Automatic Target recognition using Deep Learning Techniques

In this project, we have implemented a deep learning model that can automatically recognize the target in an image. Deep learning has evolved a lot over the past few years, it is reliable and can be used in real world applications. It is all made possible due to digital world that is generat

Project Title

Automatic Target recognition using Deep Learning Techniques

Project Area of Specialization

Artificial Intelligence

Project Summary

In this project, we have implemented a deep learning model that can automatically recognize the target in an image. Deep learning has evolved a lot over the past few years, it is reliable and can be used in real world applications. It is all made possible due to digital world that is generating huge amount data per day, efficient deep learning algorithms and fast computers. Object detection involves two things i.e. classification and localization. It means that what is name of the object and where it is located in the image. It can be done by drawing the bounding box around the object and labelling its name on top of the bounding box. To do this we need to train a deep learning model of our choice on our custom dataset. And once the model is trained then it will be to detect those custom multiple objects in the image/video. Detection can also be done in real time as well. We have performed detection on 5 classes using deep learning model called YOLOv4 on Google Colab (Cloud GPUs).

Project Objectives

• Implementation of an automatic target recognition system.
•  Recognition of target using deep learning technique.

Project Implementation Method

• Created custom datatset.
• Labelled it using "labelImg".
• Cloned the deep learning algorithm YOLOv4.
• Trained the YOLOv4 on our custom datatset on Google Colab.

Benefits of the Project

Object detection is one of the important components of many vision systems. 
It has numerous applications in: 
•    Traffic control
•    Human- computer interaction 
•    Digital forensics 
•    Gesture recognition
•    Augmented reality 
•    Visual surveillance

Technical Details of Final Deliverable

Following are the techinacal deliverables:

• Trained AI Model of around 5500 images of 5 classes.
• Script for Training on goole collab.
• Custom made data set of 5500 Images of 5 classes.
• Detailed Theisis Report.

Final Deliverable of the Project

Software System

Core Industry

IT

Other Industries

Transportation , Security

Core Technology

Artificial Intelligence(AI)

Other Technologies

Robotics

Sustainable Development Goals

Industry, Innovation and Infrastructure

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com