Quantum Neural Networks for Enhanced Crater and Boulder Detection Using Hyper Spectral Imaging
Abstract: This study presents an advanced approach to detecting and analyzing craters and boulders using quantum neural networks and hyper spectral imaging (HSI). By leveraging pixel-by-pixel classification through semantic segmentation, our method accurately determines the edges and depths of geological features. The use of a custom quantum-based neural network with an n?n architecture enhances edge detection and reduces processing time, achieving an accuracy rate of 80%. The proposed algorithm efficiently converts RGB images into HSI data for in-depth spectral analysis, surpassing traditional Geographic Information Systems (GIS) techniques. Additionally, our approach integrates cognitive neural networks and advanced data servers to optimize location detection within a defined azimuth range. This research highlights the effectiveness of quantum-driven methodologies in improving spatial resolution and analytical precision, paving the way for enhanced geological feature classification in remote sensing applications.
Keywords: QGIS Software, IBM Qiskit, Quantum Circuit, Nanosatellite
How to Cite?: Priyanshu Halder, "Quantum Neural Networks for Enhanced Crater and Boulder Detection Using Hyper Spectral Imaging", Volume 14 Issue 2, February 2025, International Journal of Science and Research (IJSR), Pages: 176-180, https://www.ijsr.net/getabstract.php?paperid=SR25203105727, DOI: https://dx.doi.org/10.21275/SR25203105727