Hailiang Zhao

Reliable visual detection of small floating objects on the water surface is a prerequisite for environmental monitoring and clean-up tasks performed by unmanned surface vehicles (USVs) on inland waterways. Such scenes are routinely degraded by low illumination at dawn and dusk, strong specular reflections, ripple-induced clutter, and large object-scale variations, which together cause missed detections, false alarms, and unstable localization. Aiming at these practical challenges, this study conducts a scenario-oriented optimization and experimental validation based on the lightweight YOLOv11n detector. We integrate multiple mature attention mechanisms, regression loss functions and data augmentation strategies to develop an improved scheme, YOLOv11-LREP, for floating object detection. The detailed optimizations are as follows: (i) a Coordinate Attention (CoordAtt) module is inserted at the top of the backbone to enhance positional encoding and highlight obstacle-related semantic regions; (ii) three Efficient Channel Attention (ECA) modules are embedded at the multi-scale fusion nodes of the Neck so that reflection- and ripple-induced spurious channel responses can be suppressed at almost no extra cost; (iii) the Powerful-IoU (PIoU) loss replaces the original regression loss to enforce four-side boundary alignment and stabilize convergence on small, blurred-edge targets; and (iv) a joint low-light and reflection augmentation strategy, together with CutMix region-level mixing, broadens the training distribution along the illumination and occlusion axes. Experiments on the public FloW-Img dataset, split into 1200 training and 800 validation images (2024 instances) and run under a fixed random seed (seed = 0, deterministic = true), show that YOLOv11-LREP attains AP₅₀ = 80.1%, AP_50:95 = 38.5%, and AP_S = 24.3% with only 2.84 M parameters and 9.3 GFLOPs. On an NVIDIA RTX 4060 Laptop GPU, the model runs at 3.3 ms total per 640 × 640 image (≈303 FPS), satisfying real-time perception requirements while retaining lightweight deployability. The ablation results indicate that different components contribute differently to localization accuracy, small-object sensitivity, and robustness, and that the final configuration provides a balanced trade-off rather than the best value for every individual metric. A systematic threshold sensitivity analysis (F₁ fluctuation < 0.2%) demonstrates the stability of the final model.

Reliable visual detection of small floating objects on the water surface is a prerequisite for environmental monitoring and clean-up tasks performed by unmanned surface vehicles (USVs) on inland waterways. Such scenes are routinely degraded by low illumination at dawn and dusk, strong specular reflections, ripple-induced clutter, and large object-scale variations, which together cause missed detections, false alarms, and unstable localization. This paper proposes YOLO11-LREP, a lightweight detection framework built upon YOLO11n and tailored for water-surface floating-object recognition under such adverse conditions. Four complementary improvements are integrated: (i) a Coordinate Attention (CoordAtt) module is inserted at the top of the backbone to enhance positional encoding and highlight obstacle-related semantic regions; (ii) three Efficient Channel Attention (ECA) modules are embedded at the multi-scale fusion nodes of the Neck so that reflection- and ripple-induced spurious channel responses can be suppressed at almost no extra cost; (iii) the Powerful-IoU (PIoU) loss replaces the original regression loss to enforce four-side boundary alignment and stabilize convergence on small, blurred-edge targets; and (iv) a joint low-light and reflection augmentation strategy, together with CutMix region-level mixing, broadens the training distribution along the illumination and occlusion axes. Experiments on the public FloW-Img dataset, split into 1,200 training and 800 validation images (2,024 instances) and run under a fixed random seed (seed = 0, deterministic = true), show that YOLO11-LREP attains AP₅₀ = 80.1 %, AP₅₀:₉₅ = 38.5 %, and AP_S = 24.3 % with only 2.84 M parameters and 9.3 GFLOPs. On an NVIDIA RTX 4060 Laptop GPU, the model runs at 3.3 ms total per 640×640 image (≈303 FPS), satisfying real-time perception requirements while retaining lightweight deployability. Ablation experiments verify the individual and complementary contributions of each component, and a systematic threshold sensitivity analysis (F₁ fluctuation < 0.2 %) demonstrates the stability of the final model.

Recent studies on self-supervised monocular depth estimation have achieved promising results, which are mainly based on the joint optimization of depth and pose estimation via high-level photometric loss. However, how to learn the latent and beneficial task-specific geometry representation from videos is still far from being explored. To tackle this issue, we propose two novel schemes to learn more effective representation from monocular videos: (i) an Inter-task Attention Model (IAM) to learn the geometric correlation representation between the depth and pose learning networks to make structure and motion information mutually beneficial; (ii) a Spatial-Temporal Memory Module (STMM) to exploit long-range geometric context representation among consecutive frames both spatially and temporally. Systematic ablation studies are conducted to demonstrate the effectiveness of each component. Evaluations on KITTI show that our method outperforms current state-of-the-art techniques.

Abnormalities of navigation buoys include tilting, rusting, breaking, etc. Realizing automatic extraction and evaluation of rust on buoys is of great significance for maritime supervision. Severe rust may cause damage to the buoy itself. Therefore, a lightweight method based on machine vision is proposed for extracting and evaluating the rust of the buoy. The method integrates image segmentation and processing. Firstly, image segmentation technology is used to extract the metal part of the buoy based on an improved U-Net. Secondly, the RGB image is converted into an HSV image by preprocessing, and the transformation law of HSV channel color value is analyzed to obtain the best segmentation threshold and then the pixels of the rusted and the metal parts can be extracted. Finally, the rust ratio of the buoy is calculated to evaluate the rust level of the buoy. Results show that both the segmentation precision and recall are above 0.95, and the accuracy is nearly 1.00. Compared with the rust evaluation algorithm directly using the image processing method, the accuracy and processing speed of rust grade evaluation are greatly improved.