Search Results (3,576)

Unsupervised person re-identification (Re-ID) has been proven very effective and it boosts the performance in learning representations from unlabeled data in the dataset. Most current methods have good accuracy, but there are two main problems. First, clustering often generates noisy labels. Second, features can change because of different camera styles. Noisy labels causes incorrect optimization, which reduces the accuracy of the model. The latter results in inaccurate prediction for samples within the same category that have been captured by different cameras. Despite the significant variations inherent in the vast source data, the principles of invariance and symmetry remain crucial for effective feature recognition. In this paper, we propose a method called Invariance Constraint Contrast Learning (ICCL) to address these two problems. Specifically, we introduce center invariance and instance invariance to reduce the effect of noisy samples. We also use camera invariance to handle feature changes caused by different cameras. Center invariance and instance invariance help decrease the impact of noise. Camera invariance improves the classification accuracy by using a camera-aware classification strategy. We test our method on three common large-scale Re-ID datasets. It clearly improves the accuracy of unsupervised person Re-ID. Specifically, our approach demonstrates its effectiveness by improving mAP by 3.5% on Market-1501, 1.3% on MSMT17 and 3.5% on CUHK03 over state-of-the-art methods. Full article

Teleoperation in agricultural environments requires enhanced situational awareness for effective architectural scouting and decision-making for orchard management applications. The dynamic complexity of orchard structures presents challenges for remote visualization during architectural scouting operations. This study presents an adaptive streaming and rendering pipeline for real-time point cloud visualization in Virtual Reality (VR) teleoperation systems. The proposed method integrates selective streaming that localizes teleoperators within live maps, an efficient point cloud parser for Unity Engine, and an adaptive Level-of-Detail rendering system utilizing dynamically scaled and smoothed polygons. The implementation incorporates pseudo-coloring through LiDAR reflectivity fields to enhance the distinction between materials and geometry. The pipeline was evaluated using datasets containing LiDAR point cloud scans of orchard environments captured during spring and summer seasons, with testing conducted on both standalone and PC-tethered VR configurations. Performance analysis demonstrated improvements of 10.2–19.4% in runtime performance compared to existing methods, with a framerate enhancement of up to 112% achieved through selectively streamed representations. Qualitative assessment confirms the method’s capability to maintain visual continuity at close proximity while preserving the geometric features discernible for architectural scouting operations. The results establish the viability of VR-based teleoperation for precision agriculture applications, while demonstrating the critical relationship between Quality-of-Service parameters and operator Quality of Experience in remote environmental perception. Full article

Black smoke emitted from diesel vehicles contains substantial amounts of hazardous substances. With the increasing annual levels of such emissions, there is growing concern over their detrimental effects on both the environment and human health. Therefore, it is imperative to strengthen the supervision and control of black smoke emissions. An effective approach is to analyze the smoke emission status of vehicles. Conventional object detection models often exhibit limitations in detecting black smoke, including challenges related to multi-scale target sizes, complex backgrounds, and insufficient localization accuracy. To address these issues, this study proposes a multi-dimensional detection algorithm. First, a multi-scale feature extraction method was introduced by replacing the conventional C2F module with a mechanism that employs parallel convolutional kernels of varying sizes. This design enables the extraction of features at different receptive fields, significantly improving the capability to capture black smoke patterns. To further enhance the network’s performance, a four-layer adaptive feature fusion detection head was proposed. This component dynamically adjusts the fusion weights assigned to each feature layer, thereby leveraging the unique advantages of different hierarchical representations. Additionally, to improve localization accuracy affected by the highly irregular shapes of black smoke edges, the Inner-IoU loss function was incorporated. This loss effectively alleviates the oversensitivity of CIoU to bounding box regression near image boundaries. Experiments conducted on a custom dataset, named Smoke-X, demonstrated that the proposed algorithm achieves a 4.8% increase in precision, a 5.9% improvement in recall, and a 5.6% gain in mAP50, compared to baseline methods. These improvements indicate that the model exhibits stronger adaptability to complex environments, suggesting considerable practical value for real-world applications. Full article

The operational status of photovoltaic modules directly impacts power generation efficiency, making rapid and precise fault detection crucial for intelligent operation and maintenance of Photovoltaic (PV) power plants. Addressing the perceptual limitations of single-modal images in complex environments, this study constructs an RGBIRPV multimodal dataset tailored for centralized PV power plants and proposes an RFE-YOLO model. This model enhances detection performance through three core mechanisms: The RC module employs a CBAM-based attention mechanism for multi-parameter feature extraction, utilizing heterogeneous RC_V and RC_I architectures to achieve differentiated feature enhancement for visible and infrared modalities. The lightweight adaptive fusion FA module introduces learnable modality balance and attention cascading mechanisms to optimize multimodal information fusion. Concurrently, the multi-scale enhanced EVG module based on GSConv achieves synergistic representation of shallow details and deep semantics with low computational overhead. The experiment employed an 8:1:1 data partitioning scheme. Compared to the YOLOv11n model employing feature-level mid-fusion, the model proposed in this study achieves improvements of 2.9%, 1.8%, and 1.5% in precision, mAP@50, and F1 score, respectively. It effectively meets the demand for rapid and accurate detection of PV module failures in real power plant environments, providing an effective technical solution for intelligent operation and maintenance of photovoltaic power plants. Full article

This study proposes ToRLNet, a lightweight tomato ripeness detector designed for real-time deployment in resource-constrained agricultural settings. Built on YOLOv12n, ToRLNet integrates three self-constructed modules (WaveFusionNet for frequency–spatial enhancement and feature extraction, ETomS for efficient context-aware encoding, and SFAConv for selective multi-scale downsampling) to address subtle inter-stage color transitions, small fruit instances, and cluttered canopies. We benchmark ToRLNet against lightweight and small-scale YOLO baselines (YOLOv8–YOLOv12) and conduct controlled ablations isolating each module’s contribution. ToRLNet attains Precision 90.27%, Recall 86.77%, F1-score 88.49%, mAP50 91.76%, and mAP 78.01% with only 6.9 GFLOPs, outperforming representative nano/small YOLO variants under comparable compute budgets. Ablation results show WaveFusionNet improves spectral–textural robustness, ETomS balances the precision–recall trade-off while reducing redundancy, and SFAConv preserves fine chromatic gradients and boundary structure during downsampling; their combination yields the most balanced performance. These findings demonstrate that ToRLNet delivers a favorable accuracy–efficiency trade-off and provides a practical foundation for on-board perception in automated harvesting, yield estimation, and greenhouse management. Full article

Lychee detection and maturity classification are crucial for yield estimation and harvesting. In densely packed lychee clusters with limited training samples, accurately determining ripeness is challenging. This paper proposes a new transformer model incorporating a Kolmogorov–Arnold Network (KAN), termed GhostResNet (GRN)–KAN–Transformer, for lychee detection and ripeness classification in dense on-tree fruit clusters. First, within the backbone, we introduce a stackable multi-layer GhostResNet module to reduce redundancy in feature extraction and improve efficiency. Next, during feature fusion, we add a large-scale layer to enhance sensitivity to small objects and to increase polling of the small-scale feature map during querying. We further propose a multi-layer cross-fusion attention (MCFA) module to achieve deeper hierarchical feature integration. Finally, in the decoding stage, we employ an improved KAN for the classification and localization heads to strengthen nonlinear mapping, enabling a better fitting to the complex distributions of categories and positions. Experiments on a public dataset demonstrate the effectiveness of GRN-KANformer. Compared with the baseline, GFLOPs and parameters of the model are reduced by 8.84% and 11.24%, respectively, while mean Average Precision (mAP) metrics mAP50 and mAP50–95 reach 94.7% and 58.4%, respectively. Thus, it lowers computational complexity while maintaining high accuracy. Comparative results against popular deep learning models, including YOLOv8n, YOLOv12n, CenterNet, and EfficientNet, further validate the superior performance of GRN-KANformer. Full article

Monitoring water quality in Welsh rivers has become a critical public concern, particularly in efforts to address pollution and protect the environment. This study presents the development and assessment of an interactive web and mobile application, featuring a real-time mapping interface built using the Mapbox framework. The platform provides stakeholders, including farmers, environmental agencies, and the public, with easy access to real-time water quality data using the Ystwyth River in Mid-Wales as a trial system. Users can click on map markers to view sensor readings for key water quality parameters. These include pH, electrical conductivity (EC), temperature, dissolved oxygen (DO), total dissolved solids (TDS) and nutrients levels such as nitrate (NO₃). This paper focuses on the feasibility of combining in situ sensor technology with a user-friendly mobile app to enable stakeholders to visualize the impact of land management practices and make informed decisions. The system aims to enhance environmental surveillance, increase transparency, and promote sustainable agricultural practices by providing critical water quality information in an accessible format. Future developments will explore the integration of artificial intelligence (AI) for predictive modelling and satellite data for broader spatial coverage, with the goal of scaling up the system to other catchments and improving proactive water quality management. Full article

Dimensionality reduction is fundamental for analyzing high-dimensional data, supporting visualization, denoising, and structure discovery. We present a systematic, large-scale benchmark of three widely used methods—Principal Component Analysis (PCA), Isometric Mapping (Isomap), and t-Distributed Stochastic Neighbor Embedding (t-SNE)—evaluated by average silhouette scores to quantify cluster preservation after embedding. Our full factorial simulation varies sample size $n\in \{100,200,300,400,500\}$, noise variance ${\sigma }^2\in \{0.25,0.5,0.75,1,1.5,2\}$, and feature count $p\in \{20,50,100,200,300,400\}$ under four generative regimes: (1) a linear Gaussian mixture, (2) a linear Student-t mixture with heavy tails, (3) a nonlinear Swiss-roll manifold, and (4) a nonlinear concentric-spheres manifold, each replicated 1000 times per condition. Beyond empirical comparisons, we provide mathematical results that explain the observed rankings: under standard separation and sampling assumptions, PCA maximizes silhouettes for linear, low-rank structure, whereas Isomap dominates on smooth curved manifolds; t-SNE prioritizes local neighborhoods, yielding strong local separation but less reliable global geometry. Empirically, PCA consistently achieves the highest silhouettes for linear structure (Isomap second, t-SNE third); on manifolds the ordering reverses (Isomap > t-SNE > PCA). Increasing ${\sigma }^2$ and adding uninformative dimensions (larger p) degrade all methods, while larger n improves levels and stability. To our knowledge, this is the first integrated study combining a comprehensive factorial simulation across linear and nonlinear regimes with distribution-based summaries (density and violin plots) and supporting theory that predicts method orderings. The results offer clear, practice-oriented guidance: prefer PCA when structure is approximately linear; favor manifold learning—especially Isomap—when curvature is present; and use t-SNE for the exploratory visualization of local neighborhoods. Complete tables and replication materials are provided to facilitate method selection and reproducibility. Full article

The pollination of kiwiberry flowers is closely related to fruit growth, development, and yield. Rapid and precise identification of flowers under natural field conditions plays a key role in enhancing pollination efficiency and improving overall fruit quality. Flowers and buds are densely distributed, varying in size, and exhibiting similar colors. Complex backgrounds, lighting variations, and occlusion further challenge detection. To address these issues, the YOLO11s-RFBS model was proposed. The P5 detection head was replaced with P2 to improve the detection of densely distributed small flowers and buds. RFAConv was incorporated into the backbone to strengthen feature discrimination across multiple receptive field scales and to mitigate issues caused by parameter sharing. The C3k2-Faster module was designed to reduce redundant computation and improve feature extraction efficiency. A weighted bidirectional feature pyramid slim neck network was constructed with a compact architecture to achieve superior multi-scale feature fusion with minimal parameter usage. Experimental evaluations indicated that YOLO11s-RFBS reached a mAP@0.5 of 91.7%, outperforming YOLO11s by 2.7%, while simultaneously reducing the parameter count and model footprint by 33.3% and 31.8%, respectively. Compared with other mainstream models, it demonstrated superior comprehensive performance. Its detection speed exceeded 21 FPS in deployment, satisfying real-time requirements. In conclusion, YOLO11s-RFBS enables accurate and efficient detection of kiwiberry flowers and buds, supporting intelligent pollination robots. Full article

Unmanned Aerial Vehicle (UAV) detection often faces challenges such as small target size, loss of textural details, and interference from complex backgrounds. To address these issues, this paper proposes a novel object detection algorithm named Spatial-Frequency Aware DETR (SFA-DETR), which integrates both spatial- and frequency-domain perception. For spatial-domain modeling, a backbone network named IncepMix is designed to dynamically fuse multi-scale receptive field information, enhancing the model’s ability to capture contextual information while reducing computational cost. For frequency-domain modeling, a Frequency-Guided Attention Block (FGA Block) is introduced to improve perception of target boundaries through frequency-aware guidance, thereby increasing localization accuracy. Furthermore, an adaptive sparse attention mechanism is incorporated into AIFI to emphasize semantically critical information and suppress redundant features. Experiments conducted on the DUT Anti-UAV dataset demonstrate that SFA-DETR improves mAP50 and mAP50:95 by 1.2% and 1.7%, respectively, while reducing parameter count and computational cost by 14.44% and 3.34%. The results indicate that the proposed method achieves a balance between detection accuracy and computational efficiency, validating its effectiveness in UAV detection tasks. Full article

Object detection technology plays a vital role in monitoring the growth status of aquaculture organisms and serves as a key enabler for the automated robotic capture of target species. Existing models for underwater biological detection often suffer from low accuracy and high model complexity. To address these limitations, we propose AOD-YOLO—an enhanced model based on YOLOv11s. The improvements are fourfold: First, the SPFE (Sobel and Pooling Feature Enhancement) module incorporates Sobel operators and pooling operations to effectively extract target edge information and global structural features, thereby strengthening feature representation. Second, the RGL (RepConv and Ghost Lightweight) module reduces redundancy in intermediate feature mappings of the convolutional neural network, decreasing parameter size and computational cost while further enhancing feature extraction capability through RepConv. Third, the MDCS (Multiple Dilated Convolution Sharing Module) module replaces the SPPF structure by integrating parameter-shared dilated convolutions, improving multi-scale target recognition. Finally, we upgrade the C2PSA module to C2PSA-M (Cascade Pyramid Spatial Attention—Mona) by integrating the Mona mechanism. This upgraded module introduces multi-cognitive filters to enhance visual signal processing and employs a distribution adaptation layer to optimize input information distribution. Experiments conducted on the URPC2020 and RUOD datasets demonstrate that AOD-YOLO achieves an accuracy of 86.6% on URPC2020, representing a 2.6% improvement over YOLOv11s, and 88.1% on RUOD, a 2.4% increase. Moreover, the model maintains relatively low complexity with only 8.73 M parameters and 21.4 GFLOPs computational cost. Experimental results show that our model achieves high accuracy for aquaculture targets while maintaining low complexity. This demonstrates its strong potential for reliable use in intelligent aquaculture monitoring systems. Full article

In autonomous driving, detecting small and occluded objects remains a substantial challenge due to the complexity of real-world environments. To address this, we propose RSO-YOLO, an enhanced model based on YOLOv12. First, the bidirectional feature pyramid network (BiFPN) and space-to-depth convolution (SPD-Conv) replace the original neck network. This design efficiently integrates multi-scale features while preserving fine-grained information during downsampling, thereby improving both computational efficiency and detection performance. Additionally, a detection head for the shallower feature layer P2 is incorporated, further boosting the model’s capability to detect small objects. Second, we propose the feature enhancement and compensation module (FECM), which strengthens features in visible regions and compensates for missing semantic information in occluded areas. This module improves detection accuracy and robustness under occlusion. Finally, we propose a lightweight global cross-dimensional coordinate detection head (GCCHead), built upon the global cross-dimensional coordinate module (GCCM). By grouping and synergistically enhancing features, this module addresses the challenge of balancing computational efficiency with detection performance. Experimental results demonstrate that on the SODA10M, BDD100K, and FLIR ADAS datasets, RSO-YOLO achieves mAP@0.5 improvements of 8.0%, 10.7%, and 7.2%, respectively, compared to YOLOv12. Meanwhile, the number of parameters is reduced by 15.4%, and model complexity decreases by 20%. In summary, RSO-YOLO attains higher detection accuracy while reducing parameters and computational complexity, highlighting its strong potential for practical autonomous driving applications. Full article

Quantum machine learning (QML) integrates quantum computing with classical machine learning. Within this domain, QML-CQ classification tasks, where classical data is processed by quantum circuits, have attracted particular interest for their potential to exploit high-dimensional feature maps, entanglement-enabled correlations, and non-classical priors. Yet, practical realizations remain constrained by the Noisy Intermediate-Scale Quantum (NISQ) era, where limited qubit counts, gate errors, and coherence losses necessitate frugal, noise-aware strategies. The Data Re-Uploading (DRU) algorithm has emerged as a strong NISQ-compatible candidate, offering universal classification capabilities with minimal qubit requirements. While DRU has been experimentally demonstrated on ion-trap, photonic, and superconducting platforms, no implementations exist for spin-based quantum processing units (QPU-SBs), despite their scalability potential via CMOS-compatible fabrication and recent demonstrations of multi-qubit processors. Here, we present a pulse-level, noise-aware DRU framework for spin-based QPUs, designed to bridge the gap between gate-level models and realistic spin-qubit execution. Our approach includes (i) compiling DRU circuits into hardware-proximate, time-domain controls derived from the Loss–DiVincenzo Hamiltonian, (ii) explicitly incorporating coherent and incoherent noise sources through pulse perturbations and Lindblad channels, (iii) enabling systematic noise-sensitivity studies across one-, two-, and four-spin configurations via continuous-time simulation, and (iv) developing a noise-aware training pipeline that benchmarks gate-level baselines against spin-level dynamics using information-theoretic loss functions. Numerical experiments show that our simulations reproduce gate-level dynamics with fidelities near unity while providing a richer error characterization under realistic noise. Moreover, divergence-based losses significantly enhance classification accuracy and robustness compared to fidelity-based metrics. Together, these results establish the proposed framework as a practical route for advancing DRU on spin-based platforms and motivate future work on error-attentive training and spin–quantum-dot noise modeling. Full article

Cross-scene classification of hyperspectral images poses significant challenges due to the lack of a priori knowledge and the differences in data distribution across scenes. While traditional studies have had limited use of a priori knowledge from other modalities, recent advancements in pre-trained large-scale language-vision models have shown strong performance on various downstream tasks, highlighting the potential of cross-modal assisted learning. In this paper, we propose a Semantic-aware Collaborative Parallel Network (SCPNet) to mitigate the impact of data distribution differences by incorporating linguistic modalities to assist in learning cross-domain invariant representations of hyperspectral images. SCPNet uses a parallel architecture consisting of a spatial–spectral feature extraction module and a multiscale feature extraction module, designed to capture rich image information during the feature extraction phase. The extracted features are then mapped into an optimized semantic space, where improved supervised contrastive learning clusters image features from the same category together while separating those from different categories. Semantic space bridges the gap between visual and linguistic modalities, enabling the model to mine cross-domain invariant representations from the linguistic modality. Experimental results demonstrate that SCPNet significantly outperforms existing methods on three publicly available datasets, confirming its effectiveness for cross-scene hyperspectral image classification tasks. Full article

Accurate, scalable mapping of coral reef habitats is essential for monitoring ecosystem health and detecting change over time. In this study, we introduce a novel mathematically based nonlinear spectral unmixing method for benthic habitat classification, which provides sub-pixel estimates of benthic composition, capturing the mixed benthic composition within individual pixels. We compare its performance against two machine learning approaches: semi-supervised K-Means clustering and AdaBoost decision trees. All models were applied to high-resolution PlanetScope satellite imagery and ICESat-2-derived terrain metrics. Models were trained using a ground truth dataset constructed from benthic photoquadrats collected at Heron Reef, Australia, with additional input features including band ratios, standardized band differences, and derived ICESat-2 metrics such as rugosity and slope. While AdaBoost achieved the highest overall accuracy ($93.3\%$) and benefited most from ICESat-2 features, K-Means performed less well ($85.9\%$) and declined when these metrics were included. The spectral unmixing method uniquely captured sub-pixel habitat abundance, offering a more nuanced and ecologically realistic view of reef composition despite lower discrete classification accuracy ($64.8\%$). These findings highlight nonlinear spectral unmixing as a promising approach for fine-scale, transferable coral reef habitat mapping, especially in complex or heterogeneous reef environments. Full article