A Design of Novel Method for Classification of Waste Materials with its location using Deep Learning and Computer Vision for Smart Cities
Journal Title: International Journal of Innovative Research in Computer Science and Technology - Year 2021, Vol 9, Issue 6
Abstract
Waste management is the one of the main problems in all over the globe, presently waste materials are collected and sorted by hand, it is very time consuming and it also requires so much man power. Improper management of waste materials leads to hazards including environmental deterioration, soil contamination, water pollution, and air pollution. To solve this problem, there may be a requirement for an automatic method to aid to recognize the type of waste substances and it’s Position. Today’s technology is so sophisticated due of Artificial Intelligence and Machine Learning. These technologies may be utilized to address various real time issues, this article handles the fundamental challenge of detecting and separating the waste items like plastic, paper and metal with their location. In this article above stated issue is addressed using the Faster RCNN (Region Based Convolutional Neural Networks) model which is very much accurate compared to other algorithms like YOLO (You Look Only Once) and other similar algorithms. The model is trained on a custom dataset gathered on a mobile camera and pre-processed using Label-Img Tool. Data collected with different light conditions and in unique angles. The model is trained using Faster R-CNN identify objects and to obtain locations. This may assist individuals to keep their surroundings tidy and to become conscious of the garbage substances and to identify them. This paper has been precisely recognizing kind of items and places with higher accuracy.
Authors and Affiliations
Dr. Ashish Oberoi
Keywords
Related Articles
- EP ID EP747151
- DOI 10.55524/ijircst.2021.9.6.71
- Views 52
- Downloads 0
Performance, Emission & Combustion Characteristics of I.C Engine Using Jatropha Methyl Ester Oil and Bio-Diesel Blends
This essay is focused on the idea of suggesting an alternative fuel for diesel engines. The experiments show that the diesel-biodiesel blends can be used as substitute fuels for diesel engines. Recent studies have demons...
IoT Based Sound and Air Pollution Measuring Temperature and Humidity Monitoring System
Now a day in metropolitan cities air and sound pollution becomes serious issues, because of high decibels and toxic gases present within the environment which directly effect on human health and thus needs a special atte...
A Survey on Feature Selection in Data Mining
Feature Selection is a fundamental problem in machine learning and data mining . Feature Selection is an effective way for reducing dimensionality, removing irrelevant data increasing learning accuracy. Feature Selection...
Object Detection Using Convolutional Neural Networks: A Review
The amount of data on the Internet has increased dramatically as a result of the advent of intelligent devices and social media. Object detection has become a popular international study topic as an important element of...
An Evaluation of the Current Status of Agricultural Implements Manufacturing Industries: Emission of Pollutants Perspective
Agricultural Implements manufacturing industries use raw material from the Iron and steel industry to produces agricultural machinery products. If we explore the research done in past, a majority of work has been taken o...