Scribd Logo
Upload

Welcome to Scribd!

  • 18 views

    Suspicious Human Activity Detection System

    Uploaded by

    bmahalakshmi775
    The document describes a proposed system for detecting unusual human activity using optical flow analysis and motion influence maps. The system aims to enhance security by accurately identifying suspicious behaviors. It analyzes areas of significant motion to filter out normal activities and highlight potential abnormalities, using machine learning to recognize deviations from regular motion patterns.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    Suspicious Human Activity Detection System

    Uploaded by

    bmahalakshmi775
    18 views11 pages
    The document describes a proposed system for detecting unusual human activity using optical flow analysis and motion influence maps. The system aims to enhance security by accurately identifying suspicious behaviors. It analyzes areas of significant motion to filter out normal activities and highlight potential abnormalities, using machine learning to recognize deviations from regular motion patterns.

    Original Title

    Suspicious human activity detection system

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document describes a proposed system for detecting unusual human activity using optical flow analysis and motion influence maps. The system aims to enhance security by accurately identifying suspicious behaviors. It analyzes areas of significant motion to filter out normal activities and highlight potential abnormalities, using machine learning to recognize deviations from regular motion patterns.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    18 views11 pages

    Suspicious Human Activity Detection System

    Uploaded by

    bmahalakshmi775
    The document describes a proposed system for detecting unusual human activity using optical flow analysis and motion influence maps. The system aims to enhance security by accurately identifying suspicious behaviors. It analyzes areas of significant motion to filter out normal activities and highlight potential abnormalities, using machine learning to recognize deviations from regular motion patterns.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    You are on page 1of 11

    Unusual human activity

    detection system
    TEAM MEMBERS
    MAHALAKSHMI.B-111721102075
    LAKSHMI PRIYA.V.C-111721102062
    POOJA RAO.R.J-111721102112
    ABSTRACT
    3

    OBJECTIVES
    4

    agenda ARCHITECTURE DIAGRAM


    5

    METHODOLOGY6

    LITERATURE REVIEW
    7
    Abstract:
    • The development of intelligent surveillance systems for abnormal human activity
    detection is crucial for ensuring public safety and security. In this study, we propose an
    innovative approach leveraging optical flow analysis and motion influence maps to
    enhance the accuracy of abnormal activity detection in video streams.By focusing on
    areas with significant motion influence, our system effectively filters out normal activities
    and highlights potential abnormalities. Machine learning algorithms are employed to
    analyze these maps, enabling the system to recognize deviations from regular motion
    patterns. This approach offers a dynamic and adaptive method for abnormal activity
    detection, ensuring robust performance even in complex environments with varying
    lighting conditions and occlusions.The integration of optical flow analysis and motion
    influence maps provides a powerful solution for real-time abnormal human activity
    detection, significantly enhancing the capabilities of existing surveillance systems.

    20XX presentation title


    Objectives:
    1) Enhance public safety by accurately identifying suspicious behaviors and
    potential threats.
    2) Provide robust performance in complex environments, including varying lighting
    conditions and occlusions.
    3) Improve security measures by filtering out normal activities and highlighting
    potential abnormalities.
    4)Integrate optical flow analysis and motion influence maps to create a dynamic
    abnormal activity detection system.
    5)Contribute to the advancement of intelligent surveillance technologies for
    proactive threat prevention.

    20XX presentation title


    Existing System:
    • With the increase in the amount of anti-social activities taking
    place in the environment, security has been given the utmost
    importance lately.
    • Therefore, organizations require a constant monitoring of people
    and their interactions. Since this constant monitoring of data either
    Click icon to add picture
    by humans to judge if the events are abnormal is a near impossible
    task as it requires a lot of workforce and constant attention.
    • Therefore, the challenge that comes up is the demand for an
    automatic and intelligent analysis for such video sequences.

    20XX presentation title


    Proposed system
    • Our project comes forward as an attempt to provide solution to
    such a problem as the model developed is a smart surveillance
    system which can detect unusual or abnormal activity
    automatically.
    • This system can be effectively installed in a CCTV Camera to
    Click icon to add picture
    perform vison-based surveillance on a video footage.
    • . A method for representing the motion characteristics is described
    for detection and localisation of unusual activities in the crowd
    scenes on a generalised framework which includes both a local and
    global range for detection of such activities.

    20XX presentation title


    Architecture diagram:

    20XX presentation title


    Methodology:
    • The Abnormal Human Activity Detection System is an intelligent open computer vision-
    based surveillance system.
    1)Data Input and Pre-processing:For the pre-processing the input video file is subjected to the system. The video
    is split in series of images known as frames and these frames are handled in a sequence. The frame which is
    RGB is correspondingly converted to gray scale.
    •
    2)Optical Flow Analysis:After the pre-processing step which was done for each frame in the given video, the
    next step is Optical Flow which we determine for every pixel of frame by the use of Gunnar Farne Back's
    algorithm.
    •
    3)Motion Information Using Motion Influence Map:In motion influence map the feature extraction, a block
    where an unordinary action happens, alongside its neighbouring blocks, has distinctive vectors of motion
    influence. Megablock is created out of that.Then clustering of megablocks is performed using the spatio-
    temporal highlights and set the focuses as codewords.
    •
    4)Frame and Pixel level detection for Abnormal Activities:If the most elevated value of the minimum-distance
    matrix is bigger than the edge, we group the current frame as abnormal.The smaller the estimation of an
    element,the less likely an irregular movement is to happen in the individual block.

    20XX presentation title


    Literature Review:
    Title:Suspicious human activity detection

    Video Analytics, also referred to as Video Content Analysis (VCA), is a generic term
    used to describe computerized processing and analysis of video streams. Before
    detecting the human activities from a video input,first the object is detected by frame
    difference, background elimination and background registration techniques. Post
    processing techniques are used to increase the clarity of the frame obtained. The noises
    in the frames are removed by using the Gaussian filter approach. Background
    subtraction and histogram of gradients technique is used for detecting the presence or
    absence of a human. The detection of human motion can be done by several other
    methods. One such method is the motion estimation map. It is used to estimate the
    motion of humans in a surveillance video.In this paper Canny Edge Detection algorithm
    is used to detect the edges in a image.The faces of the persons in the processed frame
    have to be identified. This is done by using the Surf features approach.

    20XX presentation title


    References:
    [1] Attard, L., & Farrugia, R. A. (2011, April). Vision based
    surveillance system. In 2011 IEEE EUROCON-International
    Conference on Computer as a Tool (pp. 1-4). IEEE.
    [2] Khan, K., Albattah, W., Khan, R. U., Qamar, A. M., & Nayab, D.
    (2020). Advances and trends in real time visual crowd analysis.
    Sensors, 20(18), 5073. Click icon to add picture
    [3] Gnouma, M., Ejbali, R., & Zaied, M. (2018). Abnormal events’
    detection in crowded scenes. Multimedia Tools and
    Applications, 77(19), 24843-24864.
    [4] Rodriguez, M. D., & Shah, M. (2007, September). Detecting and
    segmenting humans in crowded scenes. In Proceedings of the 15th
    ACM international conference on Multimedia (pp. 353-356)

    20XX presentation title


    thank you

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy