and method of crime on internet network can not be predicted. Therefore, we just keep trying to use various methods in secur...
详细信息
As a higher education institution, knowing which GPA of the semester has the most determinant to affecting the academic performance of students is important yet challenging. Therefore, this paper deliberates the usage...
详细信息
Action recognition has been an active research area in computer vision community during the recent years. However, it is still a challenging task due to the difficulties mainly resulted from the background clutter, il...
详细信息
ISBN:
(纸本)9781509055050
Action recognition has been an active research area in computer vision community during the recent years. However, it is still a challenging task due to the difficulties mainly resulted from the background clutter, illumination changes, large intra-class variation and noise. In this paper, we aim to develop an action recognition approach by navigating focus of attention (action region) with saliency detection and introducing a feature descriptor, namely Histogram of Accumulated Changing Gradient Orientation (HACGO). We firstly detect saliency in each video frame by computing pattern and color distinctness to localize action region. Then, we extract appearance and motion features using proposed HACGO, and existing HOG and HOF feature descriptors. Finally, a multi-class SVM classifier is applied to recognize different actions. The experiments were conducted on the standard UCF Sports action dataset. As experimental results, our action recognition approach achieved high recognition accuracy with a new combination of feature descriptors.
The optimal location and sizing of distribution static compensator (DSTATCOM) in distribution systems is a complex nonlinear problem. This problem is constrained by various technical limits and can offer different obj...
The optimal location and sizing of distribution static compensator (DSTATCOM) in distribution systems is a complex nonlinear problem. This problem is constrained by various technical limits and can offer different objectives that would provide many benefits to the network. These include minimization of power losses, index of voltage profile, load balancing index, and annual cost saving index which have been considered in this paper. In the present work, the Imperialist Competitive Algorithm (ICA) is employed for optimizing the distribution systems where an optimal location and sizing of DSTATCOM is investigated. In this study, an aggregating operator named Max-geometric mean is used for combination of objectives and providing overall objective function. The scaling of objectives is performed in the fuzzy framework. The proposed algorithm is implemented in 33 and 69 buses IEEE test systems. Furthermore, the uncertainty of the loads of the balanced system is modeled by using a fuzzy technique. Based on the numerical results of this work, one can extract that the performance of the ICA is slightly higher than other meta-heuristic algorithms; hence the introduced approach can be used by utility services for optimal DSTATCOM allocation and sizing in the distribution systems.
作者：
Djuana, EComputer System Laboratory
Electrical Engineering Department Faculty of Industrial Technology Trisakti University Grogol Jakarta 11440 Indonesia
Folksonomy, as one result of collaborative tagging process, has been acknowledged for its potential in improving categorization and searching of web resources. However, folksonomy contains ambiguities such as synonymy...
Folksonomy, as one result of collaborative tagging process, has been acknowledged for its potential in improving categorization and searching of web resources. However, folksonomy contains ambiguities such as synonymy and polysemy as well as different abstractions or generality problem. To maximize its potential, some methods for associating tags of folksonomy with semantics and structural relationships have been proposed such as using ontology learning method. This paper evaluates our previous work in ontology learning according to gold-standard evaluation approach in comparison to a notable state-of-the-art work and several baselines. The results show that our method is comparable to the state-of the art work which further validate our approach as has been previously validated using task-based evaluation approach.
暂无评论