Local Information Research Articles

Remote Sensing Image Segmentation Based on Probabilistic Fuzzy Local Information Clustering

Abstract. In this paper, a remote sensing image segmentation based on probabilistic fuzzy local information clustering algorithm is proposed. First, assuming that the spectral measure within the same ground object follows the same probability distribution. The dissimilarity between pixel and object is modeled by the negative logarithm of the Gaussian probability density function. It can improve the noise sensitive problem caused by the Euclidean distance which can only describe the data with isotropic distribution. Then, in order to consider the effect of local spatial constraint, on the one hand, the probability measure is used to modify the local fuzzy factor to establish the dissimilarity measure with spatial constraints. On the other hand, the hidden Markov random field is used to model the prior probability model of pixel membership. Next, the entropy regularization term of the objective function is built by combining the Kullback-Leibler(KL) maximum entropy model to further improve the robustness and noise resistance. The qualitative and quantitative analysis of simulated image and different types of real remote sensing images show that the proposed algorithm can effectively overcome the above problems and further improve the accuracy of image segmentation to over 95%.

Exploring charge sharing compensation using inter-pixel coincidence counters for photon counting detectors by deep-learning from local information

Photon counting detectors (PCDs) have well-acknowledged advantages in computed tomography (CT) imaging. However, charge sharing and other problems prevent PCDs from fully realizing the anticipated potential in diagnostic CT. PCDs with multi-energy inter-pixel coincidence counters (MEICC) have been proposed to provide particular information about charge sharing, thereby achieving lower Cramér-Rao Lower Bound (CRLB) than conventional PCDs when assessing its performance by estimating material thickness or virtual monochromatic attenuation integrals (VMAIs). This work explores charge sharing compensation using local spatial coincidence counter information for MEICC detectors through a deep-learning method.
Approach: By analyzing the impact of charge sharing on photon count detection, we designed our network with a focus on individual pixels. Employing MEICC data of patches centered on POIs as input, we utilized local information for effective charge sharing compensation. The output was VMAI at different energies to address real detector issues without knowledge of primary counts. To achieve data diversity, a fast and online data generation method was proposed to provide adequate training data. A new loss function was introduced to reduce bias for training with high-noise data. The proposed method was validated by Monte Carlo (MC) simulation data for MEICC detectors that were compared with conventional PCDs. 
Main-Results: For conventional data as a reference, networks trained on low-noise data yielded results with a minimal bias (about 0.7%) compared with > 3% for the polynomial fitting method. The results of networks trained on high-noise data exhibited a slightly increased bias (about 1.3%) but a significantly reduced standard deviation (STD) and normalized root mean square error (NRMSE). The simulation study of the MEICC detector demonstrated superior compared to the conventional detector across all the metrics. Specifically, for both networks trained on high-noise and low-noise data, their biases were reduced to about 1% and 0.6%, respectively. Meanwhile, the results from a MEICC detector were of about 10% lower noise than a conventional detector. Moreover, an ablation study showed that the additional loss function on bias was beneficial for training on high-noise data.
Significance: We demonstrated that a network-based method could utilize local information in PCDs effectively by patch-based learning to reduce the impact of charge sharing. MEICC detectors provide very valuable local spatial information by additional coincidence counters. Compared with MEICC detectors, conventional PCDs only have limited local spatial information for charge sharing compensation, resulting in higher bias and standard deviation in VMAI estimation with the same patch strategy.&#xD.

Effects of DM and KSEA interactions on entanglement, Fisher and Wigner-Yanase information correlations of two XYZ-Heisenberg-qubit states under a magnetic field

We employ entanglement negativity, local quantum uncertainty (LQU), and local quantum Fisher information (LQFI) to characterize thermal entanglement between two XYZ-Heisenberg-qubit states under the influence of Dzyaloshinsky-Moriya(DM) and Kaplan-Shekhtman-Entin-Wohlman-Aharony (KSEA) interactions, as well as a magnetic field and thermal equilibrium temperature. A comparative examination reveals similar behaviors among these correlation measures. For the antiferromagnetic scenario, we observe that increasing the DM interaction parameter D z enhances thermal entanglement. Conversely, in the ferromagnetic case, the behavior of thermal entanglement differs with varying D z . Additionally, employing Kraus operators, we explore the performance of these quantifiers under decoherence. Notably, LQFI exhibits greater robustness than negativity and LQU, even displaying a frozen phenomenon at some time under dephasing effects.

3D reconstruction and depth estimation method for local anomalies of rail surface based on multi-view stereo matching

Abstract Detecting rail surface anomalies has become crucial for ensuring the safety of train operations. However, manual detection methods are time-consuming and labor-intensive. Although traditional detection models based on one-dimensional signals or two-dimensional images can effectively identify the existence of defects, they are difficult to use to obtain local depth characteristic information, leading to difficulties in accurately assessing the extent of damage in abnormal regions. Rail track maintenance strategies are typically developed based on the detected different depth ranges of defects. To address this issue, this paper proposes a local depth estimation method based on the point cloud of the target rail surface reconstructed by PatchmatchNet. Firstly, according to the acquisition method of multi-view images and the sampling environment at the site, a practical data collection protocol is established for generating a multi-view dataset of rail surface. Next, dense point cloud of the target rail surface were reconstructed by PatchmatchNet. Subsequently, a method for estimating the local anomaly depth is developed based on the point cloud. Experimental results demonstrate that the proposed method achieves a minimum error of approximately 5.5% within a maximum depth range of 0.35mm, when compared to depth measurements obtained using a structured light camera. Finally, this paper presents a more comprehensive three-dimensional representation of the local abnormal physical structure, surpassing traditional one-dimensional and two-dimensional forms. This enhanced representation offers richer information for the effective determination of whether the anomalies constitute defects and aids in distinguishing true defects from other surface irregularities. Such advancement significantly improves the precision of defect assessment and supports the development of highly precise repair strategies.

The Analysis of Smarter Future

With the continuous development of technology, smart home control systems, as one of the applications of artificial intelligence in daily life, are receiving increasing attention. However, smart home control systems face challenges in practical applications, such as complex scenarios and multimodal information. In this context, this paper introduces Visual Question Answering (VQA) technology to enhance the intelligence and user experience of smart home control systems. Despite the potential advantages of VQA technology in smart home control systems, current models still have certain shortcomings in handling local image information and integrating visual-language multimodal features. To address this, this paper proposes an innovative Transformer-based Multimodal Fusion Network (TMFNet) model. TMFNet aims to overcome the limitations of existing models in dealing with complex smart home scenarios by introducing a global-local feature attention mechanism, deep encoding-decoding modules, and multimodal representation modules.

Deep and shallow feature fusion framework for remote sensing open pit coal mine scene recognition

Understanding land use and damage in open-pit coal mining areas is crucial for effective scientific oversight and management. Current recognition methods exhibit limitations: traditional approaches depend on manually designed features, which offer limited expressiveness, whereas deep learning techniques are heavily reliant on sample data. In order to overcome the aforementioned limitations, a three-branch feature extraction framework was proposed in the present study. The proposed framework effectively fuses deep features (DF) and shallow features (SF), and can accomplish scene recognition tasks with high accuracy and fewer samples. Deep features are enhanced through a neighbouring feature attention module and a Graph Convolutional Network (GCN) module, which capture both neighbouring features and the correlation between local scene information. Shallow features are extracted using the Gray-Level Co-occurrence Matrix (GLCM) and Gabor filters, which respectively capture local and overall texture variations. Evaluation results on the AID and RSSCN7 datasets demonstrate that the proposed deep feature extraction model achieved classification accuracies of 97.53% and 96.73%, respectively, indicating superior performance in deep feature extraction tasks. Finally, the two kinds of features were fused and input into the particle swarm algorithm optimised support vector machine (PSO-SVM) to classify the scenes of remote sensing images, and the classification accuracy reached 92.78%, outperforming four other classification methods.

LRSDet: lightweight remote sensing target detection network with local-global information awareness and rapid sample assignment

Abstract With the rapid development of aerospace and unmanned aerial vehicles, using neural networks for object detection in optical remote sensing images (O-RSI) has encountered heightened challenges. The optical remote sensing images have the characteristics of complex geometric scenes, dense groups of objects, and significant multi-scale variations of objects; researchers need to use more complex models to achieve higher accuracy. However, this complexity also brings challenges to the application of lightweight scenes. Therefore, to cope with the trade-off challenge between model complexity and detection accuracy, we propose a lightweight network model LRSDet in this study. The model integrates local and global information processing mechanisms and introduces a fast positive sample assignment strategy to adapt to resource-constrained embedded and mobile platforms. By constructing a lightweight feature extraction network and a lightweight path aggregation network and incorporating the ESM-Attention module, the feature extraction capability of the model in complex remote sensing scenarios is significantly improved. In addition, the application of a dynamic soft threshold strategy further optimizes the positive sample selection process and improves the detection efficiency of the model. Experimental on the O-RSI datasets DIOR, NWPU VHR-10, and RSOD, while analyzing model real-time performance on aerial video and embedded devices, outperforming other state-of-the-art methods.

DGSIST: Clustering spatial transcriptome data based on deep graph structure Infomax

Although spatial transcriptomics data provide valuable insights into gene expression profiles and the spatial structure of tissues, most studies rely solely on gene expression information, underutilizing the spatial data. To fully leverage the potential of spatial transcriptomics and graph neural networks, the DGSI (Deep Graph Structure Infomax) model is proposed. This innovative graph data processing model uses graph convolutional neural networks and employs an unsupervised learning approach. It maximizes the mutual information between graph-level and node-level representations, emphasizing flexible sampling and aggregation of nodes and their neighbors. This effectively captures and incorporates local information from nodes into the overall graph structure. Additionally, this paper developed the DGSIST framework, an unsupervised cell clustering method that integrates the DGSI model, SVD dimensionality reduction algorithm, and k-means++ clustering algorithm. This aims to identify cell types accurately. DGSIST fully uses spatial transcriptomics data and outperforms existing methods in accuracy. Demonstrations of DGSIST’s capability across various tissue types and technological platforms have shown its effectiveness in accurately identifying spatial domains in multiple tissue sections. Compared to other spatial clustering methods, DGSIST excels in cell clustering and effectively eliminates batch effects without needing batch correction. DGSIST excels in spatial clustering analysis, spatial variation identification, and differential gene expression detection and directly applies to graph analysis tasks, such as node classification, link prediction, or graph clustering. Anticipation lies in the contribution of the DGSIST framework to a deeper understanding of the spatial organizational structures of diseases such as cancer.

Swincloud: a hybrid network for cloud detection in thermal infrared remote sensing images

ABSTRACT Cloud cover is a significant factor affecting the effectiveness of satellite-based Earth observations. Existing cloud detection algorithms primarily rely on imaging data from satellite sensors in the visible to near-infrared spectral range, making it challenging to achieve day-and-night cloud monitoring. Convolutional neural networks have shown outstanding performance in previous cloud detection algorithms due to their robust ability to extract local information. However, their inherent inductive bias limits their capacity to learn long-range semantic information. To address these challenges, we proposed SwinCloud, a U-shaped semantic segmentation network based on an enhanced Swin Transformer for cloud detection in the thermal infrared spectral range. Specifically, we augment the Swin Transformer's window attention module with a CNN-based parallel pathway to effectively model global-local information. We employ a feature fusion module before the final upsampling module in the decoder to better integrate low-level spatial information and high-level semantic information. On the Landsat-8 cloud detection dataset, our model outperforms state-of-the-art methods. When transferred to the SDGSAT-TIS cloud detection dataset, the mIOU of experiment results reaches 69.9%, demonstrating the strong transferability of SwinCloud across different sensors. We also applied SwinCloud to cloud detection in the visible bands of Landsat-8. The results demonstrated SwinCloud's generalization capability across different bands.

Socio-psychological Paradigms and Economic Metrics of the Beneficiary Farmers of Centrally Sponsored Agricultural Schemes: A Comprehensive Evaluation of PKVY, PMKSY and SHC in Maharashtra

The present study focused on assessing the socio-psychological constructs and economic variables of beneficiaries of centrally sponsored agricultural schemes namely Paramparagat Krishi Vikas Yojana (PKVY), Pradhan Mantri Krishi Sinchayee Yojana (PMKSY), and the Soil Health Card Scheme (SHC). An ex post facto research design was employed in the present study. Amravati and Buldhana districts in Vidarbha region of Maharashtra was selected for the study. For the proposed study 60 beneficiary farmers were selected from Amravati districts and 60 beneficiary farmers were selected from Buldhana districts for each scheme. Thus, for the three schemes, a total of 360 beneficiary farmers were selected from seven selected talukas of two districts of Vidarbha for three schemes. Majority of the middle aged respondents (61.11%) having secondary school level of education (39.44%) received low level of training (59.00%), but PKVY beneficiaries received high level of training (73.33%). Majority of the overall respondents had small land holdings (40.28%) with 1.01 to 1.50 ha. of irrigation potential (41.39%) having biseasonal cropping system (96.94%). Beneficiary farmers had sound financial background with 35.83 per cent of PKVY respondents with annual income in the range of Rs. 2,07,901 to 3,35,301/-, 56.67 per cent of PMKSY respondents in an annual income range of Rs. 2,86,962 to Rs. 4,77,753/-, and 40.83 per cent of SHC respondents in the range of Rs. 2,10,101 to 3,29,701/- annual income respectively. In overall beneficiaries of centrally sponsored agricultural schemes, 63.89 per cent of the respondents had medium level of social participation, source of information (65.00%), innovativeness (58.33%), economic motivation (47.50 %) and benefits accrued (43.06%). The study revealed lower participation of older farmers, indicating a need for targeted outreach and simplified training. Educated farmers benefited more, suggesting their role in promoting new technologies. Local information sources, like friends and relatives, were crucial, emphasizing the need for Gram Sabhas and exhibitions to improve awareness and participation.

Intelligent recognition and automatic localization of pipeline welds based on multi-vision system

Abstract Currently, the leakage detection of spacecraft pipeline welds relies on manual point-by-point inspection using a detection gun, which is inefficient and inadequate for the automation needs of spacecraft production. However, the accurate recognition and precise localization of widely distributed and small pipeline welds are crucial for automated detection. Therefore, this paper proposes a multi-vision detection and localization system that integrates global and local information, considering both comprehensive global 3D search and high-precision local 3D measurement. The improved YOLOv8 model is employed for pipeline weld recognition, which improves the recognition rate of welds. Based on the deep learning recognized and segmented welds, this paper proposes stereo matching and segmentation extraction methods for 3D localization and pipeline orientation determination. Additionally, the system integrates a robot to perform automated point-by-point inspection of welds within the area without collisions. The experimental results demonstrate the effectiveness of the improved YOLOv8 and the proposed methods for 3D weld localization and pipeline orientation determination. The maximum deviation of the spatial distance of fine weld positioning is 0.20 mm, and the repeatability of the 3D coordinates is around 0.1 mm. The system can perform precise localization and detection, meeting the requirements for automatic weld recognition and localization.

A Person Re-Identification Method for Fusing Convolutional Attention and Transformer Architecture

Rapid and accurate localization of target person via person re-identification is one of the important methods in intelligent security systems,but faces great challenges due to complex environmental changes. In order to build a model applicable to various complex scenes, deep learning-based person re-identification models have become a key research direction for researchers. The existing convolutional neural network-based or transformer-based deep learning models are still have certain shortcomings in the extraction of local details and are not able to cope well with realistic complex scenes. To address this problem, a method fusing convolutional neural network and transformer (FCAT) is proposed to enhance the transformer's attention to local detail information. This method mainly improves the transformer's ability to extract local detail features indirectly by embedding convolutional space attention and channel attention respectively to enhance the attention to important regions and important channel features in the image. Comparative ablation experiments on three publicly available person re-identification datasets demonstrate that FCAT achieves comparable results to existing methods on non-occluded datasets, and significantly improves performance on occluded datasets. The proposed model is also has a lightweight effect, and the inference speed is improved without increasing the amount of outer computation and model parameters.

Automatic High-Resolution Operational Modal Identification of Thin-Walled Structures Supported by High-Frequency Optical Dynamic Measurements.

High-frequency optical dynamic measurement can realize multiple measurement points covering the whole surface of the thin-walled structure, which is very useful for obtaining high-resolution spatial information for damage localization. However, the noise and low calculation efficiency seriously hinder its application to real-time, online structural health monitoring. To this end, this paper proposes a novel high-resolution frequency domain decomposition (HRFDD) modal identification method, combining an optical system with an accelerometer for measuring high-accuracy vibration response and introducing a clustering algorithm for automated identification to improve efficiency. The experiments on the cantilever aluminum plate were carried out to evaluate the effectiveness of the proposed approach. Natural frequency and damping ratios were obtained by the least-squares complex frequency domain (LSCF) method to process the acceleration responses; the high-resolution mode shapes were acquired by the singular value decomposition (SVD) processing of global displacement data collected by high-speed cameras. Finally, the complete set of the first nine order modal parameters for the plate within the frequency range of 0 to 500 Hz has been determined, which is closely consistent with the results obtained from both experimental modal analysis and finite element analysis; the modal parameters could be automatically picked up by the DBSCAN algorithm. It provides an effective method for applying optical dynamic technology to real-time, online structural health monitoring, especially for obtaining high-resolution mode shapes.

Remaining useful life prediction of lithium-ion batteries based on DBO[sbnd]CNN-DSformer

In order to improve the accuracy of predicting RUL of lithium-ion batteries, a lithium-ion battery RUL prediction method based on the DBOCNN-DSformer model is proposed. Firstly, the health characteristics of the battery are extracted and the local information of health features is mined using CNN. DSformer is utilized for global information, local information, and variable correlation learning of battery aging characteristics. The DBO is used to optimize the super-parameters of the CNN-DSformer model and build the DBOCNN-DSformer model. Finally, the battery aging data set was used for verification. The results show that DBOCNN-DSformer, which sets different prediction starting points, can extract sequence information from input data and establish long-term dependencies between sequences. The maximum average MRE error in the NASA data set was 0.05, the maximum average MAE was 0.018, and the maximum average AE error was within 5. The maximum average MRE error of the CALCE data set was 0.37, the maximum average MAE was 0.014, and the maximum average AE prediction error was within 10. Compared with LSTM, RNN, and Transformer models, it was found that DBOCNN-DSformer showed high prediction accuracy and good robustness.

Dictionary trained attention constrained low rank and sparse autoencoder for hyperspectral anomaly detection

Dictionary representations and deep learning Autoencoder (AE) models have proven effective in hyperspectral anomaly detection. Dictionary representations offer self-explanation but struggle with complex scenarios. Conversely, autoencoders can capture details in complex scenes but lack self-explanation. Complex scenarios often involve extensive spatial information, making its utilization crucial in hyperspectral anomaly detection. To effectively combine the advantages of both methods and address the insufficient use of spatial information, we propose an attention constrained low-rank and sparse autoencoder for hyperspectral anomaly detection. This model includes two encoders: an attention constrained low-rank autoencoder (AClrAE) trained with a background dictionary and incorporating a Global Self-Attention Module (GAM) to focus on global spatial information, resulting in improved background reconstruction; and an attention constrained sparse autoencoder (ACsAE) trained with an anomaly dictionary and incorporating a Local Self-Attention Module (LAM) to focus on local spatial information, resulting in enhanced anomaly reconstruction. Finally, to merge the detection results from both encoders, a nonlinear fusion scheme is employed. Experiments on multiple real and synthetic datasets demonstrate the effectiveness and feasibility of the proposed method.

Unsupervised Multi-Scale Hybrid Feature Extraction Network for Semantic Segmentation of High-Resolution Remote Sensing Images

Generating pixel-level annotations for semantic segmentation tasks of high-resolution remote sensing images is both time-consuming and labor-intensive, which has led to increased interest in unsupervised methods. Therefore, in this paper, we propose an unsupervised multi-scale hybrid feature extraction network based on the CNN-Transformer architecture, referred to as MSHFE-Net. The MSHFE-Net consists of three main modules: a Multi-Scale Pixel-Guided CNN Encoder, a Multi-Scale Aggregation Transformer Encoder, and a Parallel Attention Fusion Module. The Multi-Scale Pixel-Guided CNN Encoder is designed for multi-scale, fine-grained feature extraction in unsupervised tasks, efficiently recovering local spatial information in images. Meanwhile, the Multi-Scale Aggregation Transformer Encoder introduces a multi-scale aggregation module, which further enhances the unsupervised acquisition of multi-scale contextual information, obtaining global features with stronger feature representation. The Parallel Attention Fusion Module employs an attention mechanism to fuse global and local features in both channel and spatial dimensions in parallel, enriching the semantic relations extracted during unsupervised training and improving the performance of unsupervised semantic segmentation. K-means clustering is then performed on the fused features to achieve high-precision unsupervised semantic segmentation. Experiments with MSHFE-Net on the Potsdam and Vaihingen datasets demonstrate its effectiveness in significantly improving the accuracy of unsupervised semantic segmentation.

UTran-DSR: a novel transformer-based model using feature enhancement for dysarthric speech recognition

Over the past decade, the prevalence of neurological diseases has significantly risen due to population growth and aging. Individuals suffering from spastic paralysis, brain attack, and idiopathic Parkinson’s disease (PD), among other neurological illnesses, commonly suffer from dysarthria. Early detection and treatment of dysarthria in these patients are essential for effectively managing the progression of their disease. This paper provides UTrans-DSR, a novel encoder-decoder architecture for analyzing Mel-spectrograms (generated from audios) and classifying speech as healthy or dysarthric. Our model employs transformer encoder features based on a hybrid design, which includes the feature enhancement block (FEB) and the vision transformer (ViT) encoders. This combination effectively extracts global and local pixel information regarding localization while optimizing the mel-spectrograms feature extraction process. We keep up with the original class-token grouping sequence in the vision transformer while generating a new equivalent expanding route. More specifically, two unique growing pathways use a deep-supervision approach to increase spatial data recovery and expedite model convergence. We add consecutive residual connections to the system to reduce feature loss while increasing spatial data retrieval. Our technique is based on identifying gaps in mel-spectrograms distinguishing between normal and dysarthric speech. We conducted several experiments on UTrans-DSR using the UA speech and TORGO datasets, and it outperformed the existing top models. The model performed significantly in pixel’s localized and spatial feature extraction, effectively detecting and classifying spectral gaps. The Tran-DSR model outperforms previous research models, achieving an accuracy of 97.75%.

BIF-Net: Boundary information fusion network for abdominal aortic aneurysm segmentation

The accurate abdominal aortic aneurysm (AAA) segmentation is significant for assisting clinicians in diagnosis and treatment planning. However, existing segmentation methods exhibit a low utilization rate for the semantic information of vessel boundaries, which is disadvantageous for segmenting AAA with significant scale variability of vessel diameter (diameter ranges from 4 mm to 85 mm). To tackle this problem, we introduce a boundary information fusion network (BIF-Net) specially designed for AAA segmentation. BIF-Net initially constructs convolutional kernel functions based on Gabor and Sobel operators, enriching the global semantic features and localization information through the Gabor and Sobel dilated convolution (GSDC) module. Additionally, BIF-Net supplements lost boundary feature information during the sampling process through the guided filtering feature supplementation (GFFS) module and the channel-spatial attention module (CSAM), enhancing the ability to capture targets with shape diversity and boundary features. Finally, we introduce a boundary feature loss function to alleviate the impact of the imbalance between positive and negative samples. The results demonstrate that BIF-Net outperforms current state-of-the-art methods across multiple evaluation metrics, achieving the highest Dice similarity coefficient (DSC) accuracies of 93.29 % and 91.01 % on the preoperative and postoperative datasets, respectively. Compared to the state-of-the-art methods, BIF-Net improves DSC by 6.86 % and 3.85 %. Due to the powerful boundary feature extraction ability, the proposed BIF-Net is a competitive AAA segmentation method exhibiting significant potential for application in diagnosis and treatment processes of AAA.

A Spatial-Frequency Approach to Point-Wise Frequency Response Function Estimation with Digital Image Correlation

The use of digital image correlation for modal analysis is becoming an appealing option thanks to its non-contact and full-field measurement process. However, frequency response function (FRF) estimation can be challenging due to the limited number of time domain data and heavy measurement noise. Thereby, the present work aims to propose a method which improves the estimation accuracy of point-wise FRFs. Firstly, a Gaussian-process-based spatial-frequency model is proposed, which makes use of the intrinsic properties of the FRF and the local spatial information of field measurements. Then, a Bayesian solution is developed, which is enforced by a stable and efficient numerical procedure. Finally, the effectiveness of the proposed method is verified by making a comparison with the spectral estimator through the use of simulated data, and it is further validated based on an experimental application.

MSDA-HLGCformer-based context-aware fusion network for underwater organism detection

Underwater organism detection is crucial for marine ecology research and resource management. However, underwater images often suffer from issues like blurring, noise, and color distortion, making it challenging to distinguish targets from complex backgrounds. Existing detection methods struggle to separate targets in such conditions. To address these problems, we propose a Cross-Context Fusion Transformer YOLO network (CCFT-YOLO) for underwater organism detection. Specifically, we propose an MSDA-HLGCformer backbone network that captures and integrates local features at different depths and distances through the Multi-Scale Dilated Attention (MSDA) block at the low level, while at the high level, a hierarchical local–global context former (HLGCformer) is developed to contextualize the information at each scale, allowing the model to focus on the global context of the underwater environment. A context-aware cross-level fusion module (CACLFM) is designed to balance the retention of salient target and background texture information by integrating local and global information. Quantitative and qualitative experimental results show that CCFT-YOLO is competitive and robust in underwater organism detection compared to other state-of-the-art detectors.