For aquaculture resource evaluation and ecological environment monitoring, the automatic detection and identification of marine organisms is critical; however, due to the low quality of underwater images and the characteristics of underwater biological detection, the lack of abundant features can impede traditional hand-designed feature extraction approaches or CNN-based object detection algorithms, particularly in complex underwater environments. Therefore, the goal of this study was to perform object detection in underwater environments. This study developed a novel method for capturing feature information by adding the convolutional block attention module (CBAM) to the YOLOv5 backbone network. The interference of underwater organism characteristics in object characteristics decreased and the output object information of the backbone network was enhanced. In addition, a self-adaptive global histogram stretching algorithm (SAGHS) was designed to eliminate degradation problems, such as low contrast and color loss, that are caused by underwater environmental features in order to restore image quality. Extensive experiments and comprehensive evaluations using the URPC2021 benchmark dataset demonstrated the effectiveness and adaptivity of the proposed methods. Additionally, this study conducted an exhaustive analysis of the impacts of training data on performance.

The traditional simultaneous localization and mapping (SLAM) systems rely on the assumption of a static environment and fail to accurately estimate the system’s location when dynamic objects are present in the background. While learning-based dynamic SLAM systems have difficulties in handling unknown moving objects, geometry-based methods have limited success in addressing the residual effects of unidentified dynamic objects on location estimation. To address these issues, we propose an anti-dynamics two-stage RGB-D SLAM approach. In the first stage, we identify potential motion regions for both known and unknown dynamic objects and rapidly generate pose estimates through optical flow tracking and model generation techniques. In the second stage, dynamic features within each frame are eliminated through dynamic assessment. For unidentified dynamic objects, we propose an approach involving superpixel extraction and geometric clustering to delineate potential motion regions based on color and geometric cues within the image. We conducted extensive experiments using public datasets and real-world scenarios, which demonstrated that our method surpasses current state-of-the-art (SOTA) dynamic SLAM techniques on public datasets. Our method’s robustness was also confirmed through experiments in real scenes featuring objects moving at varying speeds.

This letter introduces a novel framework for dense Visual Simultaneous Localization and Mapping (VSLAM) based on Gaussian Splatting. Recently, SLAM based on Gaussian Splatting has shown promising results. However, in monocular scenarios, the Gaussian maps reconstructed lack geometric accuracy and exhibit weaker tracking capability. To address these limitations, we jointly optimize sparse visual odometry tracking and 3D Gaussian Splatting scene representation for the first time. We obtain depth maps on visual odometry keyframe windows using a fast Multi-View Stereo (MVS) network for the geometric supervision of Gaussian maps. Furthermore, we propose a depth smooth loss and Sparse-Dense Adjustment Ring (SDAR) to reduce the negative effect of estimated depth maps and preserve the consistency in scale between the visual odometry and Gaussian maps. We have evaluated our system across various synthetic and real-world datasets. The accuracy of our pose estimation surpasses existing methods and achieves state-of-the-art. Additionally, it outperforms previous monocular methods in terms of novel view synthesis and geometric reconstruction fidelities.

Regular monitoring of marine life is essential for preserving the stability of marine ecosystems. However, underwater target detection presents several challenges, particularly in balancing accuracy with model efficiency and real-time performance. To address these issues, we propose an innovative approach that combines the Structured Space Model (SSM) with feature enhancement, specifically designed for small target detection in underwater environments. We developed a high-accuracy, lightweight detection model—UWNet. The results demonstrate that UWNet excels in detection accuracy, particularly in identifying difficult-to-detect organisms like starfish and scallops. Compared to other models, UWNet reduces the number of model parameters by 5% to 390%, substantially improving computational efficiency while maintaining top detection accuracy. Its lightweight design enhances the model’s applicability for deployment on underwater robots.

In the domain of object detection, small object detection remains a pressing challenge, as existing approaches often suffer from limited accuracy, high model complexity, and difficulty meeting lightweight deployment requirements. In this paper, we propose PCPE-YOLO, a novel object detection algorithm, specifically designed to address these difficulties. First, we put forward a dynamically reconfigurable C2f_PIG module. This module uses a parameter-aware mechanism to adapt its bottleneck structures to different network depths and widths, reducing parameters while maintaining performance. Next, we introduce a Context Anchor Attention mechanism that boosts the model's focus on the contexts of small objects, thereby improving detection accuracy. In addition, we add a small object detection layer to enhance the model's localization capability for small objects. Finally, we integrate an Efficient Up-Convolution Block to sharpen decoder feature maps, enhancing small object recall with minimal computational overhead. Experiments on VisDrone2019, KITTI, and NWPU VHR-10 datasets show that PCPE-YOLO significantly outperforms both the baseline and other state-of-the-art methods in precision, recall, mean average precision, and parameters, achieving the best precision among all compared approaches. On VisDrone2019 in particular, it achieves improvements of 3.8% in precision, 5.6% in recall, 6.2% in mAP50, and 5% in F1 score, effectively combining lightweight design with high small object detection performance and providing a more efficient and reliable solution for small object detection in real-world applications.

Accurate optic disc (OD) detection is an essential yet vital step for retinal disease diagnosis. In the paper, an approach for segmenting OD boundary without manpower named full-automatic double boundary extraction is designed. There are two main advantages in it. (1) Since the performances and the computational cost produced by iterations of contour evolution of active contour models- (ACM-) based approaches greatly depend on the initialization, this paper proposes an effective and adaptive initial level set contour extraction approach using saliency detection and threshold techniques. (2) In order to handle unreliable information generated by intensity in abnormal retinal images caused by diseases, a modified LIF approach is presented by incorporating the shape prior information into LIF. We test the effectiveness of the proposed approach on a publicly available DIARETDB0 database. Experimental results demonstrate that our approach outperforms well-known approaches in terms of the average overlapping ratio and accuracy rate.