Real Time Object Detection and its Implementation using Deep Learning

Project Title

Real Time Object Detection and its Implementation using Deep Learning

Project Area of Specialization Artificial IntelligenceProject Summary

Our project detect objects efficiently based on YOLO algorithm by applying the algorithm on dataset of image data.

In this project, we proposed YOLOv2 neural network-based object detection. The network will be trained on a dataset collected, the detection results of the model will be observed on LCD screen.

Project Objectives

Our aim is to create an object detection model with the help of deep learning which will be capable of detecting and classifying real time objects from known class like

Car

Bicycle

Motor bike

Human

Project Implementation Method

We pass an image to the network, and it is then sent through various convolutions and pooling layers. Finally, we get the output in the form of the object’s class. For each input image, we get a corresponding class as an output. We use this technique to detect various objects in an image.

1. First, we take an image as input:
2. Then we divide the image into various regions
3. We will then consider each region as a separate image.
4.  Pass all these regions (images) to the CNN and classify them into various classes.
5.  Once we have divided each region into its corresponding class, we can combine all these regions to get the original image with the detected objects:

Benefits of the Project

Object detection is the solution for finding and classifying a variable number of objects on an image.

As our project works in real-time model, like when object comes within the sight of camera, will be detected, we have multiple applications.

They are being employed in surveillance cameras, self-driving cars, and image inspection systems. Specialization in object detection means that you will be able to work in fields like healthcare, cyber-security, vehicle manufacturing, and even marketing.

Technical Details of Final Deliverable

We used the following components in our project:

Raspberry Pi : For whole programming

Raspberry Pi Camera Module : Camera for real-time detection

Screen : For observing results

Kit : For enclosing the final body of our model

SD Card : For storing datasets and Raspberry Pi OS

Keyboard/Mouse

Cables

Power Supply

Final Deliverable of the Project HW/SW integrated systemCore Industry ITOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Industry, Innovation and InfrastructureRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	45000
Raspberry Pi	Equipment	1	20000	20000
Raspberry Pi Camera Module	Equipment	1	11000	11000
LCD	Equipment	1	3500	3500
Kit	Equipment	1	3000	3000
Keyboard, Mouse	Equipment	1	1000	1000
Cables	Equipment	1	1500	1500
Power Supply	Equipment	1	2000	2000
SD Card	Equipment	1	3000	3000