Scholarlink

<p>The Curiosity rover is a robotic vehicle launched by National Aeronautics and Space Administration (NASA) for exploring Mars. Often the quality of Martian images (MIs) are impacted by insufficient lighting and adverse environmental conditions. Deteriorated quality hinders the content-based screening, self-diagnostics, and terrain classification.&#xa0;A metaheuristics-equipped automated algorithm for quality compensation of MIs (MAAQCMI) is introduced in this paper.&#xa0;The MAAQCMI is a composite framework comprising a human contrast sensitivity-based sigmoid intensity transformation (HCSIT) and an integrated module of slime mold optimizer (SMO) and natural image quality evaluator (NIQE) fitness meant for incorporating auto-tuning functionality to the MAAQCMI. The MAAQCMI shows a contrast improvement ratio (CIR) (1.21 ± 0.09) higher than one, negligibly low lightness order error (LOE) (2.35 ± 3.86) and sparse feature fidelity (SFF) (0.97 ± 0.01) close to one on a dataset comprising 100 low quality MIs.&#xa0;The MAAQCMI produces quality compensated MIs with improved contrast, without injecting any colour distortions and causing any information loss.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Metaheuristics-equipped automated contrast enhancement for images from mast camera onboard curiosity Rover

  • 期刊论文

  • 发表日期：

    2025年12月12日

查看全文
  • S. Sathish,
  • J. Shanmugapriyan,
  • R. Praveen Kumar,
  • S. Vinurajkumar,
  • Vipin Venugopal

摘要

The Curiosity rover is a robotic vehicle launched by National Aeronautics and Space Administration (NASA) for exploring Mars. Often the quality of Martian images (MIs) are impacted by insufficient lighting and adverse environmental conditions. Deteriorated quality hinders the content-based screening, self-diagnostics, and terrain classification. A metaheuristics-equipped automated algorithm for quality compensation of MIs (MAAQCMI) is introduced in this paper. The MAAQCMI is a composite framework comprising a human contrast sensitivity-based sigmoid intensity transformation (HCSIT) and an integrated module of slime mold optimizer (SMO) and natural image quality evaluator (NIQE) fitness meant for incorporating auto-tuning functionality to the MAAQCMI. The MAAQCMI shows a contrast improvement ratio (CIR) (1.21 ± 0.09) higher than one, negligibly low lightness order error (LOE) (2.35 ± 3.86) and sparse feature fidelity (SFF) (0.97 ± 0.01) close to one on a dataset comprising 100 low quality MIs. The MAAQCMI produces quality compensated MIs with improved contrast, without injecting any colour distortions and causing any information loss.