0% found this document useful (0 votes)
265 views19 pages

Home Automation Using Hand Gesture

This document summarizes a student project on home automation using hand gestures. A wristband with an accelerometer sensor detects hand movements and sends the data to a Raspberry Pi. The Pi uses machine learning to recognize gestures and control devices like a TV via a relay module. The project aims to help people with mobility challenges operate devices hands-free. It details the hardware, software, algorithm, challenges, and contributions of team members to build a proof of concept that turns hand gestures into commands for home appliances.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
265 views19 pages

Home Automation Using Hand Gesture

This document summarizes a student project on home automation using hand gestures. A wristband with an accelerometer sensor detects hand movements and sends the data to a Raspberry Pi. The Pi uses machine learning to recognize gestures and control devices like a TV via a relay module. The project aims to help people with mobility challenges operate devices hands-free. It details the hardware, software, algorithm, challenges, and contributions of team members to build a proof of concept that turns hand gestures into commands for home appliances.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 19

Home Automation

using Hand Gestures


Professor – Ali Zaringhalam

Members:
Amit Bhorania Prasad Patil
Ashutosh Gajankush Shivangi Rai
Chiranth HD Sumanth Darisi
Contents
• Project Demo
• Introduction
• Hardware Details
• Software Details
• Project Outcome
• Limitations & Future Enhancement
Introduction
• Project deals with Hand gesture recognition for home
automation
• User friendly gestures to operate Device On/Off
• Accelerometer sensor wristband which senses the
acceleration of hand movement
• Raspberry Pi process the sensor data with Machine Learning
Algorithm
• Operate the devices as per the detected Hand Gestures
Application
• People with Mobility Challenges
• Home Automation
• Operating Devices for example – TV (Power On/Off, Channel
next/prev, Volume Up/Down)
• Gesture based Gaming
• Wheel Chair Control
System Block
Accelerometer
• Accelerometer measures the acceleration (rate of change of
velocity) in X, Y and Z axis
• Unit is m/s2 or in terms of g (9.8 m/s2)
• ADXL345 Accelerometer Sensor
• Low power, High resolution (10 bit) with +/- 2g range
• Interfaces on I2C Interface for data communication
Raspberry Pi
• Credit Card sized computer
• Low Cost
• Raspbian or Linux OS
• Specification
• 1GB RAM
• Micro SD Storage
• HDMI Port, 4 USB Ports
• 26 GPIOs available
• Supports different interfaces like UART, I2C, SPI etc.
• Python supports
• Lots of Libraries, Documentation and Community available
Relay Module
• 2 Channel 5V SPDT Relay
• Handles the AC Devices with the input from Digital Devices
• Normally Close (NC) – GND
• Normally Open (NO) – 120 V
• Raspberry Pi provides input using its GPIO pins
• On input High, Op will be connected to NO pin internally
Sensor Interfacing
• Raspberry Pi is connected with ADXL345 Sensor on I2C
• I2C – 2 wire Serial Protocol popular in Microcontroller
communication
• Initialize the I2C Interface
• Read the Sensor value of 3 Axis using the I2C Protocol
(Start Bit, Address, Read/Write, Register Address, ACK, Stop Bit)
Machine Learning Algo
• Heart of the Project
• Process the Accelerometer Sensor Data using custom Machine
Learning Algo
• Algorithm detects the Hand Gesture
• GPIO Module operate the Devices as per the detected hand
gesture
Algorithm
Teaser Project Demo…
Challenges
• Controlling the PI using the Laptop without HDMI Display
• Deciding the Algorithm
• Calibrating the Sensors
• Gesture Tuning
Contribution
• Amit Bhorania
• Loading the Raspbian OS and config the Pi to control from Laptop
• Searching for Machine Learning Algorithm by going through
various Research Papers
• Ashutosh Gajankush
• Understanding & Interfacing the Accelerometer Sensor with PI
• Prasad Patil & Shivangi Rai
• Ordering & Soldering the components, Taking the Gesture
Samples
• Interfacing the Relay module with GPIO
• Chiranth HD and Sumanth Darisi
• Implementing the Machine Learning Algorithm
Result
• Using the Raspberry Pi, Accelerometer Sensor and Machine
Learning Algorithm, We operated the Home Appliances using
Hand Gestures
Limitation
• User needs to wear the Accelerometer wrist band
• Current design is using the wired communication between
Sensor and Raspberry PI but we can make it wireless
Future Enhancement
• Wireless interface between Sensor and Raspberry Pi using
ESP8266 Wifi Module
• Interface the Algorithm with other Devices like Projector or TV
• Add more Gestures to the Algorithm to handle multiple
devices
Questions…
Thank you

You might also like