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 44
- Downloads 0
AI Transforming Data Networking and Cybersecurity through Advanced Innovations
The rapid expansion of data networking infrastructure has necessitated advancements in cybersecurity to mitigate increasingly sophisticated cyber threats. As the digital landscape evolves, networks are handling unprecede...
Critical Evaluation on WSNs Positioning Methods
WSN gained a lot of attention because they are small and economical devices with low power utilization, and finite computing resources are progressively being enfolded in various application situations, including environ...
Advanced Flood Monitoring and Auto Alert System
This paper contains implementation of system to monitor & control flood condition which sends alert sms in advance to people in nearby area for their security. This system will be useful to overcome current problems as i...
An Overview Benefits and Risk of Smart Healthcare Application Using Internet of Things
An Internet of Things (IoT) enables devices to gather and share data directly with one another and along with clouds, enabling for faster and more effective data collecting, recording, as well as analysis. This opens up...
A Study of WSN and Analysis of Packet Drop During Transmission
WSN is a low-power system and are often used in numerous monitoring uses, such as healthcare, environmental, and systemic health surveillance, in addition to military surveillance. It is important to reduce network resou...