UTAR Institutional Repository

Front yard surveillance system: robbery scene detection

Tang, Jia Le (2020) Front yard surveillance system: robbery scene detection. Final Year Project, UTAR.

Download (1719Kb) | Preview


    This project aims to develop an intelligent surveillance system that can recognize the robbery activities occurring in the front yard of a landed house using a security camera positioned at the place of interest. The focus of this project is to study and understand the pattern of human movement in robbery in order to implement a suitable computer vision algorithm for real-time robbery detection in the front yard of a landed house. The project is developed with the following technique: YOLO object detection, contour tracking based on temporal subtraction, and motion analysis. First YOLO will start to detect human and car present in the video frame and store its location. When a car is detected, the car stationary time starts to measure. After the initial human position is stored, the subsequent human position is then detected with simple temporal subtraction to reduce the computational resources. The process of tracking the contour is continue until no human motion is detected for the next 10 frames. All of the detected human movement will be drawn as an arrow to indicate the direction of human movement. Analysis is done by calculate the car stationary time and the number of human movements in entrance and car region. Warning is flagged is the probability of human movement in entrance and car region is high and the car stationary time exceed 25 seconds.

    Item Type: Final Year Project / Dissertation / Thesis (Final Year Project)
    Subjects: T Technology > T Technology (General)
    T Technology > TA Engineering (General). Civil engineering (General)
    Divisions: Faculty of Information and Communication Technology > Bachelor of Information Systems (Honours) Information Systems Engineering
    Depositing User: ML Main Library
    Date Deposited: 05 Jan 2021 17:19
    Last Modified: 05 Jan 2021 17:19
    URI: http://eprints.utar.edu.my/id/eprint/3794

    Actions (login required)

    View Item