2026-10-12T17:03:47Z https://www.scidb.cn/oai

10.57760/sciencedb.37379 2026-02-13T09:45:45Z

2026-02-13 Underwater pipeline images doi:10.57760/sciencedb.37379 en A total of 20 videos were acquired using an in-house developed underwater ROV equipped with an optical imaging system comprising an HD USB low-light camera (Blue Robotics, Model: BR-100126) and LED illumination units (Blue Robotics LUMEN-VP, 1,500 lm). The videos were recorded at a resolution of 1080p and a frame rate of 30 frames per second (fps) under varying illumination conditions and across diverse underwater environments, including muddy waters, sandy seabeds, and regions with dense algal growth. From the recorded footage, image frames were extracted randomly for subsequent DL-based network training. underwater pipeline; ROV; deep learning Subhabrat Swain Akash Sahay George Rajan Varughese Satish Kumar Panda EMBARGO https://creativecommons.org/publicdomain/zero/1.0/ dataset Science Data Bank