Search Results (20)

The Transformer architecture has gained widespread acceptance in image segmentation. However, it sacrifices local feature details and necessitates extensive data for training, posing challenges to its integration into computer-aided medical image segmentation. To address the above challenges, we introduce CCFNet, a collaborative cross-fusion network, which continuously fuses a CNN and Transformer interactively to exploit context dependencies. In particular, when integrating CNN features into Transformer, the correlations between local and global tokens are adaptively fused through collaborative self-attention fusion to minimize the semantic disparity between these two types of features. When integrating Transformer features into the CNN, it uses the spatial feature injector to reduce the spatial information gap between features due to the asymmetry of the extracted features. In addition, CCFNet implements the parallel operation of Transformer and the CNN and independently encodes hierarchical global and local representations when effectively aggregating different features, which can preserve global representations and local features. The experimental findings from two public medical image segmentation datasets reveal that our approach exhibits competitive performance in comparison to current state-of-the-art methods. Full article

The present analysis related to social sustainability aims at evaluating and understanding how a “circular” or “round” organization such as the so-called Organiblò (i.e., a fusion of the terms “organigram” and the Italian word for “porthole”) functions. More precisely, the present article wants to raise awareness among companies that a profound cultural change seems necessary to push the search for sustainable objectives further. In this specific regard, independent interviews with the CEOs of 11 medium-sized enterprises and 46 young middle managers were conducted. Based on their responses, our analysis highlights the advantages of a “circular” organization, which range from better corporate sustainability to greater freedom of staff and cross-functional activities as well as the valorization of individuals and enhanced flexibility and collaborative spirit. However, time is needed to effect such a profound cultural change. The main difficulties consist in the approach to decision-making processes, because top management is often not yet prone to strongly encourage transparency, a culture of feedback and inclusiveness in the workforce. Consequently, a new, additional manager (i.e., a “wheeler manager”) might disseminate a new managing culture and involve employees in contributing to the company’s sustainability. Full article

Since camera and LiDAR sensors provide complementary information for the 3D semantic segmentation of intelligent vehicles, extensive efforts have been invested to fuse information from multi-modal data. Despite considerable advantages, fusion-based methods still have inevitable limitations: field-of-view disparity between two modal inputs, demanding precise paired data as inputs in both the training and inferring stages, and consuming more resources. These limitations pose significant obstacles to the practical application of fusion-based methods in real-world scenarios. Therefore, we propose a robust 3D semantic segmentation method based on multi-modal collaborative learning, aiming to enhance feature extraction and segmentation performance for point clouds. In practice, an attention based cross-modal knowledge distillation module is proposed to effectively acquire comprehensive information from multi-modal data and guide the pure point cloud network; then, a confidence-map-driven late fusion strategy is proposed to dynamically fuse the results of two modalities at the pixel-level to complement their advantages and further optimize segmentation results. The proposed method is evaluated on two public datasets (urban dataset SemanticKITTI and off-road dataset RELLIS-3D) and our unstructured test set. The experimental results demonstrate the competitiveness of state-of-the-art methods in diverse scenarios and a robustness to sensor faults. Full article

Obstacle intrusion is a serious threat to the safety of railway traffic. LiDAR point cloud 3D semantic segmentation (3DSS) provides a new method for unmanned rail-obstacle detection. However, the inevitable degradation of model performance occurs in complex weather and hinders its practical application. In this paper, a multi-modal contrastive learning (CL) strategy, named DHT-CL, is proposed to improve point cloud 3DSS in complex weather for rail-obstacle detection. DHT-CL is a camera and LiDAR sensor fusion strategy specifically designed for complex weather and obstacle detection tasks, without the need for image input during the inference stage. We first demonstrate how the sensor fusion method is more robust under rainy and snowy conditions, and then we design a Dual-Helix Transformer (DHT) to extract deeper cross-modal information through a neighborhood attention mechanism. Then, an obstacle anomaly-aware cross-modal discrimination loss is constructed for collaborative optimization that adapts to the anomaly identification task. Experimental results on a complex weather railway dataset show that with an mIoU of 87.38%, the proposed DHT-CL strategy achieves better performance compared to other high-performance models from the autonomous driving dataset, SemanticKITTI. The qualitative results show that DHT-CL achieves higher accuracy in clear weather and reduces false alarms in rainy and snowy weather. Full article

Semantic segmentation plays a pivotal role in the intelligent interpretation of remote sensing images (RSIs). However, conventional methods predominantly focus on learning representations within the spatial domain, often resulting in suboptimal discriminative capabilities. Given the intrinsic spectral characteristics of RSIs, it becomes imperative to enhance the discriminative potential of these representations by integrating spectral context alongside spatial information. In this paper, we introduce the spectrum-space collaborative network (SSCNet), which is designed to capture both spectral and spatial dependencies, thereby elevating the quality of semantic segmentation in RSIs. Our innovative approach features a joint spectral–spatial attention module (JSSA) that concurrently employs spectral attention (SpeA) and spatial attention (SpaA). Instead of feature-level aggregation, we propose the fusion of attention maps to gather spectral and spatial contexts from their respective branches. Within SpeA, we calculate the position-wise spectral similarity using the complex spectral Euclidean distance (CSED) of the real and imaginary components of projected feature maps in the frequency domain. To comprehensively calculate both spectral and spatial losses, we introduce edge loss, Dice loss, and cross-entropy loss, subsequently merging them with appropriate weighting. Extensive experiments on the ISPRS Potsdam and LoveDA datasets underscore SSCNet’s superior performance compared with several state-of-the-art methods. Furthermore, an ablation study confirms the efficacy of SpeA. Full article

Significant advances in sensor technology and virtual reality (VR) offer new possibilities for early and effective detection of mild cognitive impairment (MCI), and this wealth of data can improve the early detection and monitoring of patients. In this study, we proposed a non-invasive and effective MCI detection protocol based on electroencephalogram (EEG), speech, and digitized cognitive parameters. The EEG data, speech data, and digitized cognitive parameters of 86 participants (44 MCI patients and 42 healthy individuals) were monitored using a wearable EEG device and a VR device during the resting state and task (the VR-based language task we designed). Regarding the features selected under different modality combinations for all language tasks, we performed leave-one-out cross-validation for them using four different classifiers. We then compared the classification performance under multimodal data fusion using features from a single language task, features from all tasks, and using a weighted voting strategy, respectively. The experimental results showed that the collaborative screening of multimodal data yielded the highest classification performance compared to single-modal features. Among them, the SVM classifier using the RBF kernel obtained the best classification results with an accuracy of 87%. The overall classification performance was further improved using a weighted voting strategy with an accuracy of 89.8%, indicating that our proposed method can tap into the cognitive changes of MCI patients. The MCI detection scheme based on EEG, speech, and digital cognitive parameters proposed in this study provides a new direction and support for effective MCI detection, and suggests that VR and wearable devices will be a promising direction for easy-to-perform and effective MCI detection, offering new possibilities for the exploration of VR technology in the field of language cognition. Full article

This paper proposes an improved model based on YOLOv5s, specifically designed to overcome the challenges faced by current target detection algorithms in the field of electric bike helmet detection. In order to enhance the model’s ability to detect small targets and densely populated scenes, a specialized layer dedicated to small target detection and a novel loss function called Normalized Wasserstein Distance (NWD) are introduced. In order to solve the problem of increasing model parameters and complexity due to the inclusion of a small target detection layer, a Cross-Stage Partial Channel Mixing (CSPCM) on top of Convmix is designed. The collaborative fusion of CSPCM and the Deep Feature Consistency (DFC) attention mechanism makes it more suitable for hardware devices. In addition, the conventional Nearest Upsample technology is replaced with the advanced CARAFE Upsample module, further improving the accuracy of the model. Through rigorous experiments on carefully constructed datasets, the results show significant improvements in various evaluation indicators such as precision, recall, mAP.5, and mAP.95. Compared with the unmodified YOLOv5s algorithm, the proposed enhanced model achieves significant improvements of 1.1%, 8.4%, 5.2%, and 8.6% on these indicators, respectively, and these enhancements are accompanied by a reduction of 778,924 parameters. The experimental results on our constructed dataset demonstrate the superiority of the improved model and elucidate its potential applications. Furthermore, promising improvements for future research are suggested. This study introduces an efficient approach for improving the detection of electric bike helmets and verifies the effectiveness and practicality of the model through experiments. Importantly, the proposed scheme has implications for other target detection algorithms, especially in the field of small target detection. Full article

Wheat is one of the widely cultivated crops. Accurate and efficient high-throughput ear counting is important for wheat production, yield evaluation, and seed breeding. The traditional wheat ear counting method is inefficient due to the small scope of investigation. Especially in the wheat field scene, the images obtained from different platforms, including ground systems and unmanned aerial vehicles (UAVs), have differences in density, scale, and wheat ear distribution, which makes the wheat ear counting task still face some challenges. To this end, a density map counting network (LWDNet) model was constructed for cross-platform wheat ear statistics. Firstly, CA-MobileNetV3 was constructed by introducing a collaborative attention mechanism (CA) to optimize the lightweight neural network MobileNetV3, which was used as the front end of the feature extraction network, aiming to solve the problem of occlusion and adhesion of wheat ears in the field. Secondly, to enhance the model’s ability to learn the detailed features of wheat ears, the CARAFE upsampling module was introduced in the feature fusion layer to better restore the characteristics of wheat ears and improve the counting accuracy of the model for wheat ears. Finally, density map regression was used to achieve high-density, small-target ear counting, and the model was tested on datasets from different platforms. The results showed that our method can efficiently count wheat ears of different spatial scales, achieving good accuracy while maintaining a competitive number of parameters (2.38 million with a size of 9.24 MB), which will benefit wheat breeding and screening analysis to provide technical support. Full article

The change-detection task is essentially a binary semantic segmentation task of changing and invariant regions. However, this is much more difficult than simple binary tasks, as the changing areas typically include multiple terrains such as factories, farmland, roads, buildings, and mining areas. This requires the ability of the network to extract features. To this end, we propose a multi-branch collaborative change-detection network based on Siamese structure (MHCNet). In the model, three branches, the difference branch, global branch, and similar branch, are constructed to refine and extract semantic information from remote-sensing images. Four modules, a cross-scale feature-attention module (CSAM), global semantic filtering module (GSFM), double-branch information-fusion module (DBIFM), and similarity-enhancement module (SEM), are proposed to assist the three branches to extract semantic information better. The CSFM module is used to extract the semantic information related to the change in the remote-sensing image from the difference branch, the GSFM module is used to filter the rich semantic information in the remote-sensing image, and the DBIFM module is used to fuse the semantic information extracted from the difference branch and the global branch. Finally, the SEM module uses the similar information extracted with the similar branch to correct the details of the feature map in the feature-recovery stage. Full article

Collaborative filtering (CF) usually suffers from data sparsity and cold starts. Knowledge graphs (KGs) are widely used to improve recommendation performance. To verify that knowledge graphs can further alleviate the above problems, this paper proposes an end-to-end framework that uses attentive knowledge graph perceptual propagation for recommendations (AKGP). This framework uses a knowledge graph as a source of auxiliary information to extract user–item interaction information and build a sub-knowledge base. The fusion of structural and contextual information is used to construct fine-grained knowledge graphs via knowledge graph embedding methods and to generate initial embedding representations. Through multi-layer propagation, the structured information and historical preference information are embedded into a unified vector space, and the potential user–item vector representation is expanded. This article used a knowledge perception attention module to achieve feature representation, and finally, the model was optimized using the stratified sampling joint learning method. Compared with the baseline model using MovieLens-1M, Last-FM, Book-Crossing and other data sets, the experimental results demonstrate that the model outperforms state-of-the-art KG-based recommendation methods, and the shortcomings of the existing model are improved. The model was applied to product design data and historical maintenance records provided by an automotive parts manufacturing company. The predictions of the recommended system are matched to the product requirements and possible failure records. This helped reduce costs and increase productivity, helping the company to quickly determine the cause of failures and reduce unplanned downtime. Full article

The increasing urban traffic problems have made the transportation system require a large amount of data. Aiming at the current problems of data types redundancy and low coordination rate of intelligent transportation systems (ITS), this paper proposes an improved digital twin architecture applicable to ITS. Based on the improved digital twin architecture, a framework for dynamic and static data collaboration in ITS is constructed. For various collaboration methods, this paper specifically describes the collaboration methods and scopes, and designs the framework and interfaces for data mapping. Finally, the effectiveness of the framework is verified by case studies to mine the spatiotemporal distribution characteristics of data, capture human travel characteristics, and visualize intersections using digital twins. This paper provides a new data fusion idea for digital twin systems in ITS, and the framework covers all data types in digital twin systems for cross-integration analysis. Full article

Precise pear detection and recognition is an essential step toward modernizing orchard management. However, due to the ubiquitous occlusion in orchards and various locations of image acquisition, the pears in the acquired images may be quite small and occluded, causing high false detection and object loss rate. In this paper, a multi-scale collaborative perception network YOLOv5s-FP (Fusion and Perception) was proposed for pear detection, which coupled local and global features. Specifically, a pear dataset with a high proportion of small and occluded pears was proposed, comprising 3680 images acquired with cameras mounted on a ground tripod and a UAV platform. The cross-stage partial (CSP) module was optimized to extract global features through a transformer encoder, which was then fused with local features by an attentional feature fusion mechanism. Subsequently, a modified path aggregation network oriented to collaboration perception of multi-scale features was proposed by incorporating a transformer encoder, the optimized CSP, and new skip connections. The quantitative results of utilizing the YOLOv5s-FP for pear detection were compared with other typical object detection networks of the YOLO series, recording the highest average precision of 96.12% with less detection time and computational cost. In qualitative experiments, the proposed network achieved superior visual performance with stronger robustness to the changes in occlusion and illumination conditions, particularly providing the ability to detect pears with different sizes in highly dense, overlapping environments and non-normal illumination areas. Therefore, the proposed YOLOv5s-FP network was practicable for detecting in-field pears in a real-time and accurate way, which could be an advantageous component of the technology for monitoring pear growth status and implementing automated harvesting in unmanned orchards. Full article

Personalized recipe recommendation is attracting more and more attention, which can help people make choices from the exploding growth of online food information. Unlike other recommendation tasks, the target of recipe recommendation is a non-atomic item, so attribute information is especially important for the representation of recipes. However, traditional collaborative filtering or content-based recipe recommendation methods tend to focus more on user–recipe interaction information and ignore higher-order semantic and structural information. Recently, graph neural networks (GNNs)-based recommendation methods provided new ideas for recipe recommendation, but there was a problem of sparsity of supervised signals caused by the long-tailed distribution of heterogeneous graph entities. How to construct high-quality representations of users and recipes becomes a new challenge for personalized recipe recommendation. In this paper, we propose a new method, a multi-level knowledge-aware contrastive learning network (MKCLN) for personalized recipe recommendation. Compared with traditional comparative learning, we design a multi-level view to satisfy the requirement of fine-grained representation of users and recipes, and use multiple knowledge-aware aggregation methods for node fusion to finally make recommendations. Specifically, the local-level includes two views, interaction view and semantic view, which mine collaborative information and semantic information for high-quality representation of nodes. The global-level learns node embedding by capturing higher-order structural information and semantic information through a network structure view. Then, a kind of self-supervised cross-view contrastive learning is invoked to make the information of multiple views collaboratively supervise each other to learn fine-grained node embeddings. Finally, the recipes that satisfy personalized preferences are recommended to users by joint training and model prediction functions. In this study, we conduct experiments on two real recipe datasets, and the experimental results demonstrate the effectiveness and advancement of MKCLN. Full article

Multiclass geospatial object detection in high-spatial-resolution remote-sensing images (HSRIs) has recently attracted considerable attention in many remote-sensing applications as a fundamental task. However, the complexity and uncertainty of spatial distribution among multiclass geospatial objects are still huge challenges for object detection in HSRIs. Most current remote-sensing object-detection approaches fall back on deep convolutional neural networks (CNNs). Nevertheless, most existing methods only focus on mining visual characteristics and lose sight of spatial or semantic relation discriminations, eventually degrading object-detection performance in HSRIs. To tackle these challenges, we propose a novel hybrid attention-driven multistream hierarchical graph embedding network (HA-MHGEN) to explore complementary spatial and semantic patterns for improving remote-sensing object-detection performance. Specifically, we first constructed hierarchical spatial graphs for multiscale spatial relation representation. Then, semantic graphs were also constructed by integrating them with the word embedding of object category labels on graph nodes. Afterwards, we developed a self-attention-aware multiscale graph convolutional network (GCN) to derive stronger for intra- and interobject hierarchical spatial relations and contextual semantic relations, respectively. These two relation networks were followed by a novel cross-attention-driven spatial- and semantic-feature fusion module that utilizes a multihead attention mechanism to learn associations between diverse spatial and semantic correlations, and guide them to endowing a more powerful discrimination ability. With the collaborative learning of the three relation networks, the proposed HA-MHGEN enables grasping explicit and implicit relations from spatial and semantic patterns, and boosts multiclass object-detection performance in HRSIs. Comprehensive and extensive experimental evaluation results on three benchmarks, namely, DOTA, DIOR, and NWPU VHR-10, demonstrate the effectiveness and superiority of our proposed method compared with that of other advanced remote-sensing object-detection methods. Full article

The hyperspectral, multispectral, and synthetic aperture radar (SAR) remote sensing images provide complementary advantages in high spectral resolution, high spatial resolution, and geometric and polarimetric properties, generally. How to effectively integrate cross-modal information to obtain a high spatial resolution hyperspectral image with the characteristics of the SAR is promising. However, due to divergent imaging mechanisms of modalities, existing SAR and optical image fusion techniques generally remain limited due to the spectral or spatial distortions, especially for complex surface features such as coastal wetlands. This paper provides, for the first time, an efficient multi-resolution collaborative fusion method for multispectral, hyperspectral, and SAR images. We improve generic multi-resolution analysis with spectral-spatial weighted modulation and spectral compensation to achieve minimal spectral loss. The backscattering gradients of SAR are guided to fuse, which is calculated from saliency gradients with edge preserving. The experiments were performed on ZiYuan-1 02D (ZY-1 02D) and GaoFen-5B (AHSI) hyperspectral, Sentinel-2 and GaoFen-5B (VIMI) multispectral, and Sentinel-1 SAR images in the challenging coastal wetlands. Specifically, the fusion results were comprehensively tested and verified on the qualitative, quantitative, and classification metrics. The experimental results show the competitive performance of the proposed method. Full article