The primary task of marine surveillance is to construct a perfect marine situational awareness (MSA) system that serves to safeguard national maritime rights and interests and to maintain blue homeland security. Progress in maritime wireless communication, developments in artificial intelligence, and automation of marine turbines together imply that intelligent shipping is inevitable in future global shipping. Computer vision-based situational awareness provides visual semantic information to human beings that approximates eyesight, which makes it likely to be widely used in the field of intelligent marine transportation. We describe how we combined the visual perception tasks required for marine surveillance with those required for intelligent ship navigation to form a marine computer vision-based situational awareness complex and investigated the key technologies they have in common. Deep learning was a prerequisite activity. We summarize the progress made in four aspects of current research: full scene parsing of an image, target vessel re-identification, target vessel tracking, and multimodal data fusion with data from visual sensors. The paper gives a summary of research to date to provide background for this work and presents brief analyses of existing problems, outlines some state-of-the-art approaches, reviews available mainstream datasets, and indicates the likely direction of future research and development. As far as we know, this paper is the first review of research into the use of deep learning in situational awareness of the ocean surface. It provides a firm foundation for further investigation by researchers in related fields.

It is crucial for unmanned surface vessels (USVs) to detect and track surrounding vessels in real time to avoid collisions at sea. However, the harsh maritime environment poses great challenges to multitarget tracking (MTT). In this paper, a novel tracking by detection framework that integrates the multimodel and multicue (M³C) pipeline is proposed, which aims at improving the detection and tracking performance. Regarding the multimodel, we predicted the maneuver probability of a target vessel via the gated recurrent unit (GRU) model with an attention mechanism, and fused their respective outputs as the output of a kinematic filter. We developed a hybrid affinity model based on multi cues, such as the motion, appearance, and attitude of the ego vessel in the data association stage. By using the proposed ship re-identification approach, the tracker had the capability of appearance matching via metric learning. Experimental evaluation of two public maritime datasets showed that our method achieved state-of-the-art performance, not only in identity switches (IDS) but also in frame rates.

High-resolution wind resource assessment over complex terrain is often limited by the high computational cost of fine-scale wind modeling, leading to underestimation of wind power density (WPD) hotspots and unreliable wind-farm preliminary siting. To overcome these challenges, this study proposes PCDR-Net, a terrain-aware physics-constrained deformable residual network that reconstructs 1 km near-surface wind fields from coarse-resolution inputs. By integrating dynamic wind-field sequences and capturing multiscale spatial patterns with flow-consistent constraints, PCDR-Net enables physically plausible reconstruction of high-resource wind structures critical for wind energy conversion. Evaluating the entire Sichuan Province with a merged 1 km resolution dataset, PCDR-Net reduced root mean square error by 44.66% compared to bilinear interpolation and achieved a 10% WPD F1 score of 0.6120. Turbine-level and farm-level validations confirmed its robustness and energy relevance, with turbine-level active-power RMSE of 665.43 kW and farm-level nRMSE of 26.08%. These results demonstrate PCDR-Net's potential for accurate wind resource management, identification of high-WPD hotspots, and preliminary wind-energy planning in complex terrain.