Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/331735
Title: | Investigation of artificial neural fuzzy inference system and deep learning algorithms for vehicle detection and classification in video surveillance |
Researcher: | Murugan V |
Guide(s): | Vijaykumar V R |
Keywords: | Engineering and Technology Engineering Engineering Electrical and Electronic video surveillance vehicle detection |
University: | Anna University |
Completed Date: | 2019 |
Abstract: | In the recent days, Video Surveillance is one of the important techniques to improve the security in different applications namely public safety, intelligence traffic monitoring systems, crowd analysis etc. The main aim of the research work is to design an automated video surveillance system by means of integrating the image processing and machine learning algorithms for detecting, tracking and classifying object of interest to enhance security in an effective way. To achieve this goal, an automated integrated video surveillance system is designed with three phases. In the first phase, an automatic moving vehicle detection and classification based on artificial neural fuzzy inference system is proposed. In this approach, primarily raw videos are converted into frames. At the preprocessing stage input RGB image is converted into gray scale image using RGB to YCbCr color space conversion process and average filter was applied to the gray scale image to reduce the false object detection. Next, vehicle detection and tracking stage includes three important steps namely, background subtraction, object detection and object tracking. To start with the vehicle detection, a Gaussian Mixture Model (GMM) based background subtraction process is adopted and it divides the static background from foreground. Subsequently, Morphological operation is applied on the background eliminated image to identify the object. The vehicles are extracted by using multiscale closing characteristics. Next, Otsu thresholding is applied to the gray scale image in order to convert the binary image. Objects are to be matched in the consecutive frame, to get the meaningful information from the sequence of images in tracking. newline |
Pagination: | xx, 139p. |
URI: | http://hdl.handle.net/10603/331735 |
Appears in Departments: | Faculty of Information and Communication Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 25.73 kB | Adobe PDF | View/Open |
02_certificates.pdf | 38.89 kB | Adobe PDF | View/Open | |
03_vivaproceedings.pdf | 620.07 kB | Adobe PDF | View/Open | |
04_bonafidecertificate.pdf | 232.71 kB | Adobe PDF | View/Open | |
05_abstracts.pdf | 11.62 kB | Adobe PDF | View/Open | |
06_acknowledgements.pdf | 218.83 kB | Adobe PDF | View/Open | |
07_contents.pdf | 19.91 kB | Adobe PDF | View/Open | |
08_listoftables.pdf | 14.97 kB | Adobe PDF | View/Open | |
09_listoffigures.pdf | 92.42 kB | Adobe PDF | View/Open | |
10_listofabbreviations.pdf | 206.08 kB | Adobe PDF | View/Open | |
11_chapter1.pdf | 538.85 kB | Adobe PDF | View/Open | |
12_chapter2.pdf | 359.08 kB | Adobe PDF | View/Open | |
13_chapter3.pdf | 801.49 kB | Adobe PDF | View/Open | |
14_chapter4.pdf | 568.14 kB | Adobe PDF | View/Open | |
15_chapter5.pdf | 1.09 MB | Adobe PDF | View/Open | |
16_chapter6.pdf | 266.19 kB | Adobe PDF | View/Open | |
17_conclusion.pdf | 37.66 kB | Adobe PDF | View/Open | |
18_references.pdf | 137.68 kB | Adobe PDF | View/Open | |
19_listofpublications.pdf | 86.24 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 58.53 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: