Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/434728
Title: | An integrated approach for object detection recognition and classification in video surveillance using artificial intelligence techniques |
Researcher: | Ariffa begum, S |
Guide(s): | Askarunisa, A and Abirami, A M |
Keywords: | Engineering and Technology Computer Science Computer Science Information Systems artificial intelligence surveillance |
University: | Anna University |
Completed Date: | 2021 |
Abstract: | Automatic detection, classification and recognition of objects are of newlinemajor importance for security systems in video surveillance applications. newlineAutomated video surveillance manages real time observation of suspicious newlineobjects, public and vehicles in a busy environment. As these systems develop newlineinto larger, successfully monitoring all cameras in a timely manner becomes newlinedifficult, particularly for public and crowded places such as airports, buildings, newlineor railway stations. The automatic detection of events is a desirable feature of newlinethese systems to allow focusing the consideration on monitored places newlinepotentially at risk. newlineRecently many contributions for video surveillance have been newlineproposed for solving the issues of object detection, classification and newlinerecognition. However, a robust video surveillance algorithm is still a challenge newlinedue to illumination changes, rapid variations in target appearance, similar nontarget newlineobjects in background and occlusions. In most video based surveillance newlinesolutions, the scene background is measured over time to detect the objects in newlinethe scene which may not belong to the static background. In foreground object newlinedetection, the objects are initially detected as blobs . However the background newlineand foreground subtraction methods alone may not give an optimal solution for newlinevideo surveillance applications. There is a need for the solution that must be able newlineto analyze human behaviors, identify subjects for standoff threat and newlinedetermination. In general, the processing framework of an automated video newlinesurveillance system includes the following stages: detection of object, newlinerecognition, classification, customer behavior and activity analysis, and newlinepersonnel identification. newline |
Pagination: | xix,143p. |
URI: | http://hdl.handle.net/10603/434728 |
Appears in Departments: | Faculty of Information and Communication Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 52.8 kB | Adobe PDF | View/Open |
02_prelim pages.pdf | 1.69 MB | Adobe PDF | View/Open | |
03_content.pdf | 58.66 kB | Adobe PDF | View/Open | |
04_abstract.pdf | 85.59 kB | Adobe PDF | View/Open | |
05_chapter 1.pdf | 286.02 kB | Adobe PDF | View/Open | |
06_chapter 2.pdf | 185.04 kB | Adobe PDF | View/Open | |
07_chapter 3.pdf | 252.05 kB | Adobe PDF | View/Open | |
08_chapter 4.pdf | 392.8 kB | Adobe PDF | View/Open | |
09_chapter 5.pdf | 243.22 kB | Adobe PDF | View/Open | |
10_chapter 6.pdf | 395.75 kB | Adobe PDF | View/Open | |
11_annexures.pdf | 107.26 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 52.28 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: