Polymetallic nodules enriched in Mn, Ni, Cu, Co, and other metals may be one of the first seabed mineral resources to be exploited. Although optical imagery is crucial for resource evaluation, semi-buried nodules are frequently overlooked. To address this, we propose a framework that integrates the elliptic approximation method (EAM) and the contour interweaving method (CIM) to reconstruct three types of semi-buried nodules segmented by U-Net: edge-buried, partition-buried, and almost-completely-buried. This strategy introduced a decision-making mechanism based on category fusion, which significantly enhanced the robustness and practicality of the reconstruction. Performance was assessed using four metrics: area ratio, absolute percentage change, intersection-over-union, and Chamfer distance. Among 1785 samples, the EAM recovered up to 41.8% of lost area, which substantially improved the minimum values of area ratio and intersection-over-union, and it performed well on almost-completely-buried nodules. The CIM achieved median area ratio and intersection-over-union values of 99.37% and 93.36%, respectively, and excelled in edge-buried and partition-buried types. Fusion experiments demonstrated the complementary strengths of both approaches: 23.96% of buried area was recovered in large-scale imagery recognized by U-Net. The proposed framework balances accuracy, adaptability, and computational efficiency, which enables real-time nodule identification on platforms with limited resources such as autonomous underwater vehicles. This could provide more direct support for resource evaluation and mining applications.

Solid mineral resources form the essential material foundation for the sustainable development of human society. The international seabed hosts vast and potentially valuable mineral deposits, among which deep-sea polymetallic nodules represent a key marine resource. Focusing on a specific area in the Western Pacific, this study aims to identify and classify small-scale polymetallic nodules in the deep-sea environment. We employ super-resolution reconstruction methods to enhance the resolution of deep-sea hydroacoustic images. Subsequently, a super-pixel segmentation approach is applied to construct a sample enhancement model for deep-sea objects, enabling in-depth extraction of multi-dimensional heterogeneous features from seabed targets and facilitating the effective development of training samples. Constrained by geological seabed samples, an accurate recognition model for seabed polymetallic nodules is established, achieving intelligent mineral classification based on multi-source data such as bathymetry and backscatter. Ultimately, by leveraging the generalization capability of the model, the recognition and classification of untrained samples can be accomplished, thereby promoting the application of the proposed algorithm in large-scale deep-sea mineral exploration.