Object identification, enhancement and tracking under dynamic background conditions

2020 ◽

Vol 13 (6) ◽

pp. 374-383

Author(s):

Vivaram Raghavulu ◽

◽

Ande Prasad ◽

Keyword(s):

Object Detection ◽

Level Set ◽

Moving Objects ◽

Theory Model ◽

Object Identification ◽

Dynamic Background ◽

Major Drawback ◽

Static Object ◽

Segmentation Problem ◽

Inference Theory

Video analytics is widely used to automatically analyze the videos to extract the required information and detect the various events object identification and traffic analysis. The segmentation of the image is referring to extracting the required region from an image. The major objective of the segmentation process is to cluster the images without being affected by the noises. The detection of the moving objects is a challenging task in video analysis due to the dynamic background of the video. The major drawback of the existing Kernel Fuzzy C-Means (KFCM) clustering is initialization of random centroids which increases the execution time to identify the segmented portions. In this research, the Grey Wolf Optimization (GWO) algorithm used to initialize the centroids of required clusters in KFCM and Level Set (LS) Algorithm is used to segment the objects in video sequence. The proposed KFCM-GWO-LS is implemented for moving and static object detection in the videos obtained from SBM-RGBD dataset. For object detection, determining central clusters are important which is performed by using KFCM. GWO helps in finding the best centroids clusters by matching with KFCM. The centroids clusters are segmented by using LS algorithm which undergoes over segmentation problem that is overcome by GWO. As all the three techniques are dependent on one another hybrid of all these techniques obtains better results. The proposed KFCM-GWO-LS is evaluated in terms of Recall, Specificity, Precision and F-measure and the experimental results showed that the proposed method improved the system performance from 0.3 % to 14.35 % compared to existing methods Multi-Sensor Scheduler Algorithm and Statistical Inference Theory model.

Download Full-text

Editorial

Research and Development on Information and Communication Technology ◽

10.32913/rd-ict.vol3.no14.612 ◽

2017 ◽

Author(s):

Vu Chi Kien ◽

Do Ngoc Minh ◽

Nguyen Hoang Ha ◽

Nguyen Linh Trung

Keyword(s):

Good Practice ◽

Scientific Publication ◽

Associate Editor ◽

Open Access Journal ◽

Object Identification ◽

Online Journal ◽

International Visibility ◽

National University ◽

Standard Practices

Dear readers,The year 2017 marks the 55th anniversary of the Journal of Information & Communications of the Ministry of Information and Communications, and the 18th anniversary of its scientific publication – the Research and Development on Information and Communication Technology (RD-ICT) journal. Again, the purpose of RD-ICT is to provide a forum for researchers and professionals to disseminate original and innovative ideas in the fields of information technology, communications and electronics in Vietnam and worldwide.Without kind support and invaluable contribution of readers and authors, and hard work of the anonymous reviewers and editors under the former editorship of Prof. Nguyễn Thúc Hải, Prof. Trần Văn Lộc and Prof. Nguyễn Cảnh Tuấn, RD-ICT would not be what it is today – a total of 37 issues in Vietnamese and 14 issues in English.To contribute to the development of research in Vietnam, toward standard practices, high quality and international visibility, RD-ICT has been taking measures by following current practices of prestigious international research journals. In this editorial, we would like to inform you some of the things we have been doing lately.Since June 2014, RD-ICT has applied online journal management and publishing, thanks to the well-known open-source Open Journal System of the Public Knowledge Project, which is used by thousands of online scientific journals worldwide. The editorial board of RD-ICT is currently being extended to include international prominent scientists, thus forming a team of international associate editors, under the complementary technical editorship of Prof. Đỗ Ngọc Minh (University of Illinois at Urbana-Champaign, United States), Prof. Nguyễn Hoàng Hà (University of Saskatchewan, Canada) and Prof. Nguyễn Linh Trung (Vietnam National University, Hanoi). Each submission is now assigned to an associate editor who then coordinates the review process and makes editorial decision.For improved paper quality in terms of organization and presentation, authors are guided to good practice of technical paper writing. In addition, accepted submissions are now copy-edited, by the corresponding associate editors, and laid out using LATEX.Apart from already being an open-access journal, RD-ICT is also looking into other measures to increase its visibility, such as all-English publishing, digital object identification, Google Scholar citation, and SCOPUS indexing.Taking the opportunity of informing the above changes, we would like to, again, express our sincere gratitude and appreciation to the readers, authors, reviewers and editors of RD-ICT, and to the leadership of the Ministry of Information and Communications and its predecessors – the Directorate General of Posts and Telecommunications, the Ministry of Post and Telecommunications – for their continued support and contribution to RD-ICT.We look forward to your comments and feedback for better developing the RD-ICT journal for Vietnam.Sincerely,Vũ Chí Kiên, Editor-in-ChiefĐỗ Ngọc Minh, Nguyễn Hoàng Hà, Nguyễn Linh Trung, Technical Editors-in-Chief

Download Full-text

Reforms and transformation paths in comparative perspective: challenging comparative views on East European and Chinese reforms

Acta Oeconomica ◽

10.1556/aoecon.55.2005.2.3 ◽

2005 ◽

Vol 55 (2) ◽

pp. 171-199 ◽

Cited By ~ 2

Author(s):

Mária Csanádi

Keyword(s):

Power Distribution ◽

State Power ◽

State Model ◽

Comparative Perspective ◽

Dynamic Background ◽

East European ◽

Structural Context ◽

Political Conditions ◽

Party State ◽

Chinese Reforms

Reforms, in view of a comparative party-state model, become the instruments of self-reproduction and self-destruction of party-state power. The specific patterns of power distribution imply different development and transformation paths through different instruments of self-reproduction. This approach also points to the structural and dynamic background of the differences in the location, sequence, speed and political conditions of reforms during the operation and transformation of party-states. In view of the model the paper points to the inconsistencies that emerge in the comparative reform literature concerning the evaluation and strategies of reforms disconnected from their systemic-structural context.

Download Full-text

ON METHODS OF OBJECT DETECTION IN VIDEO STREAMS

Computer systems and network ◽

10.23939/csn2020.01.080 ◽

2017 ◽

Vol 2 (1) ◽

pp. 80-87

Author(s):

Puyda V. ◽

◽

Stoian. A.

Keyword(s):

Computer Vision ◽

Object Detection ◽

Open Source ◽

Feature Detection ◽

Video Stream ◽

Object Identification ◽

Vision Systems ◽

Modern Computer ◽

Computer Vision Systems ◽

Open Source Hardware

Detecting objects in a video stream is a typical problem in modern computer vision systems that are used in multiple areas. Object detection can be done on both static images and on frames of a video stream. Essentially, object detection means finding color and intensity non-uniformities which can be treated as physical objects. Beside that, the operations of finding coordinates, size and other characteristics of these non-uniformities that can be used to solve other computer vision related problems like object identification can be executed. In this paper, we study three algorithms which can be used to detect objects of different nature and are based on different approaches: detection of color non-uniformities, frame difference and feature detection. As the input data, we use a video stream which is obtained from a video camera or from an mp4 video file. Simulations and testing of the algoritms were done on a universal computer based on an open-source hardware, built on the Broadcom BCM2711, quad-core Cortex-A72 (ARM v8) 64-bit SoC processor with frequency 1,5GHz. The software was created in Visual Studio 2019 using OpenCV 4 on Windows 10 and on a universal computer operated under Linux (Raspbian Buster OS) for an open-source hardware. In the paper, the methods under consideration are compared. The results of the paper can be used in research and development of modern computer vision systems used for different purposes. Keywords: object detection, feature points, keypoints, ORB detector, computer vision, motion detection, HSV model color

Download Full-text