Do you want to publish a course? Click here

Improving the performance of surveillance systems using basic features of the video images (color, edges and structure)

تحسين أداء نظم المراقبة باستخدام ميزات أساسية للصور الفيديوية (اللون و الحواف و البنية)

1294   1   18   0 ( 0 )
 Publication date 2016
and research's language is العربية
 Created by Shamra Editor




Ask ChatGPT about the research

This Research suggests a new mechanism that aims to increase the effectiveness of surveillance systems by extracting the moving objects coming from surveillance camera in order to identify them and propose a new mechanism for indexing and storing in database and classified them according to the basic characteristics and strong indicators and retrieval when needed in less possible time. The basic idea lies in the combination of the basic characteristics of the goal (color, edges and texture) which ensures the best performance in extracting the basic target features and depend on it as indexes, then nonlinear transfers has been done on the edges of the target in order to get a picture bearing the minutest details, then conducted adverse transfers on the edges of the target during the process retrieved from the database. Finally, we propose a new mechanism for indexing all images tabase to Retrieval them in best accuracy and less time, and a program had been achieved to realize this idea.


Artificial intelligence review:
Research summary
يقترح البحث آلية جديدة تهدف إلى زيادة فاعلية نظم المراقبة عن طريق تحديد الأشياء المتحركة أمام كاميرة مراقبة والتعرف عليها، واقتراح آلية جديدة لفهرستها وتخزينها ضمن قاعدة بيانات وتصنيفها وفق الخصائص الأساسية لها (اللون، الحواف، والبنية) واسترجاعها عند الحاجة إليها بأقل زمن ممكن. تعتمد الفكرة الأساسية على الدمج بين الخصائص الأساسية للهدف وإجراء التحويلات اللاخطية على حواف الهدف للحصول على صورة تحمل أدق التفاصيل، ثم إجراء التحويلات المعاكسة أثناء عملية الاسترجاع. تم اقتراح آلية فهرسة جديدة تضمن استرجاع الأهداف المطلوبة بأفضل دقة وأقل زمن، وتم تصميم البرنامج اللازم لتحقيق ذلك. تم تقسيم العمل إلى عدة مراحل، بدءًا من أخذ عينات من كاميرة المراقبة، واستخدام خوارزمية اكتشاف الحركة لاستخلاص الميزات الأساسية للصور وتخزينها ضمن قاعدة بيانات. تم اقتراح آلية فهرسة جديدة لتحويل عملية البحث إلى استعلام ضمن قاعدة البيانات لتقليل أزمنة البحث. أخيرًا، تم بناء نظام استرجاع لتحسين الوصول إلى الأهداف المطلوبة. أظهرت النتائج تحسنًا كبيرًا في نسبة استرجاع الأهداف وسرعة الوصول إليها باستخدام الميزات الأساسية للصور (اللون، الحواف، والبنية).
Critical review
دراسة نقدية: يعتبر البحث خطوة مهمة نحو تحسين نظم المراقبة، إلا أن هناك بعض النقاط التي يمكن تحسينها. أولاً، لم يتم التطرق بشكل كافٍ إلى تحديات تطبيق النظام في بيئات مختلفة، مثل الأماكن ذات الإضاءة المنخفضة أو المتغيرة. ثانيًا، قد يكون من المفيد مقارنة الأداء مع نظم مراقبة أخرى تعتمد على تقنيات مختلفة مثل التعلم العميق أو الشبكات العصبية. ثالثًا، لم يتم مناقشة التكلفة الحاسوبية للنظام بشكل مفصل، وهو أمر مهم لتقييم جدوى التطبيق في الوقت الحقيقي. أخيرًا، يمكن تحسين البحث من خلال دراسة تأثير العوامل البيئية المختلفة على دقة النظام واقتراح حلول لتلك التحديات.
Questions related to the research
  1. ما هي الفكرة الأساسية التي يعتمد عليها البحث لتحسين نظم المراقبة؟

    الفكرة الأساسية تعتمد على الدمج بين الخصائص الأساسية للهدف وهي اللون، الحواف، والبنية، وإجراء التحويلات اللاخطية على حواف الهدف للحصول على صورة تحمل أدق التفاصيل، ثم إجراء التحويلات المعاكسة أثناء عملية الاسترجاع.

  2. ما هي الآلية المقترحة لفهرسة واسترجاع ملفات الفيديو؟

    الآلية المقترحة تعتمد على استخدام الفهرسة الشجرية B* Tree المحسنة، والتي تضمن استرجاع الأهداف المطلوبة بأفضل دقة وأقل زمن، مع تصميم برنامج لتحقيق ذلك.

  3. ما هي النتائج التي توصل إليها البحث بخصوص نسبة استرجاع الأهداف؟

    أظهرت النتائج تحسنًا كبيرًا في نسبة استرجاع الأهداف باستخدام الميزات الأساسية للصور (اللون، الحواف، والبنية)، حيث وصلت نسبة الاسترجاع إلى 98.8% للأشخاص و99% للدراجات.

  4. ما هي التوصيات التي قدمها البحث للدراسات المستقبلية؟

    التوصيات تشمل توسيع عملية فهرسة ملفات الصور باستخدام معالجة الصورة والمنطق الضبابي والشبكات العصبية أو الخوارزميات الجينية، لتحقيق عمليات التخزين والاستعلام بشكل أدق مع الأهداف المتداخلة والصغيرة جدًا.


References used
MURTHY,V.S; AMSIDHAR, E.V; SANKARA, P.R "Application of the Hierarchical and K-Means Techniques in Content Based Image Retrieval". International Journal of Engineering Science and Technology, U.S.A. Vol. 2(3), 2010, 209-212
ASHFAQ, A.K; FAISAL, I. B." Real-Time Motion Trajectory-Based Indexing and Retrieval of Video Sequences".1 st , University of Illinois at Chicago, Chicago, USA, 2005,859
R.Chaudhari, A. M. " Content Based Image Retrieval Using Color and Shape Features". International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, India. Vol. 1, Issue 5, 2012, 386-392
rate research

Read More

Nowadays, wireless networks are spreading more and more. The majority of installed networks have become wireless due to the simplicity of installation; where they do not need an infrastructure. This does not mean that the role of the wired networks i s being eliminated. Instead, the wireless networks are considered as a complementary of the wired networks. With all types of networks from personal and local area networks (PAN and LAN) to wide area networks (WAN) especially the Internet, research has become oriented to focus on the quality of service (QoS) and the integration among all these networks taking into account the Internet which is considered as the backbone for each network that wants to exchange the information with any other network all over the world. In our research, we take into account the quality of service in the broadband networks such as the WiMax network (Worldwide Interoperability for Microwave Access) with IEEE 802.16e standard which covers cities and supports the mobility. This network can be used to interconnect the rural zones with the center of cities, this kind is called point-to-point, or it can be used to cover the cities and is called point-tomultipoint, The last one is used to interconnect different wireless networks especially the local one which has infrastructure (Wi-fi: Wireless Fidelity) and networks which have many users and called hotspots. However, the cells of Wi Max in the cities are called hotzones. We propose a system model that performs the load balancing process between the base stations of WiMax network. This means, the proposed load balancing algorithm exchanges the terminals between the adjacent base stations in order to make the throughput in each base station equals to the throughput in the others. This will improve the performance of the overall network and increase the available bandwidth for each terminal; in addition, this will increase the number of terminals which can be served. On one side, these advantages return to the subscribers, they also return to the operator on the other side, not to mention the good renown that the operator will get from subscribers that will make more subscribers join to this network. The proposed load balancing system can be centralized; implemented in a centralized server connected to all base stations or distributed system implemented in each base station. The load balancing algorithm which consists of several steps is placed in a controller that achieves it. The load balancing process and the handover procedure have to be fast enough in order to prevent the adverse effect on the quality of service especially for the real-time applications users.
Educational data mining aims to study the available data in the educational field and extract the hidden knowledge from it in order to benefit from this knowledge in enhancing the education process and making successful decisions that will improve th e student’s academic performance. This study proposes the use of data mining techniques to improve student performance prediction. Three classification algorithms (Naïve Bayes,J48, Support Vector Machine) were applied to the student performance database, and then a new classifier was designed to combine the results of those individual classifiers using Voting Method. The WEKA tool was used, which supports a lot of data mining algorithms and methods. The results show that the ensemble classifier has the highest accuracy for predicting students' levels compared to other classifiers, as it has achieved a recognition accuracy of 74.8084%. The simple k-means clustering algorithm was useful in grouping similar students into separate groups, thus understanding the characteristics of each group, which helps to lead and direct each group separately.
In this research we studied tricone drill bits by applying a mathematical model which gives an analysis the effected factors on its performance and efficiency(rate of penetration) , so we can change these factors in valid allowable rang of operati ng once , which it gives a positive impact on its performance which shorten time and cost of drilling run , that has been in one of the Syrian oil fields :Deir Ezzour petroleum company ..
We offer in this research, theory study using a modeling tool for the possibility of improving the performance of solar pumping system of rivers using submersible centrifugal pump with variable speed and moving solar panels controlled by logical microcontroller programmer (plc.).
Considering the increasing importance of stereo image compression and Fractal geometry becoming one of the most important fields of modern science ,we applied fractal image compression based on quadtree portioning method and global search algorithm , on a group of stereo image pairs . As the stereo image consists of two planar images , left and right .Both the left image ( reference image ) and the disparity map between left and right images , were compressed using fractal compression . We applied both block matching algorithm and Semi Global Method (SGM)to obtain the disparity map. The left image and the depth map were reconstructed using fractal decompression while the right image (target image ) was reconstructed using the reconstructed left image , disparity map and the error image between the original right image and the reconstructed right image that was build from the left image and the disparity map . The results were evaluated using quality objective measures which are MSE (Mean Square Error ) and PSNR (Peak Signal to Noise Ratio) and efficiency objective measures which are CR(Compression Ratio) and compression time . The results were compared with JPEG compression of stereo pairs based on Discrete Cosine Transform DCT and JPEG2000 compression of stereo pairs on stereo image based on Discrete Wavelet Transform DWT .
comments
Fetching comments Fetching comments
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا