Real-time Positioning Method Based on Binocular Vision for Autonomous Underwater Capture Robots

To meet real-time positioning requirements of underwater harvesting robots, a binocular vision-based localization system is designed. This system provides spatial coordinates of underwater targets for robotic harvesting operations. For degraded images in aquatic environments, a wavelet transform-based enhancement algorithm is developed. This algorithm can rapidly process binocular images to correct color distortion and enhance details. By implementing a lightweight attention mechanism for the detection model, targets can be identified faster and more precisely. Finally, according to the binocular parallax and remapping matrix, the three-dimensional coordinates of the fishing object can be calculated. Experiments were conducted in both clear and turbid water. Results demonstrate that the system satisfies practical requirements in feasibility and localization accuracy for harvesting robots. Supplementary Material File (real-time positioning method based on binocular vision.pdf) - Download - 1.92 MB Information & Authors Information Version history Copyright This work is licensed under a Non Exclusive No Reuse License.

Authors Metrics & Citations Metrics Article Usage 164views 98downloads Citations Download citation Shengfeng Jiang, Lin Zhang, Yunfeng Bi. Real-time Positioning Method Based on Binocular Vision for Autonomous Underwater Capture Robots. Authorea. 25 September 2025. DOI: https://doi.org/10.22541/au.175882572.21555607/v1 DOI: https://doi.org/10.22541/au.175882572.21555607/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu.