Why Teams call analytics are critical to your entire business
Â
INTERNET OF THINGS IMPLEMENTATION FOR WIRELESS MONITORING OF AGRICULTURAL PARAMETERS WITH LEAF DISEASE DETECTION
1. INTERNET OF THINGS IMPLEMENTATION FOR WIRELESS MONITORING
OF AGRICULTURAL PARAMETERS WITH LEAF DISEASE DETECTION
Under the esteemed guidance of
Smt P. PUSHPALATHA
Assistant Professor of ECE JNTU KAKINADA
by
PETETI SRIDHAR
I V S K CHAITANYA
K MAHESH CHOWDARY
2. CONTENTS
1. INTRODUCTION
2. INTERNET OF THINGS
3. COMPONENT DESCRIPTION
4. IMPLEMENTATION OF SENSOR NETWORK
5. LEAF DISEASE DETECTION
6. CONCLUSION AND FUTURE SCOPE
3. Abstract
Agriculture field is that the backbone of Indian economy. In Asian nation around seventieth of the population
earn its resource from agriculture sector. This Project planned that to develop a wireless system that monitors
environmental conditions in agriculture field like temperature, rainfall level, soil wet level and humidness beside leaf
diseases detection. an efficient implementation for internet of Things used for observance regular environmental conditions
by means that of low value omnipresent sensing system and result with current all parameters, affected plant disease, its
management measures is shipped to our dashboards. System is designed because for the higher yield of crops some
parameters from surroundings square measure necessary that directly have an effect on its growth. These parameters
could also be environmental condition parameters, soil parameters, irrigation parameters etc.Identification of the plant
diseases is the key to preventing the losses in the yield and quantity of the agricultural product.
The studies of the plant diseases mean the studies of visually observable patterns seen on the plant. Health
monitoring and disease detection on plant is very critical for sustainable agriculture. It is very difficult to monitor the plant
diseases manually. It requires tremendous amount of work, expertise in the plant diseases, and also require the excessive
processing time. Hence, image processing is used for the detection of plant diseases. Disease detection involves the steps
like image acquisition, image pre-processing, image segmentation, feature extraction and classification. This Project
implemented the methods used for the detection of plant diseases using their leaves images. This project also discussed
some segmentation and feature extraction algorithm used in the plant disease detection.
4. 1.INTRODUCTION
âą Our Project was planned that to develop a wireless
system that monitors environmental conditions in
agriculture field like temperature, rainfall level, soil wet
level and humidness beside leaf diseases detection.
âą An efficient implementation for internet of Things used
for observance regular environmental conditions by
means that of low value omnipresent sensing system
and result with current all parameters, affected plant
disease, its management measures is shipped to our
dashboards.
âą Health monitoring and disease detection on plant is very
critical for sustainable agriculture. It is very difficult to
monitor the plant diseases manually. It requires
tremendous amount of work, expertise in the plant
diseases, and also require the excessive processing
time. Hence, image processing is used for the detection
of plant diseases.
âą Disease detection involves the steps like image
acquisition, image pre-processing, image segmentation,
feature extraction and classification.
5. 2. Internet of Things
â The Internet of Things (IOT) is a worldwide network of
intercommunicating devices.
â IOT is a vision where âthingsâ, especially everyday
objects, such as all home appliances, furniture, clothes,
vehicles, roads and smart materials, etc. are readable,
recognizable, locatable, addressable and/or
controllable via the Internet.
6. Applications of IoT:
âą Tagging Things: Real-time item
traceability and addressability by RFIDâs.
âą Feeling Things: Sensors act as primary
devices to collect data from the environment.
âą Shrinking Things: Miniaturization and
Nanotechnology has provoked the ability of
smaller things to interact and connect within
the âthingsâ or âsmart devicesâ.
âą Thinking Things: Embedded
intelligence in devices through sensors has
formed the network connection to the
internet. It can make the âthingsârealizing the
intelligent control.
7. 3. Component description
3.1 Arduino/Geniuno UNO:
1. Digital pins: Use these pins with digitalRead(), digitalWrite(),
and analogWrite(). analogWrite() works only on the pins with
the PWM symbol.
2. Pin 13 LED: The only actuator built-in to your board.
Besides being a handy target for your first blink sketch, this
LED is very useful for debugging.
3. Power LED: Indicates that your Genuino is receiving power.
Useful for debugging.
4. ATmega microcontroller: The heart of your board.
5. Analog in: Use these pins with analogRead().
6. GND and 5V pins: Use these pins to provide +5V power and
ground to your circuits.
7. Power connector: This is how you power your Genuino when
itâs not plugged into a USB port for power. Can accept voltages
between 7-12V.
8. TX and RX LEDâs: These LEDs indicate communication
between your Genuino and your computer. Expect them to
flicker rapidly during sketch upload as well as during serial
communication. Useful for debugging.
9. USB port: Used for powering your Genuino Uno, uploading
your sketches to your Genuino, and for communicating with
your Genuino sketch (via Serial. println() etc.).
8. 3.2 DHT11 SENSOR (Temperature and Humidity Module):
âą the VDD power supply 3.5ïœ5.5V DC
âą DATA serial data, a single bus
âą NC, empty pin
âą GND ground, the negative power
3.3 SOIL MOISTURE SENSOR:
âSâ stands for Signal Input
â+â stands for Power Supply
â-â stands for GND
9. 3.4 RAINFALL MEASUREMENT SENSOR:
1. VCC : 5V DC
2. GND : ground
3. DO : high/low output
4. AO : Analog output
11. Architecture of Sensor Network
To build this application, we need 3 main components:
ï A physical layer for capturing parameters.
We will implement this using an Arduino
microcontroller and sensors.
ï A coordination layer used for capturing the
measurements from the physical layer,
and sending the measurements to our
application. We will implement this using
node.js.
ï An application layer for visualizing the
measurements in real-time. We will
implement this using a data visualization
cloud service called Plotly.
12. Physical layer â Connect DTH sensor to Arduino , the Analog
input/output pin of the sensor is connected to A0 of
Arduino .
â Connect Soil moisture sensor to Arduino , the Analog
input/output pin of the sensor is connected to A1 of
Arduino .
â Connect Rainfall measurement sensor to Arduino ,
the Analog input/output pin of the sensor is
connected to A2 of Arduino .
â Connect Arduino to the PC with the USB cable .
â Open the Arduino software , write sensor code for the
software .
â Upload the code to Arduino board.
13. Coordination
layer
What is node.js?
Node.js is an open source, cross-platform runtime environment for
server-side and networking applications.It has a library management
system called node package manager or npm that allows you to
extend its functionality in many directions.
Building Node.js server
we use Arduinoâs serial monitor to display the measurements.
Now we will build a node.js server that gets sensor parameters
from Arduino and displays these measurements on the terminal.
To build this server, we need one node library called serialport.
from your terminal, execute npm install serialport to install the
library.
To start the node.js server, from your terminal go to the
folder where server1.js is saved, and execute node server1.js.
You will see the measurements displayed on the terminal.
14. Application
layer
What is Plotly?
Plotly is an online analytics and
data visualization tool. Plotly has
a Streaming API, which makes it
perfect for our use case.
Plotly account and API keys
Create a free Plotly account by going to this
url.
After creating your account, go to your setting
and get 3 pieces of information.
Username
API key
Streaming API token
When you run server.js code, it creates a file in Plotly. From
Plotly website, click on file and you will be able to see a real-
time graph that shows.
15. 5. Leaf disease detection
âą Identification of the plant diseases is the key to
preventing the losses in the yield and quantity of the
agricultural product.
âą Disease detection involves the steps like image
acquisition, image pre-processing, image segmentation,
feature extraction and classification.
16. B.Image Pre-processing
To remove noise in image or other object
removal, different pre-processing
techniques is considered. Image clipping
i.e. cropping of the leaf image to get the
interested image region.Image smoothing is
done using the smoothing filter. Image
enhancement is carried out for increasing
the contrast. the RGB images into the grey
images using colour conversion using
equation
A. Image Acquisition
The images of the plant leaf are captured
through the camera.This image is in RGB
(Red, Green And Blue) form. Color
transformation structure for the RGB leaf
image is created, and then, a device-
independent color space transformation for
the color transformation structure is applied
.
17. 1. Segmentation using Boundary
and spot detection algorithm:
The RGB image is converted into the
HIS model for segmenting. Boundary
detection and spot detection helps to
find the infected part of the leaf . For
boundary detection the 8 connectivity of
pixels is considered and boundary
detection algorithm is applied .
2. K-means clustering:
The K-means clustering is used for
classification of object based on a set of
features into K number of classes. The
classification of object is done by
minimizing the sum of the squares of
the distance between the object and the
corresponding cluster.
The algorithm for K âmeans Clustering:
1. Pick center of K cluster, either
randomly or based on some heuristic.
2. Assign each pixel in the image to the
cluster that minimizes the distance
between the pixel and the cluster
center.
3. Again compute the cluster centers
by averaging all of the pixels in the
cluster. Repeat steps 2 and 3 until
convergence is attained.
C.Image
Segmentation
18. 3. Otsu Threshold Algorithm:
Thresholding creates binary images from grey-level images by setting all pixels
below some threshold to zero and all pixels above that threshold to one. The Otsu
algorithm defined in is as follows:
i) According to the threshold, Separate pixels into two clusters
ii) Then find the mean of each cluster.
iii) Square the difference between the means.
iv) Multiply the number of pixels in one cluster times the number in the other
The infected leaf shows the symptoms of the disease by changing the color of
the leaf. Hence the greenness of the leaves can be used for the detection of the
infected portion of the leaf. The R, G and B component are extracted from the
image. The threshold is calculated using the Otsuâs method. Then the green
pixels is masked and removed if the green pixel intensities are less than the
computed threshold.
19. i) Color co-occurrence Method :
In this method both color and texture are taken
into account to get an unique features for that
image. For that the RGB image is converted
into the HSI translation.
or the texture statistics computation the SGDM
matrix is generated and using GLCM function
the feature is calculated.
ii) Leaf color extraction using H
and B components:
The input image is enhanced by using
anisotropic diffusion technique to preserve the
information of the affected pixels before
separating the color from the background [8].
To
distinguish between grape leaf and the non-
grape leaf part, H and B components from HIS
and LAB color space is considered. A SOFM
with back propagation neural network is
implemented to recognize colors of disease
leaf.
D. Feature Extraction
20. CONCLUSION:
An easy implementation for web of Things used
for watching regular agricultural parameters
conditions by means of low price omnipresent
sensing system is achieved here with success.
The outline regarding the integrated system and
therefore the interconnecting mechanisms for
reliable measure of parameters by good sensors
and transmission of information via web is being
bestowed in easy language.
FUTURE SCOPE:
This project can be further extended by
implementing a wireless sensor network by using
zigbee and zigbee shield by this can transfer the
data. The data can be send to farmers by
implementing the GSM modules the messages
regarding plant growth can be sent to farmers
phone directly. By implementing the dash board to
this system the results can be used research
institutions and it will helpful for implementing
advance technologies in rural areas.
6 CONCLUSION AND FUTURE SCOPE