Overview / Usage

The present scenario ensures the safety and security has become an inevitably essential. There is a regressive progress in the security system as the influence of modern technology is reaching its peak. When there is a modern home with minimum human effort, it’s well known as modern home. Since there is an advent of wireless and digital technologies, all together it introduces an automated intelligent security system. The automated home security system can be designed with the surveillance camera and multiple sensors, and the use of these sensors will be defining the features of these sensors. Faster data transmission is taking place using the Wi-Fi to security systems which helps the user to control and monitor the system globally.

The main aim of this project is to design and develop a security system that includes features such as motion detection, image processing and emailing or SMS to facility owner. The proposed system characteristics involve remote monitoring, intrusion detection, system security such that system automatically adjusts the system settings on running hardware support check. The system is to be based on Raspberry Pi SBC. The specific objectives are:

▪ To study and describe how the Raspberry Pi can be interfaced with a motion detector and Pi camera.

▪ To study how a Raspberry Pi can be programmed so as to be able to send an email to a prescribed mail hub.

▪ To develop and build a prototype of the surveillance system based on the Raspberry Pi SBC.

▪ To design and implement a motion detecting and tracking system for real time video analysis and implement concepts of image processing.

▪ To implement efficient communication using wireless communication technology.

​

Methodology / Approach

This project will consist of a raspberry pi 4 at its core. The pi will be connected to a camera that continuously monitors a designated area passively through a video stream sent to the pi. The pi will monitor this stream and remains dormant until movement is detected. Movement detection is achieved by using background subtraction and pixel shift count and Ultrasonic sensor. As soon as movement is detected, the pi will initiate human detection software. This involves a script that monitors the footage folder. As soon as the file is created, the script runs, uploads the file for analysis and deletes the local copy to save space on the pi. If no human is detected, the pi will remain in its passive monitoring state. If a human is detected, the system will immediately send a notification to the user’s phone, starts recording footage. Any other unsecured activities like emergency fire, LPG leakage are also monitored and saved as a message string in pi. This saved data on the pi is then sent to the user’s email. The user’s email is set to receive push notifications.

So, the whole procedure is divided into three main subtasks-

1. Monitoring

2. Detection and Processing

3. Conveying

▪ Monitoring-

The system consists of a raspberry pi and a webcam. The system will constantly check a video stream for movement, and when movement is detected, the camera initiates human detection. If a human being is detected, the tries to capture the face of the intruder from the video stream. Exteroceptive sensors like Ultrasonic, LPG-detection, Smoke-detection provides data to Pi in case of any hinderance in their surroundings and the system acknowledges the data and further conveys it.

▪ Detection and Processing-

The main objective after detecting human presence is to process his image from ongoing video stream which is achieved by using three processing techniques.

1. Image Blurring:

Gaussian blur (also known as Gaussian smoothing) is the result of blurring an image by a Gaussian Function. It is a widely used to reduce noise and detail. The visual effect of this blurring technique is a smooth blur resembling that of viewing the image through a translucent screen, distinctly different from the bokeh effect produced by an out-of-focus lens or the shadow of an object under usual illumination. Gaussian smoothing is also used as a pre-processing stage in computer vision algorithms in order to enhance image structures at different scales.

1. Gray scaling:

Grayscale is a range of shades of gray without apparent colour. The darkest possible shade is black, which is the total absence of transmitted or reflected light. The lightest possible shade is white, the total transmission or reflection of light at all visible wavelengths. Intermediate shades of gray are represented by equal brightness levels of the three primary colours (red, green and blue) for transmitted light, or equal amounts of the three primary pigments (cyan, magenta and yellow) for reflected light.

​

1. Thresholding:

It is a process of converting a grayscale input image to a bi-level image by using an optimal threshold. The purpose of thresholding is to extract those pixels from some image which represent an object (either text or other line image data such as graphs, maps). Though the information is binary the pixels represent a range of intensities. Thus, the objective of binarization is to mark pixels that belong to true foreground regions with a single intensity and background regions with different intensities.

After the three processing techniques the image is filtered and converted to binarized image. Further a haarcascade classifier is used to detect the human face from image and this face is then transmitted forward to administrator.

▪ Conveying (Generating and sending e-mail):

After configuring the system to send an alert to the predefined subscriber, it was then necessary to generate and send the mail. Multipurpose Internet Mail Extension (MIME) package was then called and used to generate the attachment. MIME supports characters other than ASCII, non – text attachments (audio, video and application programs) etc. It thus extends the format of an email. Simple Mail Transfer Protocol (SMTP) program was then used to deliver the email from the Raspberry Pi to the configured mail hub

Technologies Used

For an embedded real-time surveillance system to be utilized for effective monitoring and alerting, the system has to have at least three functions. These functions are: detection, image processing and alert mechanism. This Raspberry Pi based security system is thus composed of mainly two parts. These are: Design Hardware and Design Software.

▪ Design Hardware (System modules):

o Raspberry Pi model 4

o Ultrasonic Sensor

o Pi Camera Module

o Smoke-Detection Sensor

o LPG-Detection sensor

o Google Assistant – Google home/Smartphones

o LEDs

o USB Type-C Power Cable

▪ Design Software:

o Python 3

o Haarcascade Classifier

o IFTTT with backend Nginx server

o Python libraries- • OpenCV • Urllib • Smtplib • Picamera • Imghdr

Documents and Presentations