Indian Journal of Science and Technology
DOI: 10.17485/IJST/v16i42.2005
Year: 2023, Volume: 16, Issue: 42, Pages: 3778-3785
Original Article
J Srilatha1*, T S Subashini2, K Vaidehi3
1Research Scholar, Department of CSE, Annamalai University, Chidambaram, 608002, TamilNadu, India
2Professor, Department of CSE, Annamalai University, Chidambaram, 608002, Tamil Nadu, India
3Associate Professor, Department of CSE, Stanley College of Engineering and Technology for Women, Hyderabad, 500001, Telangana, India
*Corresponding Author
Email: [email protected]
Received Date:26 June 2023, Accepted Date:03 October 2023, Published Date:13 November 2023
Objective: To develop a two-stage object detection method based on convolutional neural networks (CNNs) to identify and classify solid waste, contributing to the creation of intelligent systems for society. Methods: The study utilizes a base network, ResNet 101, to generate convolution feature maps. In the first stage, a Region Proposal Network (RPN) is created on top of these convolution features, producing 256-dimensional feature vectors, objectness scores, and bounding rectangles for different anchor boxes. In the next stage, the region proposals are used to train a softmax layer and regressor, enabling the classification and localization of five types of solid waste, namely cardboard, glass, metal, paper and plastic. Findings: The proposed Faster RCNN demonstrates nearly real-time object detection rates. Experimental results reveal that the Faster RCNN with ResNet 101 and RPN achieves an accuracy of 96.7%, outperforming the Faster RCNN with a simple CNN, which achieves an accuracy of 86.7%. Novelty: Unlike traditional R-CNN, which relies on computationally inefficient selective search, the proposed Faster RCNN employs RPN, a small neural network sliding on the last convolution layer's feature map, predicting object presence and bounding boxes. This approach significantly improves efficiency compared to the exhaustive examination in R-CNN's selective search.
Keywords: Object Detection, RCNN, Fast RCNN, Faster RCNN, RPN, ROI pooling
© 2023 Srilatha et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)
Subscribe now for latest articles and news.