1 / 15

Security Tracker by

Security Tracker by. Jered Olckers SUPERVISOR: MR. J. CONNAN. The system is used to track a Person across multiple frames using fixed input source. Project Overview. Requirement Analysis High Level Design Implementation Testing & Results User Manual Demonstration. Introduction.

cece
Télécharger la présentation

Security Tracker by

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Security Trackerby Jered Olckers SUPERVISOR: MR. J. CONNAN

  2. The system is used to track a Person across multiple frames using fixed input source Project Overview

  3. Requirement Analysis • High Level Design • Implementation • Testing & Results • User Manual • Demonstration Introduction

  4. At least one camera’s connected to a PC • High mega pixel camera • A camera with at least 2mega pixel is required. Requirement Analysis 1.3MP 2MP Low quality Better quality • Camera should be in a indoor environment

  5. Flow Chart Extract Frames Frame differencing Display Results High Level Design detect skin Compare Frames To Find and Section person into head, body, legs

  6. Identification procedure • Location of the Face and hands is found using skin colour • Size of the face is used as a reference for the size of the rest of the body • From this body proportions is used to determine the position of upper body and legs. • The body is then divided into 3 areas • Head, upper-body and lower-body • For each area the sum of the pixel values is averaged and later used for comparison. Implementation

  7. Reference Frame Head value Upper body value Implementation 2 Legs value Match No match False Positive

  8. Test Case 1 • Testing the user interface. • Test Case 2 • Testing accuracy in people of different and the same skin colour. • Test Case 3 • Testing the system in a security scenario. Testing

  9. Testing the user interface Feedback • Users had a problem with frame delay and jitter. • By optimizing the thread will solve this problem • Some users wanted identification notification. • Sound and graphical notification was added. Test Case 1

  10. Testing the user interface Test Case 1 Match found message box added

  11. Testing accuracy in different skin colour. • Greater difference in skin colour result in more • accurate and faster identification • A more evenly matched skin colour will rely • more on cloths the person is wearing. Test Case 2

  12. Testing the system in a security scenario. Description • A Camera was placed above the entrance • doorway of the honours lab. • The system was then started. • Result • Different people was used for identification. • The system worked well. Test Case 3

  13. Testing the system in a security senario. Mounted webcam Test Case 3 Found Match

  14. Mini-User Manual User Manual

  15. Skin Detection in Luminance Images using Threshold Technique: Hani. K. Almohair, Abd Rahman Ramli, Elsadig A. M, Shaiful J. Hashim • A Robust Vision-based Moving Target Detection and Tracking System. • Frame-skipping tracking for single object with global motion detection!: Ming Anlong, Ma Huadong References Demo

More Related