Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{176723,
        author = {Smita Wagh and Vaishnavi Bhavsar and Prabhanjan Shedbalkar and Prachi Suryawanshi},
        title = {AUTOMATIC DETECTION OF CRATERS & BOULDERS FROM ORBITER HIGH RESOLUTION CAMERA (OHRC) IMAGES USING AI/ML TECHNIQUES},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {7365-7374},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=176723},
        abstract = {Planetary exploration missions have returned high-resolution images that are essential for understanding geological processes and planning future missions. The identification of craters and boulders is an important part of these efforts. This paper proposes an automated detection method based on YOLOv8, which is enhanced by the Convolution Block Attention Module (CBAM) and the Efficient Channel Attention Network (ECA-Net) to improve accuracy and feature refinement.
The model is capable of correctly identifying small details in complex planetary images with attention mechanisms that also preserve computational efficiency. It performed better than Faster R-CNN, SSD, and RetinaNet in both speed and accuracy in datasets obtained from the Moon, Mars, and asteroids. This development makes the identification of landing sites much safer and guarantees complete geological analyses, thus being a significant contributor to autonomous planetary exploration.},
        keywords = {Planetary exploration, crater detection, boulder detection, YOLOv8, CBAM, ECA-Net, machine learning, deep learning},
        month = {April},
        }