Land Cover and Land Use Classification Approach to Maintain the Green Environment in Smart Village | IEEE Conference Publication | IEEE Xplore

Land Cover and Land Use Classification Approach to Maintain the Green Environment in Smart Village


Abstract:

India is quickly digitizing and transforming into a more intelligent nation, including smart cities and automated power transmission and distribution networks rapidly int...Show More

Abstract:

India is quickly digitizing and transforming into a more intelligent nation, including smart cities and automated power transmission and distribution networks rapidly integrating the grand scheme of things (smart metering, smart grids etc.). With about 6,000,000 villages across the country and 68% of the people living in rural areas, it is of the utmost importance to provide them with innovative technology to transform India into a smart nation. Several real-time applications, including monitoring environments, the military, surveillance, and geographic surveys, make substantial use of satellite image categorization. Thus, accurate satellite image categorization is required to improve classification accuracy. Classification of land cover relies heavily on the efficient implementation of satellite image classification using sentinel images. Recent techniques for deep learning facilitate the interpretation of temporal and spatial data for land cover categorization in remotely sensed locations. This study applies a classification approach utilizing a transfer learning model on Euro sat dataset to classify sentinel-2 images that yield in developing a thematic map. There are 27,000 categorized Sentinel-2 satellite images in the Euro sat collection, split over 13 spectral bands and ten classification levels. High computational and achievement are maximized and connected using data augmentation, early halting, and adaptive learning rates. Hence, the transfer learning model ResNet50 obtains 96% accuracy with a 90% to 10% ratio for splitting. Thus, the resulting categorization model is broadly accessible in observatory applications, which aids in developing the smart village.
Date of Conference: 09-12 August 2023
Date Added to IEEE Xplore: 20 September 2023
ISBN Information:
Conference Location: Bhubaneswar, India

I. Introduction

In the current world, remote sensing [1] [2] plays a vital function. It engages with and assists society in various fields outside hydrology, agriculture, geology, LULC, and environmental monitoring. It facilitates the evolution of the nation's ability to monitor and regulate land use and identify problem areas in unsafe places [3]. Deep Learning techniques performed the comforting performance by understanding massive data sets. The sophisticated representations of these data are performed hierarchically by the methods. Although it performs admirably when analyzing common data types, including audio, color images, text, and video, remote sensing data study is complex due to its unique properties [4]. The unique qualities of this data result from their capture by geolocated sensors [5] [6]. These data are geodetic compositions derived from various sensors with varying contents. These qualities present advanced issues in dealing with data containing different impactful variables; previous information on its source may be required. In addition, the rapid expansion of the volume of data on a global scale involves enormous metadata. However, it needs more adequate data to apply supervised machine learning techniques [7] directly. Thus, deploying deep learning algorithms is suited for handling these types of data with additional work. In addition, remote sensing is more concerned with acquiring geochemical and geophysical information than with detecting objects and classifying land cover. Thus, a technique of deep learning is required in the absence of expert proficiency. High dimensions, limited resolution, noise capture, redundant data, and sensor-related concerns are a few obstacles in this discipline. Our observation is based on Sentinel 2 satellite photos because of its accessibility, quick revisiting time, ease of collection, and capacity to facilitate classification. This research proposes a technique combining deep learning and augmentation to categorize satellite imagery-based land cover data. We show how well the model works by dividing, adding, and activating data.

References

References is not available for this document.