ICTACT Journal on Soft Computing

Open Access Open Access  Restricted Access Subscription Access

Next-Gen Remote Sensing: RCNN and Ant Colony Optimization for Accurate Land Cover Mapping


Affiliations
1 Department of Department of Computer Science and Engineering, Rajalakshmi Institute of Technology, India
2 Department of Mathematics, KCG College of Technology, India
3 Department of Mechanical Engineering, Mangalore Institute of Technology and Engineering, India
4 Department of Computer Science and Engineering-Cyber Security, K S R College of Engineering, India

   Subscribe/Renew Journal


Accurate land cover mapping is crucial for various applications, from environmental monitoring to urban planning. Traditional methods often struggle with high-dimensional data and complex landscape features. This study integrates RCNN (Region-based Convolutional Neural Network) and ANT Colony Optimization (ACO) to enhance land cover mapping accuracy. RCNN is utilized for precise segmentation of high-resolution satellite imagery, while ACO is employed for effective feature extraction, leveraging the algorithm's ability to identify and optimize features in the presence of complex patterns. Our method was evaluated using a dataset of 500 km², achieving a segmentation accuracy of 92.5% and a feature extraction precision improvement of 18.3% compared to conventional techniques. The integration of RCNN and ACO demonstrates significant advancements in capturing detailed land cover information and improving overall mapping accuracy

Keywords

RCNN, ANT Colony Optimization, Land Cover Mapping, Remote Sensing, Feature Extraction
Subscription Login to verify subscription
User
Notifications
Font Size

Abstract Views: 123




  • Next-Gen Remote Sensing: RCNN and Ant Colony Optimization for Accurate Land Cover Mapping

Abstract Views: 123  | 

Authors

O. Pandithurai
Department of Department of Computer Science and Engineering, Rajalakshmi Institute of Technology, India
P.M. Sithar Selvam
Department of Mathematics, KCG College of Technology, India
Arun Krishnan
Department of Mechanical Engineering, Mangalore Institute of Technology and Engineering, India
R. Manoja
Department of Computer Science and Engineering-Cyber Security, K S R College of Engineering, India

Abstract


Accurate land cover mapping is crucial for various applications, from environmental monitoring to urban planning. Traditional methods often struggle with high-dimensional data and complex landscape features. This study integrates RCNN (Region-based Convolutional Neural Network) and ANT Colony Optimization (ACO) to enhance land cover mapping accuracy. RCNN is utilized for precise segmentation of high-resolution satellite imagery, while ACO is employed for effective feature extraction, leveraging the algorithm's ability to identify and optimize features in the presence of complex patterns. Our method was evaluated using a dataset of 500 km², achieving a segmentation accuracy of 92.5% and a feature extraction precision improvement of 18.3% compared to conventional techniques. The integration of RCNN and ACO demonstrates significant advancements in capturing detailed land cover information and improving overall mapping accuracy

Keywords


RCNN, ANT Colony Optimization, Land Cover Mapping, Remote Sensing, Feature Extraction