Background subtraction and logical relationship for moving object detection in urban traffic video

المؤلفون المشاركون

al-Shaqaqi, B.
Bu Mihid, M.
Keche, M.
Ouamri, A.

المصدر

المؤتمر الدولي الهندسي الرابع : “نحو هندسة القرن الحادي و العشرين” : الذي نظمته كلية الهندسة بالجامعة الإسلامية-غزة يومي الاثنين و الثلاثاء الخامس عشر و السادس عشر من تشرين أول / أكتوبر 2012.

الناشر

الجامعة الإسلامية كلية الهندسة

تاريخ النشر

2012-10-31

دولة النشر

فلسطين (قطاع غزة)

عدد الصفحات

10

التخصصات الرئيسية

العلوم الهندسية والتكنولوجية (متداخلة التخصصات)

الملخص الإنجليزي

Moving object detection is a fundamental technology for video applications, such as traffic monitoring, human motion capture, and video surveillance.

A common approach is to perform background subtraction, which identifies moving objects from the portion of a video frame that differs significantly from a background model.

There are many challenges in developing a good background subtraction algorithm.

First, it must be robust against changes in illumination.

Second, it should avoid detecting non-stationary background objects such as swinging leaves, rain, snow, and shadow cast by moving objects.

Finally, its internal background model should react quickly to changes in background such as starting and stopping of vehicles.

In this paper, we work with a fixed camera in a stationary scene and a simple non-statistical background model is utilized, therefore we formulate the problem of background subtraction as the problem of composing a new background frame using current background frame and patches extracted from video sequence.

We firstly use the thresholding method to binarize the difference image background subtraction to locate the change information with respect to the background frame, and then propose an efficient background updating algorithm based on the logic XOR operation on the change information in the difference frames.

This algorithm is tested on urban traffic video sequences and compared to the mixture of gaussians and approximate median filtering.

نوع البيانات

أوراق مؤتمرات

رقم السجل

BIM-777406

• APA
• MLA
• AMA