A Rotational Libra R-CNN Method for Ship Detection

A Rotational Libra R-CNN Method for Ship Detection

₹5,500.00
Product Code: python - Deep Learning
Availability: In Stock
Viewed 1467 times

Product Description

Aim:

To automate the detection of presence of ships and to classify the types of ships available in the given Image.

Synopsis:

High resolution satellite image processing is one of the most growing fields in research today. There is so much to explore and so many ways to do it that it seems full of endless opportunities and possibilities. There are several features which can be extracted like buildings, roads etc. from land satellite images and ships, boats etc. from satellite images of sea and ocean. In this paper we will be concentrating on detecting ships automatically from the images obtained by various satellites. This is one of the major challenging tasks due to various disturbances and noises in these kinds of images. Ships can be found in different sizes as well as shapes which make it more difficult to find a pattern or some regularity in these images. It is comparatively easier in homogeneous environment consisting of just ships of different types in water. But when it comes to heterogeneous environment consisting of other elements like coasts, harbor, vessel, rocks, islands etc. the challenge increases tenfold. There are various statistical and image processing approaches which can do this manually then again this won’t be that efficient, changing the parameters again and again with different images and all can be a time consuming and tedious process. That’s why we choose one of the modern approaches which provide us with the opportunity of being automatic or at least semi-automatic, deep learning. Deep learning together with computer vision opens doors to the possibilities which we couldn’t even have thought of. In this paper we will be exploring those possibilities with the help of a certain Convolutional neural network known as Mask R_CNN and implementing it using transfer learning. This algorithm gives very high accuracy in classification of satellite images without doing any manual extraction and works with complex heterogeneous backgrounds too.


Proposed System:

This end-to-end system contains four sub-networks with different functions. The feature map of the input image is obtained by the Feature Pyramid Network (FPN) first, and then the scene mask of target and non-target area is extracted by the scene mask extraction network (SMEN). With the feature combination between the output of FPN and the estimated scene mask, the false alarm targets existing in non-target area are eliminated entirely. Then Region Proposal Network (RPN) uses the combined feature map to generate the proposed bounding boxes. After computing the RoI, we have to compute the IoU over all of the predicted regions. IoU stands for Intersection over Union and is calculated with the help of ground truths. This completes the process of Mask RCNN, where we get the masks for the objects in the image. Therefore, we took help from the pretrained weights of the COCO dataset trained on the Mask RCNN model.

When you order from finalyearprojects.in, you will receive a confirmation email. Once your order is shipped, you will be emailed the tracking information for your order's shipment. You can choose your preferred shipping method on the Order Information page during the checkout process.

The total time it takes to receive your order is shown below:

The total delivery time is calculated from the time your order is placed until the time it is delivered to you. Total delivery time is broken down into processing time and shipping time.

Processing time: The time it takes to prepare your item(s) to ship from our warehouse. This includes preparing your items, performing quality checks, and packing for shipment.

Shipping time: The time for your item(s) to tarvel from our warehouse to your destination.

Shipping from your local warehouse is significantly faster. Some charges may apply.

In addition, the transit time depends on where you're located and where your package comes from. If you want to know more information, please contact the customer service. We will settle your problem as soon as possible. Enjoy shopping!

Download Abstract

Click the below button to download the abstract.

Package Includes

Software Projects Includes

  1. Demo  Video
  2. Abstract
  3. Base paper
  4. Full Project PPT
  5. UML Diagrams
  6. SRS
  7. Source Code
  8. Screen Shots
  9. Software Links
  10. Reference Papers
  11. Full Project Documentation
  12. Online support


The Delivery time for software projects is 2 -3 working days. Some of the software projects will require Hardware interface. Please go through the hardware Requirements in the abstract carefully. The Hardware will take 7-8 Working Days

 

Hardware Projects Includes

  1. Demo  Video
  2. Abstract
  3. Base paper
  4. Full Project PPT
  5. Datasheets
  6. Circuit Diagrams
  7. Source Code
  8. Screen Shots & Photos
  9. Software Links
  10. Reference Papers
  11. Lit survey
  12. Full Project Documentation
  13. Online support


The Delivery time for Hardware projects is 7-8 working days.

   

Mini Projects: Software Includes

  1. Demo  Video
  2. Abstract
  3. Base paper
  4. Full Project PPT
  5. UML Diagrams
  6. SRS
  7. Source Code
  8. Screen Shots
  9. Software Links
  10. Reference Papers
  11. Full Project Documentation
  12. Online support

 

The Delivery time for software Miniprojects is 2 -3 working days.

 

Mini Projects - Hardware includes

  1. Demo  Video
  2. Abstract
  3. PPT
  4. Datasheets
  5. Circuit Diagrams
  6. Source Code
  7. Screen Shots & Photos
  8. Software Links
  9. Reference Papers
  10. Full Project Documentation
  11. Online support

The Delivery time for Hardware Mini projects is 7-8 working days.