Home / Current Issue / Paper 1702129
Object Detection Using MASK R-CNN
Subject area: Science,Engineering and Technology · Area of research: Electronics and Communication Engineering
Abstract
In today's world, Automation takes the front seat of growth, and one of the important things for that machine vision. We need good models for better results for computer vision. Here we present a conceptually clear, versatile, and general structure for segmentation of object instances. Our model detects objects in an image more efficiently and at the same time it generates a high quality segmentation mask for each object in the image. The model is called Mask R-CNN it actually extends Faster R-CNN model by adding a branch to predict an object mask in parallel with the bounding box recognition branch. Mask R-CNN is quick to train and adds a slight overhead to Faster R-CNN which runs at 5 fps. In addition, Mask R-CNN is easy to generalize for other functions, e.g. allowing us to estimate human poses within the same framework.
Keywords
CNN (Convolution Neural Network), ROI (Region of Interest), Instance Segmentation, Region Proposal Nertwork (RPN)
How to cite this paper
@article{1702129,
author = {K. Maruthi Pavan Surya, M. Padmasri Balasubrahmanyam, N. Kumar Venkata Siva, M. Venkata Sivanjaneyulu},
title = {Object Detection Using MASK R-CNN},
journal = {Iconic Research And Engineering Journals},
year = {2020},
volume = {3},
number = {10},
pages = {18-22},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1702129.pdf},
abstract = {In today's world, Automation takes the front seat of growth, and one of the important things for that machine vision. We need good models for better results for computer vision. Here we present a conceptually clear, versatile, and general structure for segmentation of object instances. Our model detects objects in an image more efficiently and at the same time it generates a high quality segmentation mask for each object in the image. The model is called Mask R-CNN it actually extends Faster R-CNN model by adding a branch to predict an object mask in parallel with the bounding box recognition branch. Mask R-CNN is quick to train and adds a slight overhead to Faster R-CNN which runs at 5 fps. In addition, Mask R-CNN is easy to generalize for other functions, e.g. allowing us to estimate human poses within the same framework.},
keywords = {CNN (Convolution Neural Network), ROI (Region of Interest), Instance Segmentation, Region Proposal Nertwork (RPN)},
month = {April},
}