Search Results (8,075)

Deploying target detection models on edge devices such as UAVs is challenging due to their limited size and computational capacity, while target detection models typically require significant computational resources. To address this issue, this study proposes a lightweight real-time infrared object detection model named LRI-YOLO (Lightweight Real-time Infrared YOLO), which is based on YOLOv8n. The model improves the C2f module’s Bottleneck structure by integrating Partial Convolution (PConv) with Pointwise Convolution (PWConv), achieving a more lightweight design. Furthermore, during the feature fusion stage, the original downsampling structure with ordinary convolution is replaced with a combination of max pooling and regular convolution. This modification retains more feature map information. The model’s structure is further optimized by redesigning the decoupled detection head with Group Convolution (GConv) instead of ordinary convolution, significantly enhancing detection speed. Additionally, the original BCELoss is replaced with EMASlideLoss, a newly developed classification loss function introduced in this study. This loss function allows the model to focus more on hard samples, thereby improving its classification capability. Compared to the YOLOv8n algorithm, LRI-YOLO is more lightweight, with its parameters reduced by 46.7% and floating-point operations (FLOPs) reduced by 53.1%. Moreover, the mean average precision (mAP) reached 94.1%. Notably, on devices with moderate computational power that only have a Central Processing Unit (CPU), the detection speed reached 42 frames per second (FPS), surpassing most mainstream models. This indicates that LRI-YOLO offers a novel solution for real-time infrared object detection on edge devices such as drones. Full article

In aquaculture, the presence of dead fish on the water surface can serve as a bioindicator of health issues or environmental stressors. To enhance the precision of detecting dead fish floating on the water’s surface, this paper proposes a detection approach that integrates data-driven insights with advanced modeling techniques. Firstly, to reduce the influence of aquatic disturbances and branches during the identification process, prior information, such as branches and ripples, is annotated in the dataset to guide the model to better learn the scale and shape characteristics of dead fish, reduce the interference of branch ripples on detection, and thus improve the accuracy of target identification. Secondly, leveraging the foundational YOLOv8 architecture, a DD-IYOLOv8 (Data-Driven Improved YOLOv8) dead fish detection model is designed. Considering the significant changes in the scale of dead fish at different distances, DySnakeConv (Dynamic Snake Convolution) is introduced into the neck network detection head to adaptively adjust the receptive field, thereby improving the network’s capability to capture features. Additionally, a layer for detecting minor objects has been added, and the detection head of YOLOv8 has been modified to 4, allowing the network to better focus on small targets and occluded dead fish, which improves detection performance. Furthermore, the model incorporates a HAM (Hybrid Attention Mechanism) in the later stages of the backbone network to refine global feature extraction, sharpening the model’s focus on dead fish targets and further enhancing detection accuracy. The experimental results showed that the accuracy of DD-IYOLOv8 in detecting dead fish reached 92.8%, the recall rate reached 89.4%, the AP reached 91.7%, and the F1 value reached 91.0%. This study can achieve precise identification of dead fish, which will help promote the research of automatic pond patrol machine ships. Full article

Substation equipment defect detection has always played an important role in equipment operation and maintenance. However, the task scenarios of substation equipment defect detection are complex and different. Recent studies have revealed issues such as a significant missed detection rate for small-sized targets and diminished detection precision. At the same time, the current mainstream detection algorithms are highly complex, which is not conducive to deployment on resource-constrained devices. In view of the above problems, a small target and lightweight substation main scene equipment defect detection algorithm is proposed: Efficient Attentional Lightweight-YOLO (EAL-YOLO), which detection accuracy exceeds the current mainstream model, and the number of parameters and floating point operations (FLOPs) are also advantageous. Firstly, the EfficientFormerV2 is used to optimize the model backbone, and the Large Separable Kernel Attention (LSKA) mechanism has been incorporated into the Spatial Pyramid Pooling Fast (SPPF) to enhance the model’s feature extraction capabilities; secondly, a small target neck network Attentional scale Sequence Fusion P2-Neck (ASF2-Neck) is proposed to enhance the model’s ability to detect small target defects; finally, in order to facilitate deployment on resource-constrained devices, a lightweight shared convolution detection head module Lightweight Shared Convolutional Head (LSCHead) is proposed. Experiments show that compared with YOLOv8n, EAL-YOLO has improved its accuracy by 2.93 percentage points, and the mAP50 of 12 types of typical equipment defects has reached 92.26%. Concurrently, the quantity of FLOPs and parameters has diminished by 46.5% and 61.17% respectively, in comparison with YOLOv8s, meeting the needs of substation defect detection. Full article

High-resolution imagery captured by drones can detect critical components on high-voltage transmission towers, providing inspection personnel with essential maintenance insights and improving the efficiency of power line inspections. The high-resolution imagery is particularly effective in enhancing the detection of fine details such as screws. The QYOLO algorithm, an enhancement of YOLOv8, incorporates context queries into the feature pyramid, effectively capturing long-range dependencies and improving the network’s ability to detect objects. To address the increased network depth and computational load introduced by query extraction, Ghost Separable Convolution (GSConv) is employed, reducing the computational expense by half and further improving the detection performance for small objects such as screws. The experimental validation using the Transmission Line Accessories Dataset (TLAD) developed for this project demonstrates that the proposed improvements increase the average precision (AP) for small objects by 5.5% and the F1-score by 3.5%. The method also enhances detection performance for overall targets, confirming its efficacy in practical applications. Full article

Physalis pubescens and Physalis alkekengi, members of the Physalis genus, are valued for their delicious and medicinal fruits as well as their different ripened fruit colors—golden for P. pubescens and scarlet for P. alkekengi. This study aimed to elucidate the pigment composition and genetic mechanisms during fruit maturation in these species. Fruit samples were collected at four development stages, analyzed using spectrophotometry and high-performance liquid chromatography (HPLC), and complemented with transcriptome sequencing to assess gene expression related to pigment biosynthesis. β-carotene was identified as the dominant pigment in P. pubescens, contrasting with P. alkekengi, which contained both lycopene and β-carotene. The carotenoid biosynthesis pathway was central to fruit pigmentation in both species. Key genes pf02G043370 and pf06G178980 in P. pubescens, and TRINITY_DN20150_c1_g3, TRINITY_DN10183_c0_g1, and TRINITY_DN23805_c0_g3 in P. alkekengi were associated with carotenoid production. Notably, the MYB-related and bHLH transcription factors (TFs) regulated zeta-carotene isomerase and β-hydroxylase activities in P. pubescens with the MYB-related TF showing dual regulatory roles. In P. alkekengi, six TF families—bHLH, HSF, WRKY, M-type MADS, AP2, and NAC—were implicated in controlling carotenoid synthesis enzymes. Our findings highlight the intricate regulatory network governing pigmentation and provide insights into Physalis germplasm’s genetic improvement and conservation. Full article

The precise segmentation of Zanthoxylum bungeanum clusters is crucial for developing picking robots. An improved Mask R-CNN model was proposed in this study for the segmentation of Zanthoxylum bungeanum clusters in natural environments. Firstly, the Swin-Transformer network was introduced into the model’s backbone as the feature extraction network to enhance the model’s feature extraction capabilities. Then, the SK attention mechanism was utilized to fuse the detailed information into the mask branch from the low-level feature map of the feature pyramid network (FPN), aiming to supplement the image detail features. Finally, the distance intersection over union (DIOU) loss function was adopted to replace the original bounding box loss function of Mask R-CNN. The model was trained and tested based on a self-constructed Zanthoxylum bungeanum cluster dataset. Experiments showed that the improved Mask R-CNN model achieved 84.0% and 77.2% in detection mAP50box and segmentation mAP50mask, respectively, representing a 5.8% and 4.6% improvement over the baseline Mask R-CNN model. In comparison to conventional instance segmentation models, such as YOLACT, Mask Scoring R-CNN, and SOLOv2, the improved Mask R-CNN model also exhibited higher segmentation precision. This study can provide valuable technology support for the development of Zanthoxylum bungeanum picking robots. Full article

Vehicle detection is essential for road traffic surveillance and active safety management. Deep learning methods have recently shown robust feature extraction capabilities and achieved improved detection results. However, vehicle detection models often perform poorly under abnormal lighting conditions, especially in highway tunnels. We proposed an adaptive vehicle detection model that accounts for varying luminance intensities to address this issue. The model categorizes the image data into abnormal and normal luminance scenarios. We employ an improved CycleGAN with edge loss as the adaptive luminance adjustment module for abnormal luminance scenarios. This module adjusts the brightness of the images to a normal level through a generative network. Finally, YOLOv7 is utilized for vehicle detection. The experimental results demonstrate that our adaptive vehicle detection model effectively detects vehicles under abnormal luminance scenarios in highway tunnels. The improved CycleGAN can effectively mitigate edge generation distortion. Under abnormal luminance scenarios, our model achieved a 16.3% improvement in precision, a 1.7% improvement in recall, and a 9.8% improvement in mAP_0.5 compared to the original YOLOv7. Additionally, our adaptive luminance adjustment module is transferable and can enhance the detection accuracy of other vehicle detection models. Full article

Aiming at the problems of a large volume, slow processing speed, and difficult deployment in the edge terminal, this paper proposes a lightweight insulator detection algorithm based on an improved SSD. Firstly, the original feature extraction network VGG-16 is replaced by a lightweight Ghost Module network to initially achieve the lightweight model. A Feature Pyramid structure and Feature Pyramid Network (FPN+PAN) are integrated into the Neck part and a Simplified Spatial Pyramid Pooling Fast (SimSPPF) module is introduced to realize the integration of local features and global features. Secondly, multiple Spatial and Channel Squeeze-and-Excitation (scSE) attention mechanisms are introduced in the Neck part to make the model pay more attention to the channels containing important feature information. The original six detection heads are reduced to four to improve the inference speed of the network. In order to improve the recognition performance of occluded and overlapping targets, DIoU-NMS was used to replace the original non-maximum suppression (NMS). Furthermore, the channel pruning strategy is used to reduce the unimportant weight matrix of the model, and the knowledge distillation strategy is used to fine-adjust the network model after pruning, so as to ensure the detection accuracy. The experimental results show that the parameter number of the proposed model is reduced from 26.15 M to 0.61 M, the computational load is reduced from 118.95 G to 1.49 G, and the mAP is increased from 96.8% to 98%. Compared with other models, the proposed model not only guarantees the detection accuracy of the algorithm, but also greatly reduces the model volume, which provides support for the realization of visible light insulator target detection based on edge intelligence. Full article

Current surgical practices in total knee arthroplasty (TKA) have advanced and include significant changes and improvements in alignment philosophies, femorotibial implant conformities, and ligament management to replicate in vivo knee kinematics. While corrective measures have emphasized sagittal plane alignment to restore normal flexion–extension (F–E) motion and coronal plane ligament balance, internal–external (I–E) rotation kinematics in the axial plane have been largely neglected. Recent in vivo evidence indicates that the combination of factors necessary to closely restore native tibial rotation as the knee flexes and extends is kinematic alignment (KA), which resurfaces the patient’s pre-arthritic knee without releasing ligaments, an insert with medial 1:1 ball-in-socket conformity and a lateral flat surface, and posterior cruciate ligament (PCL) retention. However, the inherent anterior–posterior (A–P) stability provided by the medial 1:1 ball-in-socket limits the surgeon’s ability to select the correct insert thickness using manual laxity testing. Accordingly, this review presents the design and validation of an instrument called an insert goniometer that measures I–E tibial rotation for inserts that differ in thickness by 1 mm and uses rotation limits at extension and 90° flexion to select the optimal insert thickness. The optimal thickness is the one that provides the greatest external tibial orientation in extension and internal tibial orientation at 90° flexion without lift-off of the insert. Full article

With the rapid advancement of intelligent manufacturing technologies, the operating environments of modern robotic arms are becoming increasingly complex. In addition to the diversity of objects, there is often a high degree of similarity between the foreground and the background. Although traditional RGB-based object-detection models have achieved remarkable success in many fields, they still face the challenge of effectively detecting targets with textures similar to the background. To address this issue, we introduce the WoodenCube dataset, which contains over 5000 images of 10 different types of blocks. All images are densely annotated with object-level categories, bounding boxes, and rotation angles. Additionally, a new evaluation metric, Cube-mAP, is proposed to more accurately assess the detection performance of cube-like objects. In addition, we have developed a simple, yet effective, framework for WoodenCube, termed CS-SKNet, which captures strong texture features in the scene by enlarging the network’s receptive field. The experimental results indicate that our CS-SKNet achieves the best performance on the WoodenCube dataset, as evaluated by the Cube-mAP metric. We further evaluate the CS-SKNet on the challenging DOTAv1.0 dataset, with the consistent enhancement demonstrating its strong generalization capability. Full article

The work deals with the influence of the reach of the applied tool holder on the edge wear, dimensional accuracy and surface quality defined by the topography as well as the roughness of the machined surface. The research has been conducted on specimens made of Inconel 718 in the configuration of sleeves, within the scope of finish turning with constant cutting parameters, v_c = 85 m/min; f = 0.14 mm/rev; a_p = 0.2 mm. The material under machining has undergone heat treatment procedures such as solution treatment and precipitation hardening, resulting in a hardness of 45 ± 2 HRC. Two kinds of turning holders have been used with the reaches of 120 mm and 700 mm. The tools are intended for turning external and internal surfaces, respectively. The tests have been conducted using V-shaped cutting inserts manufactured by different producers, made of fine-grained carbide with coatings applied by the PVD (Physical Vapour Deposition) and CVD (Chemical Vapour Deposition) methods. The edge wear has been evaluated. The value of the achieved diameter dimensions has also been assessed in relation to the set ones, as well as the recorded values of surface roughness and the surface topography parameters have also been assessed. It has been determined that the quality of the manufactured surface evaluated by the 2D and 3D roughness parameters, as well as the dimensional quality are influenced by the kind of the applied tool holder. The influence is also visible considering the edge wear. The smallest values of the deviations from the nominal dimensions have been obtained for the coated inserts of the range of higher abrasion resistance (taking into account information from the producers). The obtained results show that in predicting the dimensional accuracy in the process of turning Inconel 718 alloy with long-overhang tools, one should consider the necessity of correction of the tool path. Taking into account the achieved surface roughness, it should be pointed out that not only the kind of the tool coating but also the character of its wear has a great influence, particularly, when a long cutting distance is required. Full article

Inherited and current trends of urbanization result in growing agri–urban mixed land use patterns that strongly call for innovative management and planning tools at the urban/rural interface. This could especially help to cope with both resilience and environmental fairness goals. In this framework, the category of the Agriculture Park (AP) deserves much attention in relating meaningful experiences, especially in Mediterranean areas. This article deepens the category with the aim of assessing its features as a viable tool in the planning domain to jointly protect and enhance peri-urban farmland areas. In particular, the adopted methodology taps into an integrated and holistic approach to define and assess, by design, a multi-purpose model of a Public Agri–urban Park (PAP) drawing on the Public–Private Partnership (PPP) management model (using break-even analysis to define the contents of the PPP itself), inhabitants’ participation, and referring to a typical fringe area in the municipality of Prato (Italy). Results show the potential of the PAP to jointly achieve—according to a proactive model of green spaces’ protection—many sustainable design targets along with new forms of services aimed at social welfare. At the same time, the article highlights the call for public bodies and agencies to overcome the “business as usual” and “silo-framed” institutional approach and establish fruitful collaborative and synergistic co-design procedures with inhabitants and local stakeholders. Full article

As the sika deer breeding industry flourishes on a large scale, accurately assessing the health of these animals is of paramount importance. Implementing posture recognition through target detection serves as a vital method for monitoring the well-being of sika deer. This approach allows for a more nuanced understanding of their physical condition, ensuring the industry can maintain high standards of animal welfare and productivity. In order to achieve remote monitoring of sika deer without interfering with the natural behavior of the animals, and to enhance animal welfare, this paper proposes a sika deer individual posture recognition detection algorithm GFI-YOLOv8 based on YOLOv8. Firstly, this paper proposes to add the iAFF iterative attention feature fusion module to the C2f of the backbone network module, replace the original SPPF module with AIFI module, and use the attention mechanism to adjust the feature channel adaptively. This aims to enhance granularity, improve the model’s recognition, and enhance understanding of sika deer behavior in complex scenes. Secondly, a novel convolutional neural network module is introduced to improve the efficiency and accuracy of feature extraction, while preserving the model’s depth and diversity. In addition, a new attention mechanism module is proposed to expand the receptive field and simplify the model. Furthermore, a new pyramid network and an optimized detection head module are presented to improve the recognition and interpretation of sika deer postures in intricate environments. The experimental results demonstrate that the model achieves 91.6% accuracy in recognizing the posture of sika deer, with a 6% improvement in accuracy and a 4.6% increase in mAP50 compared to YOLOv8n. Compared to other models in the YOLO series, such as YOLOv5n, YOLOv7-tiny, YOLOv8n, YOLOv8s, YOLOv9, and YOLOv10, this model exhibits higher accuracy, and improved mAP50 and mAP50-95 values. The overall performance is commendable, meeting the requirements for accurate and rapid identification of the posture of sika deer. This model proves beneficial for the precise and real-time monitoring of sika deer posture in complex breeding environments and under all-weather conditions. Full article

Emerging contaminants (ECs) present a significant risk to both the ecological environment and human health. Landfill leachate (LL) often contains elevated EC levels, posing a potential risk to localized groundwater. This study aimed to characterize ECs in municipal solid waste landfills (MSWLs) and hazardous waste landfills (HWLs) in northeast (NE) China. One and three HWLs and MSWLs in NE China with varying types, operational years, and impermeable layers were selected as case studies, respectively. Statistical analysis of 62 indicators of nine ECs in leachate and the groundwater environment indicated the presence of perfluorinated compounds (PFCs), antibiotics, alkylphenols (APs), and bisphenol A (BPA). The leachates of the four landfills exhibited elevated concentrations of ECs of 21.03 μg/L, 40.04 μg/L, 14.54 μg/L, and 43.05 μg/L for PFCs, antibiotics, Aps, and BPA, respectively. There was a positive correlation between the highest concentrations of ECs in groundwater and those in leachate as well as with operational duration of the landfill; in contrast, groundwater EC was negatively correlated with the degree of impermeability. This study can guide future management of ECs in landfills and hazardous waste sites in China, particularly in NE China. Full article

This article presents a new 3D extreme game for virtual reality (VR), which is used to evaluate the impact of generated mental stress on the cardiological state of the playing individuals. The game was developed using Java 3D and Blender. Generated stress is investigated by recording electrocardiograms for 20 min and determining heart rate variability (HRV) parameters in the time and frequency domains and by non-linear visual and quantitative analysis methods, such as the Rescaled Range (R/S) method, Poincarè plot, Recurrence plot, Approximate (ApEn), and Sample Entropy (SampEn). The data of 19 volunteers were analyzed before and immediately after the game, and a comparative analysis was made of two types of VR: immersive and non-immersive. The results show that the application of immersive VR generates higher mental stress levels than non-immersive VR, but in both cases, HRV changes (decreases), but more significantly in immersive VR. The results of this research can provide useful information about the functioning of the autonomic nervous system, which regulates the reactions of the human body during mental stress, to help in the early detection of potential health problems. Full article