Search Results (12)

To tackle the challenges posed by substantial variations in target scale, intricate background interference, and the likelihood of missing small targets in multi-temporal UAV maize tassel imagery, an optimized lightweight detection model derived from YOLOv11 is introduced, named OTB-YOLO. Here, “OTB” is an acronym derived from the initials of the model’s core improved modules: Omni-dimensional dynamic convolution (ODConv), Triplet Attention, and Bi-directional Feature Pyramid Network (BiFPN). This model integrates the PaddlePaddle open-source maize tassel recognition benchmark dataset with the public Multi-Temporal Drone Corn Dataset (MTDC). Traditional convolutional layers are substituted with omni-dimensional dynamic convolution (ODConv) to mitigate computational redundancy. A triplet attention module is incorporated to refine feature extraction within the backbone network, while a bidirectional feature pyramid network (BiFPN) is engineered to enhance accuracy via multi-level feature pyramids and bidirectional information flow. Empirical analysis demonstrates that the enhanced model achieves a precision of 95.6%, recall of 92.1%, and mAP@0.5 of 96.6%, marking improvements of 3.2%, 2.5%, and 3.1%, respectively, over the baseline model. Concurrently, the model’s computational complexity is reduced to 6.0 GFLOPs, rendering it appropriate for deployment on UAV edge computing platforms. Full article

In the process of high-speed wire rod production, flying steel accidents may occur due to various reasons. Current detection methods relying on sensors like hardware make debugging complex as well as limit real-time and accuracy. These methods are complicated to debug, and the real-time and accuracy of detection are poor. Therefore, this paper proposes a flying steel detection method based on improved You Only Look Once v8 (YOLOv8), which can realize high-precision flying steel detection based on machine vision through the monitoring video of the production site. Firstly, the Omni-dimensional Dynamic Convolution (ODConv) is added to the backbone network to improve the feature extraction ability of the input image. Then, a lightweight C2f-PCCA_RVB module is proposed to be integrated into the neck network, so as to carry out the lightweight design of the neck network. Finally, the Efficient Multi-Scale Attention (EMA) module is added to the neck network to fuse the context information of different scales and improve the feature extraction ability. The experimental results show that the average accuracy (mAP@0.5) of the flying steel detection method based on the improved YOLOv8 is 99.1%, and the latency is reduced to 2.5 ms, which can realize the real-time accurate detection of the flying steel. Full article

Antibody–drug conjugates (ADCs) are promising cancer therapeutics, but optimizing their cytotoxic payloads remains challenging. We present DumplingGNN, a novel hybrid Graph Neural Network architecture for predicting ADC payload activity and toxicity. Integrating MPNN, GAT, and GraphSAGE layers, DumplingGNN captures multi-scale molecular features using both 2D and 3D structural information. Evaluated on a comprehensive ADC payload dataset and MoleculeNet benchmarks, DumplingGNN achieves state-of-the-art performance, including BBBP (96.4% ROC-AUC), ToxCast (78.2% ROC-AUC), and PCBA (88.87% ROC-AUC). On our specialized ADC payload dataset, it demonstrates 91.48% accuracy, 95.08% sensitivity, and 97.54% specificity. Ablation studies confirm the hybrid architecture’s synergy and the importance of 3D information. The model’s interpretability provides insights into structure–activity relationships. DumplingGNN’s robust toxicity prediction capabilities make it valuable for early safety evaluation and biomedical regulation. As a research prototype, DumplingGNN is being considered for integration into Omni Medical, an AI-driven drug discovery platform currently under development, demonstrating its potential for future practical applications. This advancement promises to accelerate ADC payload design, particularly for Topoisomerase I inhibitor-based payloads, and improve early-stage drug safety assessment in targeted cancer therapy development. Full article

The main goal of six-dimensional pose estimation is to accurately ascertain the location and orientation of an object in three-dimensional space, which has a wide range of applications in the field of artificial intelligence. Due to the relative sparseness of the point cloud data captured by the depth camera, the ability of models to fully understand the shape, structure, and other features of the object is hindered. Consequently, the model exhibits weak generalization when faced with objects with significant shape differences in the new scene. The deep integration of feature levels and the mining of local and global information can effectively alleviate the influence of the above factors. To solve these problems, we propose a new Two-Stage Geometric Neighborhood Fusion Network for category-level 6D pose estimation (TGNF-Net) to estimate objects that have not appeared in the training phase, which strengthens the fusion capacity of feature points within a specific range of neighborhoods, enabling the feature points to be more sensitive to both local and global geometric information. Our approach includes a neighborhood information fusion module, which can effectively utilize neighborhood information to enrich the feature set of different modal data and overcome the problem of heterogeneity between image and point cloud data. In addition to this, we design a two-stage geometric information embedding module, which can effectively fuse geometric information of the multi-scale range into keypoint features. This way enhances the robustness of the model and enables the model to exhibit stronger generalization capabilities when faced with unknown or complex scenes. These two strategies enhance the expression of features and make NOCS coordinate predictions more accurate. Many experiments show that our approach is superior to other classical methods on the CAMERA25, REAL275, HouseCat6D, and Omni6DPose datasets. Full article

The detection of tea bud targets is the foundation of automated picking of premium tea. This article proposes a high-performance tea bud detection model to address issues such as complex environments, small target tea buds, and blurry device focus in tea bud detection. During the spring tea-picking stage, we collect tea bud images from mountainous tea gardens and annotate them. YOLOv5 tea is an improvement based on YOLOv5, which uses the efficient Simplified Spatial Pyramid Pooling Fast (SimSPPF) in the backbone for easy deployment on tea bud-picking equipment. The neck network adopts the Bidirectional Feature Pyramid Network (BiFPN) structure. It fully integrates deep and shallow feature information, achieving the effect of fusing features at different scales and improving the detection accuracy of focused fuzzy tea buds. It replaces the independent CBS convolution module in traditional neck networks with Omni-Dimensional Dynamic Convolution (ODConv), processing different weights from spatial size, input channel, output channel, and convolution kernel to improve the detection of small targets and occluded tea buds. The experimental results show that the improved model has improved precision, recall, and mean average precision by 4.4%, 2.3%, and 3.2%, respectively, compared to the initial model, and the inference speed of the model has also been improved. This study has theoretical and practical significance for tea bud harvesting in complex environments. Full article

Semantic change detection (SCD) is a newly important topic in the field of remote sensing (RS) image interpretation since it provides semantic comprehension for bi-temporal RS images via predicting change regions and change types and has great significance for urban planning and ecological monitoring. With the availability of large scale bi-temporal RS datasets, various models based on deep learning (DL) have been widely applied in SCD. Since convolution operators in DL extracts two-dimensional feature matrices in the spatial dimension of images and stack feature matrices in the dimension termed the channel, feature maps of images are tri-dimensional. However, recent SCD models usually overlook the stereoscopic property of feature maps. Firstly, recent SCD models are usually limited in capturing spatial global features in the process of bi-temporal global feature extraction and overlook the global channel features. Meanwhile, recent SCD models only focus on spatial cross-temporal interaction in the process of change feature perception and ignore the channel interaction. Thus, to address above two challenges, a novel fine-grained feature perception network (FFPNet) is proposed in this paper, which employs the Omni Transformer (OiT) module to capture bi-temporal channel–spatial global features before utilizing the Omni Cross-Perception (OCP) module to achieve channel–spatial interaction between cross-temporal features. According to the experiments on the SECOND dataset and the LandsatSCD dataset, our FFPNet reaches competitive performance on both countryside and urban scenes compared with recent typical SCD models. Full article

Affected by the complex underwater environment and the limitations of low-resolution sonar image data and small sample sizes, traditional image recognition algorithms have difficulties achieving accurate sonar image recognition. The research builds on YOLOv7 and devises an innovative fast recognition model designed explicitly for sonar images, namely the Dual Attention Mechanism YOLOv7 model (DA-YOLOv7), to tackle such challenges. New modules such as the Omni-Directional Convolution Channel Prior Convolutional Attention Efficient Layer Aggregation Network (OA-ELAN), Spatial Pyramid Pooling Channel Shuffling and Pixel-level Convolution Bilat-eral-branch Transformer (SPPCSPCBiFormer), and Ghost-Shuffle Convolution Enhanced Layer Aggregation Network-High performance (G-ELAN-H) are central to its design, which reduce the computational burden and enhance the accuracy in detecting small targets and capturing local features and crucial information. The study adopts transfer learning to deal with the lack of sonar image samples. By pre-training the large-scale Underwater Acoustic Target Detection Dataset (UATD dataset), DA-YOLOV7 obtains initial weights, fine-tuned on the smaller Smaller Common Sonar Target Detection Dataset (SCTD dataset), thereby reducing the risk of overfitting which is commonly encountered in small datasets. The experimental results on the UATD, the Underwater Optical Target Detection Intelligent Algorithm Competition 2021 Dataset (URPC), and SCTD datasets show that DA-YOLOV7 exhibits outstanding performance, with mAP@0.5 scores reaching 89.4%, 89.9%, and 99.15%, respectively. In addition, the model maintains real-time speed while having superior accuracy and recall rates compared to existing mainstream target recognition models. These findings establish the superiority of DA-YOLOV7 in sonar image analysis tasks. Full article

Blockchain technology ensures record-keeping by redundantly storing and verifying transactions on a distributed network of nodes. Permissionless blockchains have pushed the development of decentralized applications (DApps) characterized by distributed business logic, resilience to centralized failures, and data immutability. However, storage scalability without sacrificing throughput is one of the remaining open challenges in permissionless blockchains. Enhancing throughput often compromises storage, as seen in projects such as Elastico, OmniLedger, and RapidChain. On the other hand, solutions seeking to save storage, such as CUB, Jidar, SASLedger, and SE-Chain, reduce the transactional throughput. To our knowledge, no analysis has been performed that relates storage growth to transactional throughput. In this article, we delve into the execution of the Bitcoin and Ethereum transactional models, unlocking patterns that represent any transaction on the blockchain. We reveal the trade-off between transactional throughput and storage. To achieve this, we introduce the spent-by relation, a new abstraction of the UTXO model that utilizes a directed acyclic graph (DAG) to reveal the patterns and allows for a graph with granular information. We then analyze the transactional patterns to identify the most storage-intensive ones and those that offer greater flexibility in the throughput/storage trade-off. Finally, we present an analytical study showing that the UTXO model is more storage-intensive than the account model but scales better in transactional throughput. Full article

Ship detection is vital for maritime safety and vessel monitoring, but challenges like false and missed detections persist, particularly in complex backgrounds, multiple scales, and adverse weather conditions. This paper presents YOLO-Vessel, a ship detection model built upon YOLOv7, which incorporates several innovations to improve its performance. First, we devised a novel backbone network structure called Efficient Layer Aggregation Networks and Omni-Dimensional Dynamic Convolution (ELAN-ODConv). This architecture effectively addresses the complex background interference commonly encountered in maritime ship images, thereby improving the model’s feature extraction capabilities. Additionally, we introduce the space-to-depth structure in the head network, which can solve the problem of small ship targets in images that are difficult to detect. Furthermore, we introduced ASFFPredict, a predictive network structure addressing scale variation among ship types, bolstering multiscale ship target detection. Experimental results demonstrate YOLO-Vessel’s effectiveness, achieving a 78.3% mean average precision (mAP), surpassing YOLOv7 by 2.3% and Faster R-CNN by 11.6%. It maintains real-time detection at 8.0 ms/frame, meeting real-time ship detection needs. Evaluation in adverse weather conditions confirms YOLO-Vessel’s superiority in ship detection, offering a robust solution to maritime challenges and enhancing marine safety and vessel monitoring. Full article

In the upcoming 6G era, edge artificial intelligence (AI), as a key technology, will be able to deliver AI processes anytime and anywhere by the deploying of AI models on edge devices. As a hot issue in public safety, person re-identification (Re-ID) also needs its models to be urgently deployed on edge devices to realize real-time and accurate recognition. However, due to complex scenarios and other practical reasons, the performance of the re-identification model is poor in practice. This is especially the case in public places, where most people have similar characteristics, and there are environmental differences, as well other such characteristics that cause problems for identification, and which make it difficult to search for suspicious persons. Therefore, a novel end-to-end suspicious person re-identification framework deployed on edge devices that focuses on real public scenarios is proposed in this paper. In our framework, the video data are cut images and are input into the You only look once (YOLOv5) detector to obtain the pedestrian position information. An omni-scale network (OSNet) is applied through which to conduct the pedestrian attribute recognition and re-identification. Broad learning systems (BLSs) and cycle-consistent adversarial networks (CycleGAN) are used to remove the noise data and unify the style of some of the data obtained under different shooting environments, thus improving the re-identification model performance. In addition, a real-world dataset of the railway station and actual problem requirements are provided as our experimental targets. The HUAWEI Atlas 500 was used as the edge equipment for the testing phase. The experimental results indicate that our framework is effective and lightweight, can be deployed on edge devices, and it can be applied for suspicious person re-identification in public places. Full article

Backscatter communication (BackCom) constitutes intriguing technology that enables low-power devices in transmitting signals by reflecting ambient radio frequency (RF) signals that consume ultra-low energy. Applying the BackCom technique in large-scale networks with massive low-power devices can effectively address the energy issue observed in low-power devices. Prior studies only consider large-scale BackCom networks equipped with omni-directional antennas, called Omn-BackCom Net. To improve the network’s performance, we employ directional antennas in large-scale BackCom networks, called Dir-BackCom Nets. This article establishes a theoretical model for analyzing the performance of Dir-BackCom Nets. The performance metrics include both connectivity and spatial throughput. Our model is genaralized for both Dir-BackCom Nets and Omn-BackCom Net. The accuracy of our theoretical model is verified by extensive simulations. Results indicate that Dir-BackCom Nets can improve connectivity and spatial throughput. Moreover, results show that the throughput can be maximized by choosing an optimal density of BTs. In addition, both the connectivity and spatial throughput of BackCom Nets can be improved by choosing a directional antenna with a proper beamwidth and gain of the main lobe. Our theoretical model and results can offer beneficial implications for constructing Dir-BackCom Nets. Full article

Although wearable antennas have made great progress in recent years, how to design high-performance antennas suitable for most wireless communication systems has always been the direction of RF workers. In this paper, a new approach for the design and manufacture of a compact, low-profile, broadband, omni-directional and conformal antenna is presented, including the use of a customized flexible dielectric substrate with high permittivity and low loss tangent to realize the compact sensing antenna. Poly-di-methyl-siloxane (PDMS) is doped a certain proportion of aluminum trioxide (Al₂O₃) and Poly-tetra-fluoro-ethylene (PTFE) to investigate the effect of dielectric constant and loss tangent. Through a large number of comparative experiments, data on different doping ratios show that the new doped materials are flexible enough to increase dielectric constant, reduce loss tangent and significantly improve the load resistance capacity. The antenna is configured with a multisection microstrip stepped impedance resonator structure (SIR) to expand the bandwidth. The measured reflection return loss (S11) showed an operating frequency band from 0.99 to 9.41 GHz, with a band ratio of 146%. The antenna covers two important frequency bands, 1.71–2.484 GHz (personal communication system and wireless body area network (WBAN) systems) and 5.15–5.825 GHz (wireless local area network-WLAN)]. It also passed the SAR test for human safety. Therefore, the proposed antenna offers a good chance for full coverage of WLAN and large-scale development of wearable products. It also has potential applications in communication systems, wireless energy acquisition systems and other wireless systems. Full article