Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Arun-Kumar21/RCNN-pytorch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RCNN - Object Detection and Semantic Segmentation

This repository provides a PyTorch implementation of the original RCNN research paper, focusing on object detection and semantic segmentation.

TODO List

  • Implement region proposal using selective search.
  • Fine-tune AlexNet on the VOC dataset.
  • Implement a bounding box regressor for precise localization.
  • Apply Non-Maximum Suppression (NMS) to reduce overlapping boxes.
  • Improve accuracy by integrating a VGG-based architecture.

Region Proposal using Selective Search

We use selective search to extract approximately 2000 region proposals per image for object detection.

The resulting output looks like this:

Original Image Region Proposal Image
Original Image Region Proposal
Original Image Region Proposal

Object Detection using AlexNet with Bounding Box Regressor

We fine-tune AlexNet on the VOC dataset to classify objects and employ a bounding box regressor for enhanced localization accuracy.

The resulting output looks like this:

Original Image Detected Objects
Original Image Detected Objects
Original Image Detected Objects

Non-Maximum Suppression (NMS) for Reducing Overlapping Boxes

Non-Maximum Suppression (NMS) is applied to eliminate overlapping bounding boxes, ensuring that only the most confident prediction is retained for each detected object.

The resulting output looks like this:

Original Image After NMS
Original Image After NMS

Contributors

This project is maintained and developed by:

  • Arun Kumar
  • Deepak Diwan
  • Satyam Kumar
  • Mansi Aggarwal

About

RCNN pytorch implementation

Resources

Stars

Watchers

Forks

Languages