Site Loader
Rock Street, San Francisco

INTRUDER DETECTION SYSTEM USING IOT BLUEMIX Submitted in partial fulfilment for the award of the degree of M.S. In Software Engineering (Integrated) by P.V. INDU BHANU – 13MSE0047 Under the guidance of PROF. SRINIVAS KOPPU Assistant Professor (Senior) School of Information Technology and Engineering April 2018 DECLARATION I here by declare that the thesis entitled Optic Disc Localization in Retinal Images Based on Cumulative Sumfields submitted by me, for the award of the degree of Specify the name of the degree VIT is a record of bonafide work carried out by me under the supervision of Prof.Srinivas koppu I further declare that the work reported in this thesis has not been submitted and will not be submitted, either in part or in full, for the award of any other degree or diploma in this institute or any other institute or university. Place Vellore Date 27/04/2018 Signature of the Candidate P.V. Indu BhanuCERTIFICATE This is to certify that the thesis entitled Optic Disc Localization In Retinal Images Based On Cumulative Sumfields submitted by P.V. Indu Bhanu (13MSE0047) SITE VIT, for the award of the M.S is a record of bonafide work carried out by him/her under my supervision. The contents of this report have not been submitted and will not be submitted either in part or in full, for the award of any other degree or diploma in this institute or any other institute or university. The Project report fulfils the requirements and regulations of VIT and in my opinion meets the necessary standards for submission. Signature of the Guide Signature of the Hod Internal Examiner External Examiner CONTENTS CONTENTS ………………………………………………………………………………………………………4 LIST OF FIGURES …………………………………………………………………………………………….6 LIST OF TABLES ………………………………………………………………………………………………7 LIST OF ACRONYMS ……………………………………………………………………………………….8 ABSTRACT . 9 CHAPTER 1 INTRODUCTION 1.1 INTRODUCTION …………………………………………………………………………………………10 1.2 OVERVIEW ……………………………………………………………. 10 1.3 CHALLENGES …………………………………………………………….11 1.4 PROJECT STATEMENT …………………………………………………………………………….. 11 1.5 OBJECTIVES ……………………………………………………………………………………………….11 1.6 SCOPE OF THE PROJECT …………………………………………………………………………… 12 CHAPTER 2 BACK GROUND 2.1 INTRODUCTION …………………………………………………………………………………………13 2.2 LITERATURE SURVEY ……………………………………………………………………………… 13 2.3 ASSUMPTIONS ………………………………………………………………………………………….. 15 2.4 ORGANISATION OF REPORT …………………………………………………………………… 15 2.5 DRAWBACKS OF EXISTING SYSTEM ……… ……………………………………………… 16 2.6 REQUIREMENTS …………………………………………………………………………………………17 CHAPTER 3 SYSTEM DESIGN 3.1 SYSTEM ARCHITECTURE ………………………………………………………………………… 18 3.2 MODULE DESCRIPTION ……………………………………………………………………………19 3.3 DETAILED DESIGN…………………………………………………………………………………… 21 3.3.1 USECASE DIAGRAM…………………………………………………………………………. 21 3.3.2 CLASS DIAGRAM……………………………………………………………………………….22 3.3.3 ACTIVITY DIAGRAM………………………………………………………………………… 23 CHAPTER 4 IMPLEMENTATION AND TESTING 4.1 IMPLEMENTATION STRATEGY ……………………………………………………………….. 24 4.2 IMPLEMENTATION……………………………………………………………………………………. 25 4.3 TOOLS, TECHNIQUES METHODOLOGY……………………………………………….. 26 4.4 TESTING METHODS…………………………………………………………………………………… 27 4.4.1 MOTION DETECTION ……………………………………………………………………….. 27 4.4.2 CAPTURE IMAGE ……………………………………………………………………………… 28 4.4.3 EMAIL SERVICE……………………………………………………………………………….. 29 4.4.4 IMAGE CLASSIFICATION …………………………………………………………………. 30 CHAPTER 5 CODING 5.1 SAMPLE CODE…………………………………………………………………………………………… 31 5.2 SCREENSHOTS……………………………………………………………………………………………66 CHAPTER 6 RESULTS AND DISCUSSIONS 6.1 RESULTS……………………………………………………………………………………………………. 82 6.2 CONCLUSION……………………………………………………………………………………………. 82 6.2 FUTURE WORK………………………………………………………………………………………….. 83 CHAPTER 7 REFERENCES 7.1 REFERENCES……………………………………………………………………………………………… 84 LIST OF FIGURES Fig 3.1 SYSTEM ARCHITECTURE……………………………………………………………………. 10 Fig 3.3.1 USECASE DIAGRAM……………………………………………………………………….12 Fig 3.3.2 CLASS DIAGRAM……………………………………………………………………. 13 Fig 3.3.3 ACTIVITY DIAGRAM………………………………………………………………………14 LIST OF TABLES Table 4.5.1 MOTION DETECTION……………………………………………………………………. 10 Table 4.5.2 CAPTURE IMAGE………………………………………………………………………….. 10 Table 4.5.3 EMAIL SERVICE……………………………………………………………………………. 10 Table 4.5.4 IMAGE CLASSIFICATION……………………………………………………………… 10 LIST OF ACRONYMS PIR sensor Passive Infrared sensor SMS Short Message Service IoT Internet of Things IBM International Business Machines corporation ABSTRACT This project helps in identifying the properties of an image which will be used to identify the nature of an image. This project includes in setting up a system where you can get SMS to your mobile or an email with an attachment file containing the photo of a person who has visited your house by using smartphone as IP-Camera, Raspberry Pi and a PIR sensor, Node-Red programming tool, Watsons Visual recognition tool, and Twilio or SendGrid for Email service. Here an old smartphone is used as an IP-Camera. It is connected to a local network with the help of a Raspberry Pi which allows us to capture a snapshot at any moment when a motion occurs. Decision of when to capture the snapshot is determined with the help of PIR sensor. We use Node-RED visual programming tool which takes the help of IBM Watson by making use of its services through nodes. IBM Watsons visual recognition service firstly detects a face and the executes other command based on the response obtained from Watson. Twilio or SendGrid are used in the project which allows us to send SMS to a number or multiple numbers that someone is at the door step and an email service which allows us to send an email containing the picture of the person visited the home. CHAPTER 1 INTRODUCTION INTRODUCTION Here, the complete image processing computations are done by Watson, and we set up Raspberry Pi which is connected to Bluemix IOT platform service and it doesnt do any image processing. IBM Bluemix allows users to understand the content of images and classify images into logical categories. For instance consider we upload the images for certain areas, we can create a custom classifier and can get crowded ratio which we will be used for finding routes and we can also find gender of people if number of people in image are comparatively less and that can also be used for increasing efficiency. 1.2 SYSTEM OVERVIEW Intrusion Detection System is currently being able to sense the motion of objects and take a picture. The objects in the picture are identified and the user is alerted if there is a person in the picture. This existing setup can be used in cases where the user must leave their home for a long period of time. The device when setup and switched on, connects to the cloud provided to the user to manage all their devices. The activity of a device is stored in the cloud and the user can access it from remotely anywhere in the world. The proposed system helps in solving the problem of taking action against the intruder visiting the home when you are not available at home. It also helps the user to monitor their home remotely which increases the security of the users home with less expensive equipment unlike security cameras, storage devices etc. instead we just use email services, IBM cloud for storage and an old smart phone as an IP-Camera. 1.3 CHALLENGES The images which we get are not so accurate, we need to increase the quality of images by enhancing images. Basically, the idea behind enhancement techniques is to bring out detail that is obscured, or simply to highlight certain features of interest in an image. We use cloud IOT platforms like IBM Watson and messaging services like SendGrid or Node-RED and hence reducing the amount of Physical storage required and also increasing the overall performance of the system. 1.4 PROBLEM STATEMENT With the increasing volume of users using internet there is a need for identifying certain attributes of the user so that data quality could be quite good. Images are now one of the key enablers of users connectivity. Accuracy of attribute information retrieved from images are quite low when compared to processing from Bluemix. The information can not only be used for identifying gender but also for predicting accidents in certain area, so before any accident happens we can predict it. The aggregated information can result in unexpected exposure of ones social environment and lead to abuse of ones personal information. The main aim is to collect the quality data and increase target marketing which will be used to reduce cost to a great extent. 1.5 OBJECTIVE Existing systems tend to perform the face detection using complex systems like MATLAB and SIMULINK where the load on the required system is too high. It also requires us to install these software that are licensed on the Raspberry Pi which increases the storage capacity required on the Pi. To encounter these issues, we use cloud IOT platforms like IBM Watson and messaging services like SendGrid or Node-RED and hence reducing the amount of Physical storage required and also increasing the overall performance of the system. The proposed system helps in solving the problem of taking action against the intruder visiting the home when you are not available at home. It also helps the user to monitor their home remotely which increases the security of the users home with less expensive equipment unlike security cameras, storage devices etc. instead we just use email services, IBM cloud for storage and an old smart phone as an IP-Camera. 1.6 SCOPE The main aim of the project is to detect the intruder which includes in setting up a system where the users can get SMS to their mobile or an email with an attachment file containing the photo of a person who has visited their house by using smartphone as IP-Camera, Raspberry Pi and a PIR sensor, Node-Red programming tool, IBM Watson, and Twilio or SendGrid or Node-RED for Email service. Advantages Provides user an opportunity to monitor the home remotely which increases the security. The system easy to setup and doesnt use expensive equipment like security cameras, storage devices etc. CHAPTER 2 BACKGROUND 2.1 INTRODUCTION Various techniques have been developed in Image Processing during the last four to five decades. Most of the techniques are developed for enhancing images obtained from unmanned spacecrafts, space probes and military reconnaissance flights. Image Processing is a technique to enhance raw images received from cameras/sensors placed on satellites, space probes and aircrafts or pictures taken in normal day-to-day life for various applications11. Image Processing systems are becoming popular due to easy availability of powerful personnel computers, large size memory devices, graphics softwares etc. The IBM Watson Visual Recognition service uses deep learning algorithms to analyze images (.jpg, or .png) for scenes, objects, faces, and other content, and return keywords that provide information about that content13. 2.2 LITERATURE SURVEY Generally people are curious to know who had arrived at their doorstep when they were away from home and it would be good to receive a notification when someone arrives at the doorstep or if some activity is detected using image processing and some messaging service. Image Processing is a technique to enhance raw images received from cameras/sensors placed on satellites, space probes and aircrafts or pictures taken in normal day-to-day life for various applications11. Image processing has changed warfare in the last decade with remote piloted drone aircrafts being able to get images which were transmitted and analysed remotely. We use Watson visual recognition for image processing. Watson uses Deepqa which is a software architecture for deep content analysis and evidence-based reasoning that embodies that philosophy. The overarching principles in Deepqa are massive parallelism, many experts, pervasive confidence estimation, and integration of shallow and deep knowledge12. The first step in any application of Deepqa to solve a qa problem is content acquisition, or identifying and gathering the content to use for the answer and evidence sources3. Content acquisition is a combination of manual and automatic steps. The first step is to analyse example questions from the problem space to produce a description of the kinds of questions that must be answered and a characterization of the application domain. Analyzing example questions is primarily a manual task, while domain analysis may be informed by automatic or statistical analyses. Given the kinds of questions and broad domain of the Jeopardy Challenge, the sources for Watson include a wide range of encyclopedias, dictionaries, thesauri, newswire articles, literary works, and so on.Given a reasonable baseline corpus, Deepqa then applies an automatic corpus expansion process. The process involves four high-level steps (1) identify seed documents and retrieve related documents from the web (2) extract self-contained text nuggets from the related web documents (3) score the nuggets based on whether they are informative with respect to the original seed document and (4) merge the most informative nuggets into the expanded corpus. The live system itself uses this expanded corpus and does not have access to the web during play. In addition to the content for the answer and evidence sources, Deepqa leverages other kinds of semi structured and structured content. Another step in the content-acquisition process is to identify and collect these resources, which include databases, taxonomies, and ontologies, such as dbPedia8, WordNet and the Yago ontology. The first step in the run-time question-answering process is question analysis. During question analysis the system attempts to understand what the question is asking and performs the initial analyses that determine how the question will be processed by the rest of the system. The DeepQA approach encourages a mixture of experts at this stage, and in the Watson system we produce shallow parses12,deep parses, logical forms, semantic role labels, co reference, relations, named entities, and so on, as well as specific kinds of analysis for question answering. Most of these technologies are well understood and are not discussed here, but a few require some elaboration. Question classification is the task of identifying question types or parts of questions that require special processing. This can include anything from single words with potentially double meanings to entire clauses that have certain syntactic, semantic, or rhetorical functionality that may inform downstream components with their analysis. Question classification may identify a question as a puzzle question, a math question, a definition question, and so on. It will identify puns, constraints, definition components, or entire sub clues within questions. 2.3 ASSUMPTIONS The images we capture from IP-Camera when a motion is detected should be highly contrasted so that we can have a better classification of images. Currently we are using images for classification purpose only, in future will try to make data prediction for the classified data from Bluemix which can make more productivity with less image processing. 2.4 ORGANIZATION OF REPORT The report is organized in the following way. What follows is the literature review of the previous works in the image and data processing. Then, the design and setup of the system is explained. The details about implementation of the proposed image, data processing techniques are explained in the section after design. The results and discussion of the future works, and the conclusions drawn are all explained in the further sections 2.5 DRAWBACK OF EXISTING SYSTEM Existing systems tend to perform the face detection using complex systems like MATLAB and SIMULINK where the load on the required system is too high. It also requires us to install these software that are licensed on the Raspberry Pi which increases the storage capacity required on the Pi. To encounter these issues, we use cloud IOT platforms like IBM Watson and messaging services like SendGrid or Node-RED and hence reducing the amount of Physical storage required and also increasing the overall performance of the system. The enhancements on this system use the likes of advanced and lightweight technologies that help in the easier detection of faces and also reduce the overall cost due to the use of Open Source Services that are widely available these days. 2.6 SYSTEM REQUIREMENTS HARDWARE REQUIREMENTS SystemIntel or AMD x86-64 processorRAM512 mb.HardDisk 80 GBSensorsPIR sensor Raspberry PI WiFi router Old Smart phone or IP-Camera SOFTWARE REQUIREMENTS LanguagesPython, JsonTechnologiesRaspberry PI(VNC viewer), Node-RED,IBM Watson.Operating systemWindows XP/ 7/ 8/8.1/10 CHAPTER 3 SYSTEM DESIGN 3.1 Architecture Diagram Fig 3.1 System Architecture Diagram 3.2 Module Description Setting up Smartphone as IP Camera Here in this module, we used a smartphone which acts as an IP-Camera which is controlled using Raspberry Pi where both smartphone and Raspberry pi are connected to the same local network(Router). Firstly, we used an application called IP Webcam where all we need to do is to be able to get an image from the camera at any instance. Motion detection using PIR sensor The PIR sensor is used for motion detection which is used in our project to capture snapshots from the IP-Camera only when activity is detected in front of the door. As soon as the image is captured using IP Webcam and then the digital status of the output pin of PIR sensor can be seen in Node Red page. When the motion is detected it sends a digital signal which is taken as an input to Raspberry Pi. As soon as a signal is detected , the flow in the Node-Red program halts for 5 seconds. Visual recognition The Visual Recognition services comes with a set of built-in classes so that you can analyse images with high accuracy right out of the box. You can also train custom classifiers to create specialized classes, and create custom collections to search for similar images. In this project, the visual recognition is done using IBM Watson. Here the image which is captured using IP Webcam is given as an input to IBM Watson and the result obtained by Watsons analysis is displayed. Based on the result we can known if a person is detected in the image or if something else is detected in the image. Emailing service using Twilio or SendGrid Email can also act as a cloud storage which stores all the images captured using IP-Webcam. In this way we can avoid the problem of saving long duration videos captured from the camera to detect activities. Images will be captured whenever a motion or activity is detected so there is no need to buy large capacity storage devices to save data. Here, we are using Twilio or SendGrid messaging service for emailing the image as a file to the user. 3.3 Detailed Design 3.3.1 Use Case Diagram Fig 3.3.1 Use case Diagram 3.3.2 Class Diagram Fig3.3.2 Class Diagram 3.3.3 Activity Diagram Fig3.3.3 Activity Diagram 4. IMPLEMENTATION AND TESTING 4.1 IMPLEMENTATION STRATEGY MODULAR DESCRIPTION Implementation is the stage of the project when the theoretical design is turned out into a working system. Thus it can be considered to be the most critical stage in achieving a successful new system and in giving the user, confidence that the new system will work and be effective. The implementation stage involves careful planning, investigation of the existing system and its constraints on implementation, designing of methods to achieve changeover and evaluation of changeover methods. MODULES Setting up Smartphone as IP Camera Motion detection using PIR sensor Visual recognition Emailing service using Twilio or SendGrid or Node-RED MODULES DESCRIPTION Setting up Smartphone as IP Camera Here in this module, we used a smartphone which acts as an IP-Camera which is controlled using Raspberry Pi where both smartphone and Raspberry pi are connected to the same local network(Router). Firstly, we used an application called IP Webcam where all we need to do is to be able to get an image from the camera at any instance. Motion detection using PIR sensor The PIR sensor is used for motion detection which is used in our project to capture snapshots from the IP-Camera only when activity is detected in front of the door. As soon as the image is captured using IP Webcam and then the digital status of the output pin of PIR sensor can be seen in Node Red page. When the motion is detected it sends a digital signal which is taken as an input to Raspberry Pi. As soon as a signal is detected , the flow in the Node-Red program halts for 5 seconds. Visual recognition The Visual Recognition services comes with a set of built-in classes so that you can analyse images with high accuracy right out of the box. You can also train custom classifiers to create specialized classes, and create custom collections to search for similar images. In this project, the visual recognition is done using IBM Watson. Here the image which is captured using IP Webcam is given as an input to IBM Watson and the result obtained by Watsons analysis is displayed. Based on the result we can known if a person is detected in the image or if something else is detected in the image. Emailing service using Twilio or SendGrid or Node-RED Email can also act as a cloud storage which stores all the images captured using IP-Webcam. In this way we can avoid the problem of saving long duration videos captured from the camera to detect activities. Images will be captured whenever a motion or activity is detected so there is no need to buy large capacity storage devices to save data. Here, we are using Twilio or SendGrid or Node-RED messaging service for emailing the image as a file to the user. 4.2 IMPLEMENTATION Usually every software maintains the SDLC that is nothing but Software Development Life Cycle. It is a standard which is used by software industry to develop good software. This project includes in setting up a system where you can get SMS to your mobile or an email with an attachment file containing the photo of a person who has visited your house by using smartphone as IP-Camera, Raspberry Pi and a PIR sensor, Node-Red programming tool, Watsons Visual recognition tool, and Twilio or SendGrid for Email service. Here an old smartphone is used as an IP-Camera. It is connected to a local network with the help of a Raspberry Pi which allows us to capture a snapshot at any moment when a motion occurs7. Decision of when to capture the snapshot is determined with the help of PIR sensor. We use NODE-RED visual programming tool which takes the help of IBM Watson by making use of its services through nodes2. IBM Watsons visual recognition service firstly detects a face and the executes other command based on the response obtained from Watson. Twilio or SendGrid are used in the project which allows us to send SMS to a number or multiple numbers that someone is at the door step and an email service which allows us to send an email containing the picture of the person visited the home9. Here, the complete image processing computations are done by Watson, and we set up Raspberry Pi which is connected to Bluemix IOT platform service and it doesnt do any image processing. IBM Bluemix allows users to understand the content of images and classify images into logical categories5. 4.3 TOOLS, TECHNIQUES AND METHODOLOGY The Detection System is built using IoT and Image Processing technologies. Here, we made use of Raspberry PI, Node-RED and IBM Watson. Here, the very first module of capturing image with an old smart phone is done in python using Raspberry PI tool and Raspbian Jessie OS. In the next modules, we use Node-RED programming tool to send the data or images to e-mail or IBM cloud where nodes in Node-RED can either be imported using Json code or can even be dragged and dropped and the can be fed with necessary code(Json, HTML, JavaScript etc.)10. E-mail service can be used to notify the user with an attachment containing the image of the intruder. We also use IBM Watson to analyse the image and classify the data from the image. 4.4 TESTING METHODS 4.4.1 MODULE NAME MOTION DETECTION SNOTEST CASE DESCRIPTIONEXPECTED RESULTACTUAL RESULTSTATUS REMARKS1Detecting motion using PIR sensorDetects motionMotion detected successfully PASS Objects sensed successfully2Detecting motion using PIR sensorDetects motionMotion not detected FAIL Object not sensed successfully3Detecting motion using PIR sensorDetects motionMotion detected but object not sensed FAILObject sensed but doesnt detect motion.4Detecting motion using PIR sensorDetects motionObject not sensed but motion detected FAILObject not sensed but detects motion Table 4.4.1 4.4.2 MODULE NAME CAPTURE IMAGE SNOTEST CASE DESCRIPTIONEXPECTED RESULTACTUAL RESULTSTATUS REMARKS1Capturing images using IP WebcamCaptures imageImage captured successfully PASSImage captured in smart phone and stored in Raspberry PI2Capturing images using IP WebcamCaptures imageImage not captured successfully FAILImage is not captured in smart phone3Capturing images using IP WebcamCaptures imageImage captured but not stored in PI FAILImage captured in smart phone but is not stored in Raspberry PI Table 4.4.2 4.4.3 MODULE NAME EMAIL SERVICE SNOTEST CASE DESCRIPTIONEXPECTED RESULTACTUAL RESULTSTATUS REMARKS1 Send email with an image attachmentEmail sent successfullyEmail sent successfully PASSEmail is sent with image as an attachment file2 Send email with an image attachmentEmail sent successfullyEmail is not sent successfully FAILEmail is not sent to the user3 Send email with an image attachmentEmail sent successfullyEmail sent successfully FAILEmail is sent but image is not attached in the file4 Send email with an image attachmentEmail sent successfullyEmail sent successfully FAILEmail is sent but attachment file is missing Table 4.4.3 4.4.4 MODULE NAME IMAGE CLASSIFICATION SNOTEST CASE DESCRIPTIONEXPECTED RESULTACTUAL RESULTSTATUS REMARKS1 Send image to IBM Watson and classify dataImage sent successfullyImage sent successfully PASSImage is sent to Watson and data is classified 2 Send image to IBM Watson and classify dataImage sent successfullyImage not sent successfully FAILImage is not sent to Watson for classification3 Send image to IBM Watson and classify dataImage sent successfullyImage sent successfully FAILImage is sent to Watson but is missing4 Send image to IBM Watson and classify dataImage sent successfullyImage sent successfully FAILImage is sent to Watson but data is not classified properly Table 4.4.4 CHAPTER 6 IMPLEMENTATION 5.1 SAMPLE CODE STEP 1 CAMERA MODULE sudo nano review.py import os os.system(wget 192.168.1.1248080/photo.jpg) ctrlx Y python review.py STEP 2 PIR MOTION SENSOR MOTION MODULE import RPi.GPIO as GPIO import time GPIO.setwarnings(False) GPIO.setmode(GPIO.BOARD) GPIO.setup(3, GPIO.OUT) while True GPIO.output(3,1) time.sleep(1) GPIO.output(3,0) time.sleep(1) STEP 3 NODE-RED MODULE An example node-red flow id 41e935d1.d2619c, type inject, z d100b337.680e88, name , topic , payload , payloadType date, repeat 5, crontab , once true, x 205, y 178.5, wires 8332d581.5c7d58 , id 8332d581.5c7d58, type exec, z d100b337.680e88, command vcgencmd, addpay false, append measure_temp, useSpawn , name getCPUtemp, x 422, y 257, wires 8508a722.f6e4c8, 975b7227.de75a8, , , id 8508a722.f6e4c8, type debug, z d100b337.680e88, name , active true, console false, complete payload, x 711, y 177, wires , id 975b7227.de75a8, type function, z d100b337.680e88, name msg.payload, func msg.payload dtempmsg.payload.replace(temp,).replace(Cn,)nreturn msg, outputs 1, noerr 0, x 472, y 363.5, wires 8508a722.f6e4c8, ec819393.e13098 , id ec819393.e13098, type wiotp out, z d100b337.680e88, authType d, qs true, qsDeviceId e1f1bfcf.0fae18, deviceKey , deviceType , deviceId , event event, format json, name , x 811, y 303, wires STEP 4 USER INTERFACE FOR A CLIENT DOCTYPE html html head meta charsetutf-8 meta nameviewport contentwidthdevice-width, initial-scale1 titleLumino – Login/title link hrefcss/bootstrap.min.css relstylesheet link hrefcss/datepicker3.css relstylesheet link hrefcss/styles.css relstylesheet –if lt IE 9 script srcjs/html5shiv.js/script script srcjs/respond.min.js/script endif– /head body div classrow div classcol-xs-10 col-xs-offset-1 col-sm-8 col-sm-offset-2 col-md-4 col-md-offset-4 div classlogin-panel panel panel-default div classpanel-headingLog in/div div classpanel-body form roleform fieldset div classform-group input classform-control placeholderE-mail nameemail typeemail autofocus /div div classform-group input classform-control placeholderPassword namepassword typepassword value /div div classcheckbox label input nameremember typecheckbox valueRemember MeRemember Me /label /div a hrefindex.html classbtn btn-primaryLogin/a/fieldset /form /div /div /div– /.col– /div– /.row — script srcjs/jquery-1.11.1.min.js/script script srcjs/bootstrap.min.js/script /body /html DOCTYPE html html head meta charsetutf-8 meta nameviewport contentwidthdevice-width, initial-scale1 titleDashboard/title link hrefcss/bootstrap.min.css relstylesheet link hrefcss/font-awesome.min.css relstylesheet link hrefcss/datepicker3.css relstylesheet link hrefcss/styles.css relstylesheet –Custom Font– link hrefhttps//fonts.googleapis.com/cssfamilyMontserrat300,300i,400,400i,500,500i,600,600i,700,700i relstylesheet –if lt IE 9 script srcjs/html5shiv.js/script script srcjs/respond.min.js/script endif– /head body nav classnavbar navbar-custom navbar-fixed-top rolenavigation div classcontainer-fluid div classnavbar-header button typebutton classnavbar-toggle collapsed data-togglecollapse data-targetsidebar-collapsespan classsr-onlyToggle navigation/span span classicon-bar/span span classicon-bar/span span classicon-bar/span/button a classnavbar-brand hrefspanIDS/span/a ul classnav navbar-top-links navbar-right li classdropdowna classdropdown-toggle count-info data-toggledropdown href em classfa fa-bell/emspan classlabel label-info5/span /a ul classdropdown-menu dropdown-alerts lia href divem classfa fa-envelope/em 1 New Message span classpull-right text-muted small3 mins ago/span/div /a/li li classdivider/li lia href divem classfa fa-user/em 5 New Events span classpull-right text-muted small4 mins ago/span/div /a/li /ul /li /ul /div /div– /.container-fluid — /nav div idsidebar-collapse classcol-sm-3 col-lg-2 sidebar div classprofile-sidebar div classprofile-userpic img srchttp//placehold.it/50/30a5ff/fff classimg-responsive alt /div div classprofile-usertitle div classprofile-usertitle-nameUsername/div div classprofile-usertitle-statusspan classindicator label-success/spanOnline/div /div div classclear/div /div div classdivider/div form rolesearch div classform-group input typetext classform-control placeholderSearch /div /form ul classnav menu li classactivea hrefindex.htmlem classfa fa-dashboardnbsp/em Dashboard/a/li lia hrefcharts.htmlem classfa fa-bar-chartnbsp/em Recent Activity/a/li lia hrefpanels.htmlem classfa fa-clonenbsp/em My Devices/a/li lia hreflogin.htmlem classfa fa-power-offnbsp/em Logout/a/li /ul /div–/.sidebar– div classcol-sm-9 col-sm-offset-3 col-lg-10 col-lg-offset-2 main div classrow ol classbreadcrumb lia href em classfa fa-home/em /a/li li classactiveDashboard/li /ol /div–/.row– div classrow div classcol-lg-12 h1 classpage-headerDashboard/h1 /div /div–/.row– div classrow div classcol-md-6 div classpanel panel-default chat div classpanel-heading Chat ul classpull-right panel-settings panel-button-tab-right li classdropdowna classpull-right dropdown-toggle data-toggledropdown href em classfa fa-cogs/em /a /li /ul span classpull-right clickable panel-toggle panel-button-tab-leftem classfa fa-toggle-up/em/span/div div classpanel-body ul li classleft clearfixspan classchat-img pull-left img srchttp//placehold.it/60/30a5ff/fff altUser Avatar classimg-circle / /span div classchat-body clearfix div classheaderstrong classprimary-fontUsername/strong small classtext-muted32 mins ago/small/div pHi, this is a test message./p /div /li li classright clearfixspan classchat-img pull-right img srchttp//placehold.it/60/dde0e6/5f6468 altUser Avatar classimg-circle / /span div classchat-body clearfix div classheaderstrong classpull-left primary-fontSupport/strong small classtext-muted30 mins ago/small/div pHi, how may we help you/p /div /li li classleft clearfixspan classchat-img pull-left img srchttp//placehold.it/60/30a5ff/fff altUser Avatar classimg-circle / /span div classchat-body clearfix div classheaderstrong classprimary-fontUsername/strong small classtext-muted28 mins ago/small/div pThank you/p /div /li /ul /div div classpanel-footer div classinput-group input idbtn-input typetext classform-control input-md placeholderType your message here… /span classinput-group-btn button classbtn btn-primary btn-md idbtn-chatSend/button /span/div /div /div /div–/.col– div classcol-md-6 div classpanel panel-default div classpanel-heading Timeline ul classpull-right panel-settings panel-button-tab-right li classdropdowna classpull-right dropdown-toggle data-toggledropdown href em classfa fa-cogs/em /a /li /ul span classpull-right clickable panel-toggle panel-button-tab-leftem classfa fa-toggle-up/em/span/div div classpanel-body timeline-container ul classtimeline li div classtimeline-badge primaryem classglyphicon glyphicon-link/em/div div classtimeline-panel div classtimeline-heading h4 classtimeline-titleE-mail Sent/h4 /div div classtimeline-body pAn E-mail has been sent to your registered address regarding the most recent activity./p /div /div /li li div classtimeline-badgeem classglyphicon glyphicon-camera/em/div div classtimeline-panel div classtimeline-heading h4 classtimeline-titleIntruder Detected/h4 /div div classtimeline-body pAn image of the intruder has been captured and will be sent to you shortly./p /div /div /li /ul /div /div /div–/.col– /div–/.row– /div –/.main– script srcjs/jquery-1.11.1.min.js/script script srcjs/bootstrap.min.js/script script srcjs/chart.min.js/script script srcjs/chart-data.js/script script srcjs/easypiechart.js/script script srcjs/easypiechart-data.js/script script srcjs/bootstrap-datepicker.js/script script srcjs/custom.js/script /body /html DOCTYPE html html head meta charsetutf-8 meta nameviewport contentwidthdevice-width, initial-scale1 titleRecent Activity/title link hrefcss/bootstrap.min.css relstylesheet link hrefcss/font-awesome.min.css relstylesheet link hrefcss/datepicker3.css relstylesheet link hrefcss/styles.css relstylesheet –Custom Font– link hrefhttps//fonts.googleapis.com/cssfamilyMontserrat300,300i,400,400i,500,500i,600,600i,700,700i relstylesheet –if lt IE 9 script srcjs/html5shiv.js/script script srcjs/respond.min.js/script endif– /head body nav classnavbar navbar-custom navbar-fixed-top rolenavigation div classcontainer-fluid div classnavbar-header button typebutton classnavbar-toggle collapsed data-togglecollapse data-targetsidebar-collapsespan classsr-onlyToggle navigation/span span classicon-bar/span span classicon-bar/span span classicon-bar/span/button a classnavbar-brand hrefspanIDS/span/a ul classnav navbar-top-links navbar-right li classdropdowna classdropdown-toggle count-info data-toggledropdown href em classfa fa-bell/emspan classlabel label-info5/span /a ul classdropdown-menu dropdown-alerts lia href divem classfa fa-envelope/em 1 New Message span classpull-right text-muted small3 mins ago/span/div /a/li li classdivider/li lia href divem classfa fa-user/em 5 New Events span classpull-right text-muted small4 mins ago/span/div /a/li /ul /li /ul /div /div– /.container-fluid — /nav div idsidebar-collapse classcol-sm-3 col-lg-2 sidebar div classprofile-sidebar div classprofile-userpic img srchttp//placehold.it/50/30a5ff/fff classimg-responsive alt /div div classprofile-usertitle div classprofile-usertitle-nameUsername/div div classprofile-usertitle-statusspan classindicator label-success/spanOnline/div /div div classclear/div /div div classdivider/div form rolesearch div classform-group input typetext classform-control placeholderSearch /div /form ul classnav menu li classactivea hrefindex.htmlem classfa fa-dashboardnbsp/em Dashboard/a/li lia hrefcharts.htmlem classfa fa-bar-chartnbsp/em Recent Activity/a/li lia hrefpanels.htmlem classfa fa-clonenbsp/em My Devices/a/li lia hreflogin.htmlem classfa fa-power-offnbsp/em Logout/a/li /ul /div–/.sidebar– div classcol-sm-9 col-sm-offset-3 col-lg-10 col-lg-offset-2 main div classrow ol classbreadcrumb lia href em classfa fa-home/em /a/li li classactiveRecent Activity/li /ol /div–/.row– div classrow div classcol-lg-12 h1 classpage-headerRecent Activity/h1 /div /div–/.row– div classrow div classcol-lg-12 div classpanel panel-default div classpanel-heading Line Chart ul classpull-right panel-settings panel-button-tab-right li classdropdowna classpull-right dropdown-toggle data-toggledropdown href em classfa fa-cogs/em /a /li /ul span classpull-right clickable panel-toggle panel-button-tab-leftem classfa fa-toggle-up/em/span/div div classpanel-body div classcanvas-wrapper canvas classmain-chart idline-chart height200 width600/canvas /div /div /div /div /div–/.row– div classrow div classcol-lg-12 div classpanel panel-default div classpanel-heading Bar Chart ul classpull-right panel-settings panel-button-tab-right li classdropdowna classpull-right dropdown-toggle data-toggledropdown href em classfa fa-cogs/em /a /li /ul span classpull-right clickable panel-toggle panel-button-tab-leftem classfa fa-toggle-up/em/span/div div classpanel-body div classcanvas-wrapper canvas classmain-chart idbar-chart height200 width600/canvas /div /div /div /div /div–/.row– div classrow div classcol-md-6 div classpanel panel-default div classpanel-heading Pie Chart ul classpull-right panel-settings panel-button-tab-right li classdropdowna classpull-right dropdown-toggle data-toggledropdown href em classfa fa-cogs/em /a /li /ul span classpull-right clickable panel-toggle panel-button-tab-leftem classfa fa-toggle-up/em/span/div div classpanel-body div classcanvas-wrapper canvas classchart idpie-chart /canvas /div /div /div /div div classcol-md-6 div classpanel panel-default div classpanel-heading Doughnut Chart ul classpull-right panel-settings panel-button-tab-right li classdropdowna classpull-right dropdown-toggle data-toggledropdown href em classfa fa-cogs/em /a ul classdropdown-menu dropdown-menu-right li ul classdropdown-settings lia href em classfa fa-cog/em Settings 1 /a/li li classdivider/li lia href em classfa fa-cog/em Settings 2 /a/li li classdivider/li lia href em classfa fa-cog/em Settings 3 /a/li /ul /li /ul /li /ul span classpull-right clickable panel-toggle panel-button-tab-leftem classfa fa-toggle-up/em/span/div div classpanel-body div classcanvas-wrapper canvas classchart iddoughnut-chart /canvas /div /div /div /div /div–/.row– /div –/.main– script srcjs/jquery-1.11.1.min.js/script script srcjs/bootstrap.min.js/script script srcjs/chart.min.js/script script srcjs/chart-data.js/script script srcjs/easypiechart.js/script script srcjs/easypiechart-data.js/script script srcjs/bootstrap-datepicker.js/script script srcjs/custom.js/script script window.onload function () var chart1 document.getElementById(line-chart).getContext(2d) window.myLine new Chart(chart1).Line(lineChartData, responsive true, scaleLineColor rgba(0,0,0,.2), scaleGridLineColor rgba(0,0,0,.05), scaleFontColor c5c7cc ) var chart2 document.getElementById(bar-chart).getContext(2d) window.myBar new Chart(chart2).Bar(barChartData, responsive true, scaleLineColor rgba(0,0,0,.2), scaleGridLineColor rgba(0,0,0,.05), scaleFontColor c5c7cc ) var chart3 document.getElementById(doughnut-chart).getContext(2d) window.myDoughnut new Chart(chart3).Doughnut(doughnutData, responsive true, segmentShowStroke false ) var chart4 document.getElementById(pie-chart).getContext(2d) window.myPie new Chart(chart4).Pie(pieData, responsive true, segmentShowStroke false ) /script /body /html DOCTYPE html html head meta charsetutf-8 meta nameviewport contentwidthdevice-width, initial-scale1 titleMy Devices/title link hrefcss/bootstrap.min.css relstylesheet link hrefcss/font-awesome.min.css relstylesheet link hrefcss/datepicker3.css relstylesheet link hrefcss/styles.css relstylesheet –Custom Font– link hrefhttps//fonts.googleapis.com/cssfamilyMontserrat300,300i,400,400i,500,500i,600,600i,700,700i relstylesheet –if lt IE 9 script srcjs/html5shiv.js/script script srcjs/respond.min.js/script endif– /head body nav classnavbar navbar-custom navbar-fixed-top rolenavigation div classcontainer-fluid div classnavbar-header button typebutton classnavbar-toggle collapsed data-togglecollapse data-targetsidebar-collapsespan classsr-onlyToggle navigation/span span classicon-bar/span span classicon-bar/span span classicon-bar/span/button a classnavbar-brand hrefspanIDS/span/a ul classnav navbar-top-links navbar-right li classdropdowna classdropdown-toggle count-info data-toggledropdown href em classfa fa-bell/emspan classlabel label-info5/span /a ul classdropdown-menu dropdown-alerts lia href divem classfa fa-envelope/em 1 New Message span classpull-right text-muted small3 mins ago/span/div /a/li li classdivider/li lia href divem classfa fa-user/em 5 New Events span classpull-right text-muted small4 mins ago/span/div /a/li /ul /li /ul /div /div– /.container-fluid — /nav div idsidebar-collapse classcol-sm-3 col-lg-2 sidebar div classprofile-sidebar div classprofile-userpic img srchttp//placehold.it/50/30a5ff/fff classimg-responsive alt /div div classprofile-usertitle div classprofile-usertitle-nameUsername/div div classprofile-usertitle-statusspan classindicator label-success/spanOnline/div /div div classclear/div /div div classdivider/div form rolesearch div classform-group input typetext classform-control placeholderSearch /div /form ul classnav menu li classactivea hrefindex.htmlem classfa fa-dashboardnbsp/em Dashboard/a/li lia hrefcharts.htmlem classfa fa-bar-chartnbsp/em Recent Activity/a/li lia hrefpanels.htmlem classfa fa-clonenbsp/em My Devices/a/li lia hreflogin.htmlem classfa fa-power-offnbsp/em Logout/a/li /ul /div–/.sidebar– div classcol-sm-9 col-sm-offset-3 col-lg-10 col-lg-offset-2 main div classrow ol classbreadcrumb lia href em classfa fa-home/em /a/li li classactiveMy Devices/li /ol /div–/.row– div classrow div classcol-lg-12 h1 classpage-headerMy Devices/h1 /div /div–/.row– div classrow div classcol-lg-12 h2Alerts/h2 div classalert bg-danger rolealertem classfa fa-lg fa-warningnbsp/em Intruder Detected Please review the most recent activity. a href classpull-rightem classfa fa-lg fa-close/em/a/div /div /div–/.row– div classrow div classcol-lg-12 h2Authorized Devices/h2 /div div classcol-md-4 div classpanel panel-default div classpanel-headingids-raspberry-home span classpull-right clickable panel-toggleem classfa fa-toggle-up/em/span/div div classpanel-body ul lipIP 135.21.225.16/p/li lipStatus Offline/p/li /ul /div /div /div div classcol-md-4 div classpanel panel-primary div classpanel-headingids-raspberry-work span classpull-right clickable panel-toggleem classfa fa-toggle-up/em/span/div div classpanel-body ul lipIP 172.14.22.218/p/li lipStatus Active/p/li /ul /div /div /div div classcol-md-4 div classpanel panel-success div classpanel-headingids-raspberry-college span classpull-right clickable panel-toggleem classfa fa-toggle-up/em/span/div div classpanel-body ul lipIP 31.16.21.164/p/li lipStatus Online/p/li /ul /div /div /div /div– /.row — /div–/.main– script srcjs/jquery-1.11.1.min.js/script script srcjs/bootstrap.min.js/script script srcjs/chart.min.js/script script srcjs/chart-data.js/script script srcjs/easypiechart.js/script script srcjs/easypiechart-data.js/script script srcjs/bootstrap-datepicker.js/script script srcjs/custom.js/script /body /html 5.2 SCREENSHOTS Setting up PIR sensor Install IP Webcam from playstore Open the application and start the server Note down the IP address generated by the application Open VNC viewer and provide the IP address of Raspberry PI using IP-Scanner Set up the environment where both Raspberry PI and Smart phone should be connected to same router network Execute the program to capture image and save the image in Pi storage Draw the Node-RED flow and fill the nodes with necessary information name the flow and enable it Provide the flow with timestamp Provide the image location in PI provide the description that should be sent as an attachment with the image Give the proper email ids to which the mail is to be sent Attachment file with image Node-RED flow to send the image to IBM Watson Creating necessary services and applications in Cloud Overview of the boards used and their information Device information Information about the data transferred User interface for client to handle data and multiple devices CHAPTER 6 RESULTS AND DISCUSSION 6.1 Results Whenever a new record comes there could be a variation in the outcome of possible characteristics. We constantly insert it with new values. The result also depends on the number of frequent patterns we specify. We are getting many attributes but we will be using one or two based on our need. We keep monitoring the average level of existing policies in each category of images. For now we are using Bluemix for visual recognition meanwhile we can also use other services provided by google such as tensorflow for auto detecting images and retrieving information directly when we upload an video itself. So when we upload a video automatically video will be broken in to images based on quality which could be producing efficient results when used on a single go. 6.2 CONCLUSION We proposed an approach by which one can achieve better data or characteristics of the images. We will try to make it automated and try to increase the number of attributes which can help in analytics side. This project has a vast scope where we can see continuous development by making some changes such as making this system work without any human intervention. The IDS (Intrusion Detection System) is currently being able to sense the motion of objects and take a picture. The objects in the picture are identified and the user is alerted if there is a person in the picture. This existing setup can be used in cases where the user must leave their home for a long period of time. The device when setup and switched on, connects to the cloud provided to the user to manage all their devices. The activity of a device is stored in the cloud and the user can access it from remotely anywhere in the world. Right now we are using conversion at a smaller extent and could use more machine learning algorithms for prediction purpose. This system will help a lot to target advertising where a particular individual can be tracked and most probable advertisements can be shown. 6.3 FUTURE WORK The device can be used as a complete home security module by integrating it with alarm systems that alert the authorities in the case of a theft. Furthermore, with the help of image processing and machine learning, the IDS can be programmed to detect unfamiliar faces only. In the aspect of security, we need to guarantee that our device cannot be compromised. As all the devices a user owns will be connected to one another through the cloud, it is possible that an attack on a single device will lead to the failure of the complete system. Robust authentication must be done for every request made to the device. Currently, each request is authenticated with the help of an API key which is unique and provided to the user. The user must include their API key in the header of the request, so that it can be authenticated. OAuth can be used to strengthen the authentication further. CHAPTER 7 REFERENCES 7.1 REFERENCES Al-Maolegi, M., Arkok, B. (2014). An Improved Apriori Algorithm for Association Rules.International Journal on Natural Language Computing,3(1). Catanzariti, P. (2016,May 09). Connecting a Raspberry Pi to IBM Watson, Bluemix and Node-RED. Retrieved from HYPERLINK https//www.sitepoint.com/connecting-a-raspberry-pi-to-ibm-watson-and-bluemix/ t _blank https//www.sitepoint.com/connecting-a-raspberry-pi-to-ibm-watson-and-bluemix/ Ferrucci, D., Brown, E., Chu-Carroll, J., Fan, J., Gondek, D., Kalyanpur, A. A., . . . Welty, C. (n.d.). The AI Behind Watson The Technical Article. Retrieved from HYPERLINK http//www.aaai.org/Magazine/Watson/watson.php t _blank http//www.aaai.org/Magazine/Watson/watson.php Ferruci, D. A. (2012). This is Watson.IBM Journal of Research and Development,56(3.4), 11-115. doi10.1147/JRD.2012.2184356 Getting started with IBM Cloud CLI. (n.d.). Retrieved from HYPERLINK https//console.bluemix.net/docs/cli/reference/bluemix_cli/get_started.html l getting-started t _blank https//console.bluemix.net/docs/cli/reference/bluemix_cli/get_started.htmlgetting-started How to use IP Webcam with opencv as a wireless camera. (n.d.). Retrieved from HYPERLINK https//thecodacus.com/ip-webcam-opencv-wireless-camera/ t _blank https//thecodacus.com/ip-webcam-opencv-wireless-camera/ Lunk, P. (2017,May 27). How to Use the Android IP Webcam App with Python / OpenCV. Retrieved from HYPERLINK https//www.hackster.io/peter-lunk/how-to-use-the-android-ip-webcam-app-with-python-opencv-45f28f t _blank https//www.hackster.io/peter-lunk/how-to-use-the-android-ip-webcam-app-with-python-opencv-45f28f Miller, G. A. (1995). WordNet A Lexical Database for English.Communications of the ACM,38(11), 39-41. Node-red-node-email – Node-RED. (n.d.). Retrieved from HYPERLINK https//flows.nodered.org/node/node-red-node-email t _blank https//flows.nodered.org/node/node-red-node-email Node-RED Creating your first flow. (n.d.). Retrieved from HYPERLINK https//nodered.org/docs/getting-started/first-flow t _blank https//nodered.org/docs/getting-started/first-flow Rao, K. (n.d.). Overview of Image Processing. Retrieved from HYPERLINK http//www.drkmm.com/resources/INTRODUCTION_TO_IMAGE_PROCESSING_29aug06.pdf t _blank http//www.drkmm.com/resources/INTRODUCTION_TO_IMAGE_PROCESSING_29aug06.pdf The DeepQA Research Team. (n.d.). Retrieved from HYPERLINK https//researcher.watson.ibm.com/researcher/view_group_subpage.phpid2159 t _blank https//researcher.watson.ibm.com/researcher/view_group_subpage.phpid2159 Visual Recognition. (n.d.). Retrieved from HYPERLINK https//console.bluemix.net/docs/services/visual-recognition/index.html t _blank https//console.bluemix.net/docs/services/visual-recognition/index.html Visual Recognition Demo. (n.d.). Retrieved from HYPERLINK https//visual-recognition-demo.ng.bluemix.net/ t _blank https//visual-recognition-demo.ng.bluemix.net/ PAGE MERGEFORMAT 2 Y, I-iii3JPO-fWZO0,_p7
-fm9tVpyfcvOr(CxtuWVO)88ljoJmMHhz4YH EG_jP
QySJfz_0
6JW52mz)GCnRjPAimhcq6TW
dBsxdo(bxN 8s(Iz Q 6Q

Post Author: admin

x

Hi!
I'm Avery

Would you like to get a custom essay? How about receiving a customized one?

Check it out