As an ecosystem in transition from land to sea, mangroves play a vital role in wind and wave protection and biodiversity maintenance. However, the invasion of Spartina alterniflora Loisel seriously damages the mangrove wetland ecosystem. To protect mangroves scientifically and dynamically, a semantic segmentation model for mangroves and Spartina alterniflora Loise was proposed based on UperNet (Swin-UperNet). In the proposed Swin-UperNet model, a data concatenation module was proposed to make full use of the multispectral information of remote sensing images, the backbone network was replaced with a Swin transformer to improve the feature extraction capability, and a boundary optimization module was designed to optimize the rough segmentation results. Additionally, a linear combination of cross-entropy loss and Lovasz-Softmax loss was taken as the loss function of Swin-UperNet, which could address the problem of unbalanced sample distribution. Taking GF-1 and GF-6 images as the experiment data, the performance of the Swin-UperNet model was compared against that of other segmentation models in terms of pixel accuracy (PA), mean intersection over union (mIoU), and frames per second (FPS), including PSPNet, PSANet, DeepLabv3, DANet, FCN, OCRNet, and DeepLabv3+. The results showed that the Swin-UperNet model achieved the best PA of 98.87% and mIoU of 90.0%, and the efficiency of the Swin-UperNet model was higher than that of most models. In conclusion, Swin-UperNet is an efficient and accurate model for mangrove and Spartina alterniflora Loise segmentation synchronously, which will provide a scientific basis for Spartina alterniflora Loise monitoring and mangrove resource conservation and management.

Diabetic retinopathy (DR) is a microvascular complication of diabetes. Microaneurysms (MAs) are often observed in the retinal vessels of diabetic patients and represent one of the earliest signs of DR. Accurate and efficient detection of MAs is crucial for the diagnosis of DR. In this study, an automatic model (MA-YOLO) is proposed for MA detection in fluorescein angiography (FFA) images. To obtain detailed features and improve the discriminability of MAs in FFA images, SwinIR was utilized to reconstruct super-resolution images. To solve the problems of missed detection of small features and feature information loss, an MA detection layer was added between the neck and the head sections of YOLOv8. To enhance the generalization ability of the MA-YOLO model, transfer learning was conducted between high-resolution images and low-resolution images. To avoid excessive penalization due to geometric factors and address sample distribution imbalance, the loss function was optimized by taking the Wise-IoU loss as a bounding box regression loss. The performance of the MA-YOLO model in MA detection was compared with that of other state-of-the-art models, including SSD, RetinaNet, YOLOv5, YOLOX, and YOLOv7. The results showed that the MA-YOLO model had the best performance in MA detection, as shown by its optimal metrics, including recall, precision, F1 score, and AP, which were 88.23%, 97.98%, 92.85%, and 94.62%, respectively. Collectively, the proposed MA-YOLO model is suitable for the automatic detection of MAs in FFA images, which can assist ophthalmologists in the diagnosis of the progression of DR.

Introduction: Diabetic macular edema (DME) is a major cause of vision impairment in the patients with diabetes. Optical Coherence Tomography (OCT) is an important ophthalmic imaging method, which can enable early detection of DME. However, it is difficult to achieve high-efficiency and high-precision extraction of DME in OCT images because the sources of OCT images are diverse and the quality of OCT images is not stable. Thus, it is still required to design a model to improve the accuracy of DME extraction in OCT images.Methods: A lightweight model (DME-DeepLabV3+) was proposed for DME extraction using a DeepLabV3+ architecture. In this model, MobileNetV2 model was used as the backbone for extracting low-level features of DME. The improved ASPP with sawtooth wave-like dilation rate was used for extracting high-level features of DME. Then, the decoder was used to fuse and refine low-level and high-level features of DME. Finally, 1711 OCT images were collected from the Kermany dataset and the Affiliated Eye Hospital. 1369, 171, and 171 OCT images were randomly selected for training, validation, and testing, respectively.Conclusion: In ablation experiment, the proposed DME-DeepLabV3+ model was compared against DeepLabV3+ model with different setting to evaluate the effects of MobileNetV2 and improved ASPP on DME extraction. DME-DeepLabV3+ had better extraction performance, especially in small-scale macular edema regions. The extraction results of DME-DeepLabV3+ were close to ground truth. In comparative experiment, the proposed DME-DeepLabV3+ model was compared against other models, including FCN, UNet, PSPNet, ICNet, and DANet, to evaluate DME extraction performance. DME-DeepLabV3+ model had better DME extraction performance than other models as shown by greater pixel accuracy (PA), mean pixel accuracy (MPA), precision (Pre), recall (Re), F1-score (F1), and mean Intersection over Union (MIoU), which were 98.71%, 95.23%, 91.19%, 91.12%, 91.15%, and 91.18%, respectively.Discussion: DME-DeepLabV3+ model is suitable for DME extraction in OCT images and can assist the ophthalmologists in the management of ocular diseases.

Target detection in offshore unmanned aerial vehicle data is still a challenge due to the complex characteristics of targets, such as multi-sizes, alterable orientation, and complex backgrounds. Herein, a YOLO-based detection model (YOLO-D) was proposed for target detection in offshore unmanned aerial vehicle data. Based on the YOLOv3 network, the residual module was improved by establishing dense connections and adding a dual-attention mechanism (CBAM) to enhance the use of features and global information. Then, the loss function of the YOLO-D model was added to the weight coefficients to increase detection accuracy for small-size targets. Finally, the feature pyramid network (FPN) was replaced by the secondary recursive feature pyramid network to reduce the impacts of a complicated environment. Taking the car, boat, and deposit near the coastline as the targets, the proposed YOLO-D model was compared against other models, including the faster R-CNN, SSD, YOLOv3, and YOLOv5, to evaluate its detection performance. The results showed that the evaluation metrics of the YOLO-D model, including precision (Pr), recall (Re), average precision (AP), and the mean of average precision (mAP), had the highest values. The mAP of the YOLO-D model increased by 37.95%, 39.44%, 28.46%, and 5.08% compared to the faster R-CNN, SSD, YOLOv3, and YOLOv5, respectively. The AP of the car, boat, and deposit reached 96.24%, 93.70%, and 96.79% respectively. Moreover, the YOLO-D model had a higher detection accuracy than other models, especially in the detection of small-size targets. Collectively, the proposed YOLO-D model is a suitable model for target detection in offshore unmanned aerial vehicle data.

Underwater object detection, as the principal means of underwater environmental sensing, plays a significant part in the marine economic, military, and ecological fields. Due to the degradation problems of underwater images caused by color cast, blurring, and low contrast, we proposed a model for underwater object detection based on YOLO v7. In the presented detection model, an enhanced image branch was constructed to expand the feature extraction branch of YOLOv7, which could mitigate the feature degradation issues existing in the original underwater images. The contextual transfer block was introduced to the enhanced image branch, following the underwater image enhancement module, which could extract the domain features of the enhanced image, and the features of the original images and the enhanced images were fused before being fed into the detector. Focal EIOU was adopted as a new model bounding box regression loss, aiming to alleviate the performance degradation caused by mutual occlusion and overlapping of underwater objects. Taking URPC2020 and UTDAC2020 (Underwater Target Detection Algorithm Competition 2020) datasets as experimental datasets, the performance of our proposed model was compared against with other models, including YOLOF, YOLOv6 v3.0, DETR, Swin Transformer, and InternImage. The results show that our proposed model presents a competitive performance, achieving 80.71% and 86.32% in mAP@0.5 on URPC2020 and UTDAC2020, respectively. Comprehensively, the proposed model is capable of effectively mitigating the problems encountered in the task of object detection in underwater images with degraded features and exhibits great advancement.

Photon-counting light detection and ranging is very sensitive to ambient interference, target features, and instrument performance, especially for long-distance detection of spaceborne laser altimeter and measurement of complex land-cover types with steep terrain. It is crucial to extract the signal photons on the ground surface from the collected photon point cloud (PPC). An adaptive signal photon detection method is presented in this article, which combines histogram statistics and boxplot analysis with density-based spatial clustering of applications with noise (DBSCAN), to denoise the PPC data with strong and weak noise obtained by ice, cloud, and land elevation satellite-2 laser altimeter. First, a coarse denoising with histogram of elevation is conducted on the raw PPC to reduce the calculation amount. Second, a fine denoising based on adaptive DBSCAN is used to extract the signal photons, where the key parameters of elliptic filter kernel are automatically determined according to the topographic data situation. We compared it with other methods, including local distance statistics (LDS), traditional and modified DBSCAN, traditional and modified ordering points to identify cluster structure (OPTICS), and ATL08 data. Some quantitative indicators, such as recall (R), precision (P), and F-score (F), are used to evaluate its performance. The results show that; 1) the adaptive DBSCAN has the best performance on preserving the vertical structural characteristics of ground objects, and 2) the adaptive DBSCAN in the mean R, P, and F of three land covers (i.e., mountain forest, urban, and water areas) can get up to the maximum are 0.9852, 0.9675, and 0.9761, respectively; followed by ATL08 data with 0.9773, 0.9412, and 0.9536, modified OPTICS with 0.9684, 0.9460, and 0.9586, and modified DBSCAN with 0.9613, 0.9474, and 0.9544; and then OPTICS with 0.9444, 0.9397, and 0.9378, and the DBSCAN with 0.9444, 0.9355, and 0.9554; the last one is LDS with 0.9382, 0.9261, and 0.9422. The proposed method provides an alternative approach for rapid and accurate processing of PPC on complex terrain.