You are on page 1of 9

Project Proposal Presentation

AUTOMATION OF FARMING
USING DEEP LEARNING

By
Divyansh Tiwari
Roll No : N283
Sap Id: 70471118091
Course: MBA-Tech CS

Under the guidance of


Prof. Varun Deshmukh

Department of Computer Engineering MPSTME, Shirpur Campus 2020-2021


10/19/2021 1
Outline
• Synopsis
• Goals
• Proposed Methodology
• Timeline

2
Synopsis
• Automation in the agricultural sector is extremely
imperative in order to boost the growth of this sector.

• Deep-Learning based methods have emerged as a possible


way to perform this automation

• System which makes plucking vegetables from farms just


like a human do will surely improve the efficiency of
farmers.

3
Goals
• The objective of this project is to make algorithms and
programs which will be capable of performing the
following tasks :

– Identify raw and ripe tomatoes in an image


– Identify raw and ripe tomatoes in a video
– Count the number of raw and ripe tomatoes in the frame
– Identify the percentage colour density of the tomato in a
video as well as in an image

4
Proposed Methodology
• The project deals with creating a program using computer
vision algorithms which detects raw & ripe tomatoes.
Overall, there are 4 algorithms which can be used to
achieve the results mentioned in the introduction. The 4
algorithms are:
• R-CNN
• Fast R-CNN
• Faster R-CNN
• YOLO V3

5
Proposed Methodology
• Out of all the above-mentioned approaches, YOLOv3 was
chosen for this project because of the following reasons:

• Detection speed and accuracy of YOLOv3 meets the real-


time requirements for the detection process
• Precision on small objects is provided the best by YOLOv3
• YOLOv3 uses a multi-label approach which allows classes
to be more specific and be multiple for individual
bounding boxes. This will be helpful when differentiating
between raw and ripe tomatoes.

6
Proposed Methodology
• The dataset (images) was made available by the company.
Since it consisted of just images and no pre-trained models
were available, labeling images was necessary in order to
feed it into the model for creating a custom dataset model
using YOLOv3.
• Around 900 images of raw and ripe tomatoes were
available. Right now, the images are being labeled with
precision in order to get the maximum accuracy. These
labeled images will be used further to train the Yolo V3
model.
• Once the images are labeled, the next step is to train the
model.
7
Project Schedule
Work Schedule Expected Date of Completion Status

1. Allotment of the project 3rd May 2021 Completed


2. Research on the project topic 4th May 2021 Completed
3. Data Collection 14th May 2021 Completed
4. Data Cleaning 25th May 2021 Completed
5. Training the model on custom 28th May 2021 Pending
dataset
6. Coding for detecting tomatoes 10th June, 2021 Pending
from live camera feed
7. Coding for detecting tomatoes 13th June, 2021 Pending
from a video
8. Coding for detecting the % colour 15th June, 2021 Pending
of tomatoes
9. Coding to determine the count of 20th June, 2021 Pending
raw and ripe tomatoes
10. Presenting the generated Model 24th-25th June, 2021 Pending
to ORA rental authorities
11. Model testing on real-time data 26th -28th June, 2021 Pending
12. Project completion, issue of 1 July, 2021 Pending
reliving letter and no dues certificate
Thank You

You might also like