Design and Implementation of Convolutional Neural Networks Based Image Extraction

Project Title

Design and Implementation of Convolutional Neural Networks Based Image Extraction

Project Area of Specialization Artificial IntelligenceProject Summary

The project is regarding deep learning adn in sub domain of artificial intelligence. The system would take a picture with the help of a camera and feed it to a raspberry pi.that would detect objects present within that image and be able to localize them as well using a convolutional neural network.
 

   

Project Objectives

The aim is to design and train a convolutional neural network to be able to recognize objects within an image. The system would be running on a hardware assembly comprising of raspberry pi,GPU and camera.

Project Implementation Method

Designing a convolutional neural network for the task.
Training the network.
Testing the CNN for the job.
Embedding it into GPU supported system.

System will be able to detect objects within an image.

Benefits of the Project

Applications of Object detection are wide and can be used in industry to improve production by tracing a faulty object and can also be used in logistics for automatic registration of products and record tracking. It can be used in UAV's for defense, agriculture surveillance purpose.  
 

Technical Details of Final Deliverable

The final deliverable will be in the form of hardware running convolutional neural network and camera, that would be able to detect objects.

Final Deliverable of the Project HW/SW integrated systemCore Industry ManufacturingOther Industries Security Core Technology Artificial Intelligence(AI)Other Technologies RoboticsSustainable Development Goals Industry, Innovation and InfrastructureRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	58000
NVIDIA GTX 1060	Equipment	1	30000	30000
Raspberry Pi	Equipment	1	18000	18000
camera	Equipment	1	10000	10000