You are on page 1of 13

Jaipur Service Company

Dr. Nikhil GOVIL Department of Anukul Gangwar


Computer Engineering & Application B.Tech computer Science
specialization in AML

Raghav Mittal
Raghav Gupta B.Tech computer Science
B.Tech computer science specialization in AML
Specialization in AIML

Abstract: Today, people is move towards digital in on time with a minimum wages got an issue with an AC
world so they are used various E-commerce call and ear conditional expert who will fix your AC just a
application . our project is also a E-commerce few minutes near right by your location. with a minimum
service based application which has aim of provide cost a consumer has no problem regarding a finding a
on demand services to people available on smart worker to fix their applications. or their household
phone application and web based services . Our products similarly these apps help in fixing the problem of
aim is to design an application which helps a needy corporate house cleaning home Appliance and all other
people to find a service worker very easily in a cost household problems.
efficient manner. We will design a Jaipur Service
Company. It will provide a list of worker to a Keywords— On-demand services, consumer satisfaction,
particular selected category and use the will be sustainability, wages.
Workers are also available at their near locations.
and they can provide. if no worker is available near. I. NEED OF THE STUDY
the consumer do. finding worker radius or the area
is increased. gradually so that we will find a new Now people increasingly move toward the technology so
worker for the consumer help. Now a days Our they need a platform for their needs reaching. which includes
travel , eat , shop and even dating all has undergone a shopping, dining, even dating. Know the youth demand on
a tremendous change so we can design Interactive demand services platform, which provided. on demand
Android application. named as Jaipur Service services to the pupil according to their needs and help. in their
Company Love in the marketplace. for on demand common livelihood In this context, we are defining a Jaipur
service available. through a smartphone app. service. This company, which is easily accessible by all the
Today on demand solution have proven blessings to pupils, have efficiency to provide a service provision and it is
everyone. in all the environment condition . Our a localized problem. solution which focused on provided based
Jaipur based company provide the advanced solution to the human with the cost efficient way in their
livelihoods. The rapid evolution of technology makes a Jaipur
technology to the younger generation which fulfill
service company. a new term for adapting the human changing
the demands everything to happen instantly
demands behavior. and New South the customer experience
anywhere at anytime. Jaipur service company through which company has addressing all the demand and
provides everything Add their doorstep whether their needs for their own demand services platform named as
it’s in South Cleaning, or innovation, plummy Jaipur Service Company platform It’s a simple Pupil friendly
assistance, appliance repair or electric application platform in which user can. demand its basic needs like
of fitness coaches who come to them. method of plumbing, furnishing, carpentering, painting and Etc. services
providing services. is being changed as a result. in their local peoples.
Customer demand exchanges rapidly. Jaipur based
company involved in customer needs and technical
improvement on demand app development II. INTRODUCTION
emerged. The cost of a worker or an employee. is
checked. or calculated by our system dynamically Today is the world dependent on tech All we can say fully
after considering a different parameter, a final hi-tech world . As a group of the technologies, it increases day
causeway despite to the consumer for which the by day. So the concept of working is Exchanging and so is the
cost of the worker or helper is minimized. The main future of work and employment and production is also
idea behind this if two dynamic prices is applied on changes With this, we can introduce our project that is served.
the user order to overcome a left salary problems on service demand platform named as Jaipur Service
of the worker and also provided a cheap and the Company, which provided New trend in the market of on
best experience labor or helper to the consumer. demand application. The demand of home based services. is
increased day by day. to increase these demand. home service
As the name suggest, our company is a service based application will be rapidly the old age people are not going for
company, which provided a platform to the consumer for any worries anymore, The trusted cost efficient A home
which. a consumer can hire a professional for your service application with professional qualification and
household course at your fingertips. Jaipur service personal quality. and fixed everything. at your home in very
company is a local Jaipur based company which provided efficient way. Now the problem is with the growth of city and
a services in the Jaipur marketplace. Jaipur based urbanization. the problem of Abbudance of low cost worker
company provides on demand in build services. with all the and finding a worker for their used like painting.
essential features. For example, got a leakage issue at Carpentering. preparing. lumbering and Etcetera purposes. is
home. Higher a plumber near at your locality who will fix most difficult challenge in the urban or metropolitan city of
Global. World people are constantly in a hurry. and want to in such a way that it will help in. organizing ,Support
fix their program at any cost, immediately They do not have reasoning user friendly and behaviour of the system
time to find a labor for their work. They are busy with their
everyday calculus and their work life balance to maintain this IV.I. Architectural Design
problem. Jaipur service company is available in the Metro The architecture design of the Jaipur Service Company is a
City of Rajasthan. which provides a solution of this program. representation of the. working and its Organized way to To
enriched at their home or doorstep to help you with this. Jaipur make it user friendly for the people and work efficiently. with
Service company has aimed to implement a contract based that, the basic architecture system design a mobile app
model for the people in the Jaipur, the pink city of Rajasthan. application server which is client side on Internet service
Jaipur service company has the ability of the on demand provide For and which connect to the server in the database
services economy to make everyone happy, including service of the. of the architecture represent the design of the system
providing services. providers and customers happiness to and mobile application of the Jaipur service based company.
receive essential service at their convenience is a major factor
of its success. The home services connect the local services to
the consumer while maximizing the benefits of a technology
with the cost efficient and less complicate manner With the
cost efficient method. Now the problem of finding a local
worker to help in their problem is very efficient with the
Jaipur service based company. Jaipur service company is the
IOS and app based application which is Which is commonly
used in Iphone And Smart phone Providing efficiency to the
human. it is designed. by HTML, CSS Javascript, angular
framework, Ionic framework, and firebase for its backend
efficiency.

III. PROPOSED SYSTEM


Jaipur Service company is an integrated app base service
marketplace that connects a customer to the service
professional. The People or the person Which participate in
the whole process is. consist of worker and a client The IV.II Use-Case Diagram
administration of the Jaipur service based company have
access to manage a customer and the worker. Jaipur services Use Case diagram provide a high level overview of the
company is used in. both iphone and a smartphone app. First, functionality of the system. This. system which indicate
a user can download this Jaipur service company application how the user can interact with the system through various
use cases. to achieve its goal and target the use case
from the play store and the ios store. Then a login page can
diagram also help in to identify clarify and the organize
open in which a user can log in through their mobile number. the system requirement by visualizing the interaction
The user can receive an OTP to confirm the identity of. its between users and the system. The use case diagram of a
number then it should be redirect on the login page. where Jaipur service company has four basic part which include
using can register itself. by a three simple steps. that is actor actor , usecase , system boundary and interaction. In
registered their name. the agenda and its current address. this diagram, a actor represents. a customer interacting
Jaipur service ensure that the address. which was entered by system. It’s an visual representation of the whole Jaipur
service company model.
the user. is genuine. so it can help it out. in very efficient way.
The administration has also. verify all the details. of the user.
The administration of a access. over the customer and the
worker system ported. in the Jaipur company. The major
categories of service is cleaning, painting and installation. A
user can select according to their needs. so that the worker
can help it down. at the minimum cost acquisition price for
that system. A user can select according to their need. What
he and she want to do. at their apartment Firstly, the odd
consultant team. come at the customer home. or address? to
respect the area. The whole charges for this inspection is
minimum. After the inspection. they tell the charges in the
appointment date. of the worker. A user can add. all the
services which he and she want to do at your home. user can
add all the services at the cart and book now with the
minimum wages. The description and the type features is also
available at the cart so a user can explain at efficient way to
the consultant people. after the user can buy the consultation
of the Jaipur Service Company A company will send a
consultant people to the user home . The whole process is
confirmed by the vacant team and send its consultant as soon as
possible.

IV. MPLEMENTATION
The implementation of a Jaipur service company design
is a user friendly. so that a customer and a worker can
use according to. their work. the whole formal
description and the representation of system is designed
IV.III Modular Design

Designed represented the modality and the


functionality of a Jaipur service based company.
which separate. the modules of the admin in the
user panel. in a separate blocks according to their
functions and action to achieve the customer
satisfaction and goals The modular design. helps
in view development. and the maintenance
capability of the application It create an
independent in the reuse modules of the
components The modular design contains four
midpoints. which are modules, that is a subdivide
systems then admin. user panel and the
functionality of the Jaipur service company

IV.v Sequence Diagram

Sequence diagram. illustrate. the object. that how it


interacts with the particular systems with the time the
diagram will the order in a very dynamic way. The sequence
of Jaipur beef company is below:

IV.iv Data Flow Diagram

Dataflow diagram is the important part for


representing the flow of control of the system,
including how the data enter how its is used to
represent the data. Dft diagram help in the.
understanding. the manner that how the system
work process from from the beginning to the end.
They are the essential components of the system
which indicate data processing with a different IV.vi. Control Diagram
component entity and symbol Or we can say DFT
represent a flow of process of the data proof. Control flow diagram represent the flow of control that
provides information of what input and input how the system will work. They help in understanding the
hierarchy of data There is no set of rules for logical view of operations, decision and action that the
defining a data flow diagram. to represent a Jaipur system react on it. It help. in visualizing. and analyzing the
service company. flow of data We will design level components of the system. which focus on the object
zero level 1 dataflow diagram. which explain how interaction
a data enter and exit from the system
the user need user can select the service from it .

V.i. payment page

V. Result

Jaipur service company is an app – based service


marketplace that connects customer to service
professional. Their strategy is to connect more and more
number of customers to use the platform of Urban Clap
to make their life more easy and comfortable

V.i. login page

user can login through their their mobile no after that


it will examine that user is new or old if user is existing user
then it will show old data otherwise user can add their
detaiks like name , address .

V.i. services page

in this page user can add services and after selecting the
services all the these services will show in their cart and
user can make a payment of their services

CONCLUSION

From the above result. we can conclude that. Need of


the service. play an important role in the today’s tech
market. to be received either in person or in
this is service page of Jaipur service company which will show unattended way. If making simple by a chapel service
what kind of services we provides to the user and according to company, for being a convenient and cost efficient
manner. to the people the expert also mention and Management, 4(11), 265-27
that in home services it increases. Jaipur
service company has their own strategy. If to
connect more and more number of customers
to use the platforms To make their life more
easy and comfortable. with the rise in the
nuclear family and dual couple. the Jaipur
company focused on customers is to spend a
quality time with their families. whenever
possible a services at their doom step at one
click of on their phone is welcoming the
change accepted by the customer today. giving
a rise to the business model. like Jaipur
service company There are many platform
coming in the same manner. like urban clap,
Forex, Handyman, etc. which has also is a
integrated app based service. offer a pest
prevention with the safer, orderless and
environmentally services. to their customer
approved by national and international
organizations. However, the success of these
business is well dependent how successfully
they can help the expectation of its customers
and reduce their pain and provide the overall
healing satisfaction to its customer.

REFERENCES

[1]ttps://www.indianjournals.com/ijor.asp
x?target=ijor:dbr&volume=23&issue=2&ar
ticle=008

[2]https://www.paperpublications.org/
upload/book/The%20Rise%20of%20O
nline%20on-demand-04082022-2.pdf

[3] https://www.investintech.com/pdf-to-
word
[4] Kamal Dharani, Sania Bhatti, Amirita Dewani;
Renovate -It: A geo-based technical professional
hiring system for repairing and maintenance
services 2011
[5] Cunlu Zhang ,Yimeei Guo; A Knowledge
Management System Solution Based on ASP
Platform for Domestic Appliance Repair 2012
[6]ttp://www.webopedia.com/TERM/A/Android_S
DK.html
[7] Dr. Ashok Talukder, Ms. Roopa Yavagal, Mr.
Hasan Ahmed: Mobile Computing, Technology,
Applications and Service Creation, 2nd Edition, Tata
McGrawHill, 2010.
[8] Tom Seymour ,Jasmine Zakir Hussain; How to
create an app 2014
[9] Gupta, A. (2014). E-Commerce: Role of E-
Commerce in today‟s business. International Journal
of Computing and Corporate Research, 4(1), 1-8.
[10] Niharika, S. (2015). A study of internet
marketing in India: Challenges and opportunities.
International Journal of Science Technology
Furthermore, the model integrates the CCTV Depending on the user's preferences, the completed model
camera using RTSP and delivers the detections to the
rest API in the JSON file format or telegram port,
which makes the process highly configurable and
easy to use. The resulting video canbe configured
as per the user's needs, and the frequency of different
categories of animals can be counted to provide
more insights.

Several key points should be highlighted,


including the use of various machine learning and
deep learning algorithms, the implementation of the
model on different types of wildlife, and the use of
RTSP for CCTV camera integration. The integration
with the telegram port or API server to send
encoded results in the JSON file format for
clarification of animal presence is also critical.

Overall, this study offers a potential method for


employing deep learning algorithms to identify
wildlife, which can lessen conflict between people
and animals by identifying animals early and
enabling prompt intervention to avoid unwanted
interactions. Farmers who will use it can also protect
their crops and avoid financial damages. Digital
fence can also lessen the need for physical barriers
and animal relocation, which can be expensive and
logistically difficult.

The rest of the paper is organized as follows:


Section II discusses the literature review followed by
Section III, which explains the proposed
methodology; Section IV discusses the results and
analysis. Finally, section V concludes the research
paper and provides direction for future work.

II. LITERATURE REVIEW

This literature review discusses the growing


human- animal conflicts and the demand for
monitoring and safeguarding animal welfare. It
suggests using deep learning and machine learning
algorithms to identify wildlife and stop possible
threats to people and farms. The assessment
emphasizes the factors that lead to conflicts between
people and wildlife, including deforestation, an
increase in livestock, poaching, and climate change,
as well as the effects of these factors on animals
and communities; including damage to economies,
safety, livelihoods and food security. It is dangerous
and may violate animal welfare rights to monitor
and control animals using conventional or coercive
ways. Consequently, using sensors, cameras, GPS,
drones, unmanned aerial vehicles, and ground
vehicles can improve physical security, human
property protection, and monitoring of animal
welfare. The review addresses several techniques for
tracking animals, including RFID, GPS, and drones
with cameras, and it focuses on their drawbacks and
difficulties. In order to detect wildlife and avert
potential danger to people and farmlands, the
review's conclusion suggests using machine learning
and deep learning algorithms, specifically the
YOLO object detection technique. The suggested
model includes picking animal classes, gathering
image datasets, annotating them, data preprocessing,
enhancing the data, developing models and setting up
the code to run on any GPU accelerator device.
After collecting and preparing the dataset as discussed earlier,
can be coupled with a camera and provide detections to the we passed the dataset images into the YOLO v5 custom object
REST API in the JSON file format or telegram port. detection model. “YOLO v5 is the latest version of the YOLO
(You Only Look Once) algorithm, which is a popular and
Using Wireless Sensor Networks (WSNs), digital fencing widely used deep learning algorithm for object detection tasks.”
is a novel approach to resolving conflicts between people and
wildlife. Devi and Madheswaran created the WSN-based YOLO v5 is a family of compound-scale object detection models
technology known as "Smart Fencing" to monitor and manage that have been trained on the COCO (Common Objects in
animal invasions. The system detects the presence of animals Context) dataset. It includes simple functionality for Test Time
and alerts the control unit usinga combination of infrared Augmentation (TTA), which helps to improve the accuracy of
and ultrasonic sensors. A deterrent device, such as an alarm or object detection by generating multiple versions of the input
sprinkler, is then turned on by the control unit to prevent images during testing. Additionally, it also includes
animals from accessing the protected area [3]. functionality for model assembling, hyperparameter evolution,
and export to ONNX, CoreML, and TFLite, which makes it
Digital fencing was proposed by Kumar and Sivakumar as a very versatile and flexible deep learning model for object
a long-term approach to wildlife management. In order to detection tasks.
encourage cohabitation between people and animals, the study
emphasized the significance of striking a balance between The YOLO v5 model was trained on our custom dataset, which
human activity and conservation efforts. The authors consisted of images of different categories of animals. The
addressed the various digital fencing technologies and their model was trained using transfer learning, which is a popular
uses in managing wildlife, including Radio- Frequency technique in deep learning that involves using a pre-trained
IDentification (RFID), Global Positioning systems (GPS), and model as a starting point and fine-tuning it on a new dataset.
WSNs [4]. This allowed us to leverage the knowledge and features
learned by the pre-trained model and adapt it to our specific
Comita and Robbins reviewed the most recent technological animal detection task. Fig 1, Shares the proposed model of the
advancements and how they were used in wildlife management. paper.
The study explored the possible advantages and disadvantages
of digital fencing technology, including potential effects on
animal behavior, decreased human-wildlife conflict, and better
safety for both people and wildlife [5].

Kahuga and Muraya evaluated the efficiency of digital


fencing in minimizing the conflict between people and wildlife
in Kenya. The authors investigated on how digital fencing
affected elephant behavior and evaluated how well the device
functioned to keep elephants out of agricultural fields. The
financial benefits of digital fencing as a low-cost strategy to
lessen conflict between people and wildlife were also addressed
in the paper [6].

Overall, digital fencing has the potential to be a successful and


long-lasting method of resolving conflicts between people
and wildlife. The use of physical barriers can be diminished
thanks to technology, which can also allow real- time monitoring
and management of animal behavior. However, more study is
required to assess the effectiveness over the long run and the
potential adverse effects of digital fencing on animal behavior
and ecosystem dynamics.

III. PROPOSED METHODOLOGY Fig. 1. Flow Chart of the model.


The methodology for digital fencing is divided into six phases
namely data collection phase, data augmentation phase, Image
Annotation and Acquisition phase, Model training and A. Data Collection
detection processing phase, IOU implementation phase, and
Integration with the Camera phase. Fig. (1) depicts the research The dataset preparation for animal detection is a crucial part of
approach, which we followed for digital fencing. any deep-learning project. In our project, we made sure to use
a well-balanced dataset of images for training, validation and
testing purposes. As mentioned earlier, there are various ways to
collect data and create a dataset. We
RoboFlow being a web-based tool of annotation supports various
chose to collect our dataset from open-source images, video formats for annotation such as YOLOv5, TensorFlow, and
frame extractions and available datasets. PyTorch. It also provides several other useful features such as
data augmentation, dataset splitting,and export functionality.
Our dataset had approximately 10,000 images of sevendifferent This tool being designed to streamline the annotation process
categories of animals that we focused upon, including bear, for their dataset helps the data scientists and developers train
wild boar, tiger, leopard, elephant, deer, and macaque. We their deep learning models more quickly and more efficiently.
wanted to ensure that the dataset was well balanced, so we
included approximately 1300 images of each category of D. Model Training and Detection Processing
animal. The dataset was divided into three parts - the training set, The next step was to pass the processed dataset to the YOLOv5
validation set, and testing set - in a ratio of 7:1:2 respectively. for the custom training of the model. The next challenge was to
This allowed us to train our models effectively and also create a debugging video that required counting of detections.
evaluate the performance of our modelson new and unseen The detection alarms and notification cannot be based on a single
data. frame. So, we used multiple frame check, in this the frames
are counted for the detection of the same animal and after the
To simulate the night vision of the cameras, we also used threshold is met, the notification or the alarm goes on to the
grayscale images in our dataset. This was important as we data-sharing platforms.
wanted to make sure that our models could work effectively in
low-light conditions as well. The dataset was required to be One of the biggest challenges we faced during the data- sharing
balanced and unbiased. The number of day and night images process was how to transmit the detection image to a centralized
were kept of necessary amount to make sure that our model checking system. We could not send the detection image
works perfect in both day as well as night when the animal directly as it would require large amounts of bandwidth and
attacks are prominent. storage. To overcome this challenge, we came up with the idea
The balancing of the dataset was a very important task as it is of converting the detection image into a JSON file format along
mandatory to train the model equally for all the selected classes. with other properties of the detection.
There should be generalization and equality in images for an
unbiased classification. This was necessary for the proper The JSON file included information such as the class detection
classification of animals that look similar in person and also that coordinates, camera IP, and an image of the detection. This
boosted our precision and recall value. format allowed us to transmit the information quickly and
B. Dataset Augmentation efficiently through various platforms, including REST APIs.

The open source images, camera video clips of animals and E. IOU Implementation
openly available images of the animals were the major source We could not afford multiple notifications of the same detection.
for our model’s training, testing, and validation. The major Hence, we used the concept of IOU that marks the animal as the
problem with these images was their raw nature and unclear same till it is in the frame so that it does not awakes the system
motive. Most of these images were not fit for the training again. IOU if calculated on each successful detection to the
purpose or were of too low quality. The images were then to previous frame detections do thatthe warning signals are legit
be scrapped out. The quality images were left to around 10,000, and non-repetitive. The threshold value of the IOU can be
1300 for each class. The images were than annotated according modified according to the requirement.
to the required format of annotations for YOLOv5. The
annotation part was done through the Roboflow software. This The code to count the frames of the detection was self- developed
was the most crucial, time consuming and important part of the to ensure specificity in the program and to prevent any side
whole project as the quality of dataset determines the working cases. This ensured that the animal was really present at that
of the model in the long run. Open sources could only give us place for a certain amount of time. This was important to check
raw images but without data refining and image annotation the before sending out a warning signal. One can also set the no. of
training was not possible. So, the dataset was then converted to frames to be checked before the waring signal.
the annotation format of the algorithm used.
C. Image Annotation and Acquisition Overall, the multiple warning problem or the single frame
warning problems were addressed by the above techniques used.
Even after the refining of the images, without the proper tool There will be no warning on the basis of a single frame
for annotation, it is practically very difficult to annotate a whole detection and if the animal occurs in multiple frames, it will be
dataset of 10,000 images. Thus, we used Roboflow for the noted as only one warning.
annotation process. “Roboflow is a Computer Vision developer
framework for better data collection to preprocessing, and F. Integration with the Camera
model training techniques.” Annotation includes labelling of the RTSP protocol is a protocol that is used mainly for the
selected object in a bounding box that gets a class label. This connection of video surveillance systems to the computer
label is the actual way that the deep learning learns and
distinguish the classes. Using roboflow was a great advantage
for us and it helped us manage the dataset easily.
equal to 0.434. A further increase in the accuracy of the results
device, as live video stream is transmitted directly to the can be gathered by the refinement of the dataset and increasing
computer for live detection or other purposes. User are able to the size and quality of the dataset.
access the cameras remotely from anywhere and any devices,
being fixed or mobile. To further improve the accuracy of our proposed model, we can
After obtaining the IP address of the camera for the connection use transfer learning. Transfer learning is a machine learning
purpose to our systems, we connected the camera using RTSP technique where a pre-trained model is used asa starting
so as to avail all the available use cases of the above-mentioned point for a new task. It allows us to take advantage of the pre-
method of connection. The next step was port setup and existing knowledge gained by the model from a different task
creating username and password for the camera device. and apply it to a new problem.

RTSP protocol, unabled easy integration of the camera with the We can also experiment with different hyperparameters, such
system. We used the OpenCV library in Python to read the video as learning rates, batch sizes, and optimization algorithms to
stream from the camera and passed the frames to our object further improve the accuracy of our model. Another approach to
detection model for real-time detection ofanimals. improve accuracy is by using ensemble methods where multiple
models are combined to give a more accurate prediction. One
By using the RTSP protocol, we were able to seamlessly of the hyperparameters is the confidence interval of the given
integrate a wide variety of cameras into our system, making it prediction. Fig. 2 shows the different accuracy of the prediction
highly scalable and adaptable to different environments.This cum detection results according to the different values of the
also allowed us to remotely monitor and control the cameras, confidence interval.
enabling us to quickly respond to any potential threats or
incidents.

IV. RESULTS AND ANALYSIS

In this proposed paper, we have considered around 1500 images


of each animal species. We divided the wholedataset into
various sections, some data for the training phase and some
for the testing phase. Various Machine Learning and Deep
Learning models were applied to the datasets such as Yolo v5.
Table 1 shows the training results after 50 epochs.

Class Images Instances P R mAP50 mAP50-


95
All 1986 2489 0.872 0.858 0.904 0.584
Bear 1986 326 0.874 0.837 0.905 0.589
Deer 1986 248 0.86 0.895 0.91 0.689
Elephant 1986 477 0.826 0.883 0.909 0.671
Leopard 1986 372 0.938 0.919 0.961 0.568
Monkey 1986 316 0.867 0.794 0.869 0.496
Tiger 1986 333 0.942 0.871 0.932 0.645

Wild 1986 417 0.8 0.804 0.845 0.434


Boar

As shown in Table 1, we got fair results, the combined all classes'


precision was 0.872 with a recall value of 0.858 making our
mAP over confidence value 0.5 equal to 0.904 and that with the
confidence interval of 0.5:0.95 equal to
0.584. The class with the highest mAP at the confidence
interval of 0.5 is the Leopard class having an mAP equal to
0.961. The class with the highest mAP at the confidence
interval of 0.5:0.95 is the Deer class having an mAP equal to
0.689. The class with the least mAP at the confidence
interval of 0.5 is the wild boar class having an mAP equal to
0.845. The class with the highest mAP at the confidence Fig. 2 Change of the F1 score per the confidence value. The
interval 0.5:0.95 is also the wild boar class having an mAP
F1 score of the model increases rapidly till a confidence
value of 0.15 and then reaches the max of 0.86 at 0.395 and
then degrades down rapidly to almost 0 with a
confidence
value of 1. There are two factors of the f1 score i.e., precision
and recall. Let’s now study them uniquely. Down below fig.3
and Fig. 4 show the relation of the confidence value with the
precision and recall values respectively.

Fig. 4 Relation between the recall and the confidence value


of the model.

As we can see that the precision of the model initially increases


rapidly till the confidence value reaches 0.17 and then increases
Fig. 3 Relation between the precision and the confidence gradually till the end besides a gradual dip in the three classes
value of the model. of the animals, namely, Deer, Monkey and Wild Boar. All the
classes' precision reaches 1 at a confidence value of 0.923. In
Fig. 4, the recall is at a maximum value of 0.96 at a confidence
value of 0.00. Then it starts to decline at a slow rate initially and
then rapidly. The recall value reaches almost 0 at the confidence
value of approximately 1. Let’s now study the correlation
between precision and recall. Fig. 5 shows the precision-recall
curve of the model.
Fig. 6 Confusion Metrix - Correlation between the animal
classes.
According to the above confusion matrix, we see that there is
merely any confusion between the different classes whereas
we can see major instances where the background
is detected as elephant and wild boar classes more often. This
can be due to the camouflage of the animals and can be reduced
by refining the images.
Fig. 5 Precision-Recall curve of the model at confidence
value 0.5. Furthermore, we can also consider augmenting the dataset with
more images of different angles and lighting conditions,
The above curve clearly shows that precision-recall shares which will make our model more robust to variations in the real-
an inverse relationship with each other. As soon as the recall is world scenario.
increased, the precision of the results got hampered. The
precision of the results can be compromised till the mAP of all In addition, we can also explore other object detection models
classes reaches 0.904 at the edge of the curve and then again such as EfficientDet, RetinaNet, and Mask R-CNN to see if they
starts to reduce by the increase in the recall value. We now will give better results for our use case.
study the correlation cum similarities in the appearances of
the classes that we worked upon. Down below fig. 6 shows
the apparent similarity between the classes.
Overall, by using a combination of transfer learning,
hyperparameter tuning, ensemble methods, dataset
augmentation, and exploring different object detection
models, we can further improve the accuracy of our proposed
model for wildlife conservation.
V. Conclusion and Future Scope
n this research paper, we proposed a digital
I fencing echanism using a Deep Learning algorithm to
mtackle the allenges of physical fencing such as being chtime-
nsuming, expensive, unmaintainable, etc. To co be
articular, we designed a ready-to-use version of yoloV5 pas
object detection technique for the classification of the animals
that came in a certain region covered by the anmeras.
Thus, our approach did not affect animal rights as ey ca were
not being continuously tracked like the GPS and ther
h methods of prevention unless they appeared in a
to estricted area. To implement this work, we created our own
rataset of 10,000 images belonging to seven different
d tegories of animals. As a result, we achieved classification
ca ith a precision of 0.872, recall of 0.858, mAP@0.5 of
w.904, and mAP@0.5:0.95 of 0.584.
0 ture work in this area would involve designing a more
Fvuanced version of the YOLO algorithm with an even large
adataset containing more no. of real-time quality images that ay
dbe provided by the Forest Department of India itself.
m

You might also like