Branching Characteristics Research Articles

Diffusion-based normality pre-training for weakly supervised video anomaly detection

Weakly supervised video anomaly detection is the task of detecting anomalous frames in videos where no frame-level labels are provided at training phase. Previous methods usually employed a multiple instance learning (MIL)-based ranking loss to ensure inter-class separation. However, these methods are unable to completely utilise the information from the huge amounts of normal frames. Moreover, the performance of these methods is misguided by the erroneous initial prediction of the MIL-based classifier. Taking these shortcomings into consideration, we propose a diffusion-based normality learning pretrain step, which first involves training a Global–Local Feature Encoder (GLFE) model with only normal videos to understand the feature distribution of normal frames. The resulting pre-trained Global–Local feature encoder is further optimised using Multi-Sequence Contrastive loss using both normal and anomalous videos. Our proposed GLFE model captures long- and short-range temporal features using a Transformer block and pyramid of dilated convolutions in a two-branch setup. The model adaptively learns the relation between the two branch features by introducing the Co-Attention module, which provides a learnable fusion of features. Additionally we introduced a triplet contrastive loss to provide better separation between abnormal and normal frames in anomalous videos. The developed methodology is evaluated through extensive experiments on two public benchmark datasets (UCF-Crime and ShanghaiTech). The results obtained are comparable to or better than the existing state-of-the-art weakly supervised methods.

Study on Electrochemical Corrosion of Q235 Steel in Sand Containing HA Solution under a Natural Air-Dried State

To explore the corrosion of Q235 steel in sand containing a simulated haze aqueous solution (HA solution) under a natural air-dried state, the effect of moisture (age) on the corrosion of Q235 steel in sand was comprehensively studied by EIS, polarization curve, SEM, EDS and XPS. The physical and chemical properties of the sand showed that the sand containing the HA solution was basically neutral under natural air drying, and the temperature was around 20 °C. After 14 days, the moisture content gradually decreased from 30% to 0%, and the salinity decreased from 1.26% to 0.04%. With the increase in age, the Eocp gradually positively skews, indicating the corrosion kinetics of the Q235 steel decrease. The impedance spectra showed that in the frequency of 10−2–103 Hz, the impedance spectra exhibited a flat capacitive loop, and the corrosion of Q235 steel was the strongest in the sand containing HA solution on the 8 d. The polarization curves showed that with increasing age, the degree of corrosion of Q235 steel changed from medium or above to slight corrosion in the sand containing HA solution. The pitting characteristics of anode branch for polarization curve also indicate the faster corrosion kinetics of Q235 steel in the early age (1–5 d). The corrosion current density Io first increased and then decreased, and the highest value was 3.44 × 10−5 A/cm2 at 6 d. The average corrosion rate was 0.1629 mm/a. HA solution accelerates the corrosion of Q235 steel in sand without HA solution (average corrosion rate, 1.51 × 10−2 mm/a). A large amount of brown-yellow corrosion products (iron oxides, about 70–200 μm) presented on the surface of the Q235 steel. The corrosion of Q235 steel belonged to local corrosion, and the corrosion pits were connected to form a large dimple-like area. The HA solution and the porous structure of sand jointly affect the electrochemical corrosion of Q235 steel.

Neural Network Model Based on Branch Architecture for the Quality Assurance of Volumetric Modulated Arc Therapy.

Radiation therapy relies on quality assurance (QA) to verify dose delivery accuracy. However, current QA methods suffer from operation lag as well as inaccurate performance. Hence, to address these shortcomings, this paper proposes a QA neural network model based on branch architecture, which is based on the analysis of the category features of the QA complexity metrics. The designed branch network focuses on category features, which effectively improves the feature extraction capability for complexity metrics. The branch features extracted by the model are fused to predict the GPR for more accurate QA. The performance of the proposed method was validated on the collected dataset. The experiments show that the prediction performance of the model outperforms other QA methods; the average prediction errors for the test set are 2.12% (2%/2 mm), 1.69% (3%/2 mm), and 1.30% (3%/3 mm). Moreover, the results indicate that two-thirds of the validation samples' model predictions perform better than the clinical evaluation results, suggesting that the proposed model can assist physicists in the clinic.

Branch architecture quantification of large-scale coniferous forest plots using UAV-LiDAR data

Branch architecture plays an important role in forest physical and ecological processes, greatly affecting forest spatial structure and the accumulation, production and distribution of organic carbon. Very few studies have quantified the branch architecture of large-scale forest plots, due to the lack of high-resolution large-scale three-dimensional data. The emergence of unmanned aerial vehicle-light detecting and ranging (UAV-LiDAR) provides great potential to overcome this limitation. However, due to insufficient quality of UAV-LiDAR data for branch reconstruction, existing algorithms remain tremendously challenging. We propose an effective branch reconstruction algorithm for UAV-LiDAR data to quantify branch architecture. First, individual branches are extracted using a region growth method that is guided by the branch growth direction and local smoothness constraint. Second, incorrect branches are eliminated based on three pieces of branch features, i.e., specific angles between branches at the same whorl, specific height differences between branches at different whorls, and the growth pattern of branches from the stem outward, reaching maximum distances at tips. Finally, branches are reconstructed using polynomial fitting, and branch architecture parameters are extracted based on branch models. The proposed algorithm simplifies branch reconstruction by skipping the separation of photosynthetic and non-photosynthetic components. It also adapts well to UAV-LiDAR point clouds, generating more realistic reconstructions. The algorithm successfully identified non-photosynthetic components in experiments involving 240 trees, including Scots pine, Norway spruce, and Radiata pine. The average overall accuracy for these three species was 0.88, 0.76, and 0.74, respectively. The proposed algorithm was tested for branch reconstruction using UAV-LiDAR data from a two-hectare Larix principis-rupprechtii plot. The accuracy of branch identification and parameter extraction accuracy were evaluated branch by branch based on the individual branches manually identified in terrestrial laser scanning data. Results showed the F-score of branch and stem identification was 0.58 and 1. The relative RMSE of branch length and angle was 36.87% and 18.3%, and ones of stem length and diameter were 1.46% and 6.16%. The proposed algorithm outperformed the well-known reconstruction algorithms, including TreeQSM, AdTree and Laplacian-based algorithms.

Statistical analysis on branching characteristics of positive streamer discharges in N2–O2 mixtures

Streamers are fast-propagating ionization channels that can usually branch and form complex tree-like structures in dielectric media. In this paper, we perform experiments on positive streamers in different N2–O2 mixtures under varying conditions including voltage, pressure, and electrode geometry, with at least 125 discharge images captured for each condition. We present a statistical analysis on streamer branching characteristics from 3D models that are reconstructed by stereoscopic stroboscopic images and our dedicated semi-automatic 3D reconstruction method.We found that by varying the concentration of O2, the morphology and branching characteristics are greatly changed. Specifically, the average branching angle decrease significantly from 90∘ in air to 66∘ in 1% O2, suggesting that photoionization plays an important role in streamer branching. The branching angles in our work are generally larger than previously reported results due to the resolved 3D structures of discharges by our method. A linear relation between the streamer diameter ratio and the branching direction difference of two daughter branches is found, which intersects the vertical axis almost at unity. It is also found that the average branching angles, streamer velocities and diameters increase as the voltage increases. This is again attributed to stronger photoionization effect under higher voltages. The velocities and diameters are similar at different pressures but at the same reduced electric field. The average branching angle decreases from 90∘ at 133 mbar to 79∘ at 200 mbar. This suggests that stochastic fluctuations become dominant over photoionization effect at higher pressures.

Quantitative grain size estimation on airless bodies from the negative polarization branch

This work explores characteristics of the negative polarization branch (NPB), which occurs in scattered light from rough surfaces, with particular focus on the effects of fine particles. Factors such as albedo, compression, roughness, and the refractive index are considered to determine their influence on the NPB. This study compiles experimental data and lunar observations to derive insights from a wide array of literature. Employing our proposed methodology, we estimate the representative grain sizes on the lunar surface to be D ~ 1–2 µm, with D ≲ 2–4 µm, consistent with observed grain size frequency distributions in laboratory settings for lunar fines. Considering Mars, we propose that the finest particles are likely lacking (D ≫ 10 µm), which matches previous estimations. This study highlights the potential of multiwavelength, particularly near-infrared, polarimetry for precisely gauging small particles on airless celestial bodies. The conclusions provided here extend to cross-validation with grain sizes derived from thermal modeling, asteroid taxonomic classification, and regolith evolution studies.

MA-DBFAN: multiple-attention-based dual branch feature aggregation network for aerial image semantic segmentation

MA-DBFAN: multiple-attention-based dual branch feature aggregation network for aerial image semantic segmentation

辊式枝条捡拾机构运动学仿真与试验分析

Apple tree branches have the physical characteristics of high cellulose content and high elasticity, and the use of traditional soft straw pickers will miss a large number of branches. It is necessary to design a picking mechanism that adapts to the physical characteristics of fruit tree branches. In the treatment of branches in modern orchards, the picking mechanism is an important part of the picking device. The success rate of picking directly affects the processing performance of the whole machine. To improve the picking rate, the roller branch picking mechanism is studied. The trajectory of the roller picking and the stress state of the branches are analyzed, and five main factors affecting the picking effect are obtained, i.e. the position relationship between the rotation center of the picking roller and the feeding roller, inclination angle of the steel teeth, the effective working length, the speed and the forward speed of the machine. A mathematical model is established to obtain the static and dynamic motion trajectories of the roller picking mechanism are obtained by using Matlab. Taking the analysis results of influencing factors as the optimization goal, the picking trajectory of the mechanism is simulated to obtain a set of non-inferior solutions. A roller branch picker is manufactured according to the parameter values and tested in the field, and the picking rate can reach 91%.

A Three-branch Jointed Feature and Topology Decoder guided by game-theoretic interactions for temporomandibular joint segmentation

Segmentation of the temporomandibular joint (TMJ) disc and condyle from magnetic resonance imaging (MRI) is a crucial task in TMJ internal derangement research. The automatic segmentation of the disc structure presents challenges due to its intricate and variable shapes, low contrast, and unclear boundaries. Existing TMJ segmentation methods often overlook spatial and channel information in features and neglect overall topological considerations, with few studies exploring the interaction between segmentation and topology preservation. To address these challenges, we propose a Three-Branch Jointed Feature and Topology Decoder (TFTD) for the segmentation of TMJ disc and condyle in MRI. This structure effectively preserves the topological information of the disc structure and enhances features. We introduce a cross-dimensional spatial and channel attention mechanism (SCIA) to enhance features. This mechanism captures spatial, channel, and cross-dimensional information of the decoded features, leading to improved segmentation performance. Moreover, we explore the interaction between topology preservation and segmentation from the perspective of game theory. Based on this interaction, we design the Joint Loss Function (JLF) to fully leverage the features of segmentation, topology preservation, and joint interaction branches. Results on the TMJ MRI dataset demonstrate the superior performance of our TFTD compared to existing methods.

Real-time semantic segmentation based on BiSeNetV2 for wild road

Abstract State-of-the-art segmentation models have shown great performance in structured road segmentation. However, these models are not suitable for the wild roads, which are highly unstructured. To tackle the problem of real-time semantic segmentation of wild roads, we propose a Multi-Information Concatenate Network based on BiSeNetV2 and construct a segmentation dataset Dalle Molle institute for artificial intelligence feature segmentation (IDSIAFS) based on Dalle Molle institute for artificial intelligence. The proposed model removes structural redundancy and optimizes the semantic branch based on BiSeNetV2. Moreover, the Dual-Path Semantic Inference Layer (TPSIL) reduces computation by designing the channel dimension of the semantic branch feature map and aggregates feature maps of different depths. Finally, the segmentation results are achieved by fusing both shallow detail information and deep semantic information. Experiments on the IDSIAFS dataset demonstrate that our proposed model achieves an 89.5% Intersection over Union. The comparative experiments on Cityscapes and India driving dataset benchmarks show that proposed model achieves good inference accuracy and faster inference speed.

Modelling and numerical simulation of a concentrated mass-based branch vibration

To investigate the variation patterns of spectral characteristics of main branches in fruit trees due to uneven distribution of growth, pruning, and fruit quality, as well as to determine the optimal fruit vibration harvesting, a vibration differential model of tree branches was constructed using the concentrated mass method. A three-dimensional model of the fruit tree was built using finite element software. The spectral characteristics of each branch were obtained using the linear sweep frequency method. The method of changing the mass of each branch was employed to simulate the variation in branch mass. The frequency of occurrence, mean acceleration, and coefficient of variation of the inherent frequencies were used as evaluation indicators. The results revealed that when the vibration frequency of the fruit tree was at the maximum peak frequency in the tree trunk spectrum, the frequency of occurrence and mean acceleration were optimal. And the coefficient of variation of branch acceleration was less than 1, indicating a moderate dispersion. Additionally, reducing the branch mass resulted in an increase in the maximum peak frequency of the tree trunk spectrum. Therefore, the growth, pruning, and uneven distribution of the branches in fruit trees can alter the spectral characteristics. When harvesting fruit by vibration, selecting the maximum peak frequency in the trunk vibration spectrum as the excitation force frequency yields the best fruit detachment.

Anatomical Observation and Clinical Significance of the Medial Branch of the Lumbar Dorsal Rami.

Anatomical study. This study aimed to elaborate on the anatomical characteristics of the medial branch of the lumbar dorsal rami and to discuss its possible clinical significance. Radiofrequency ablation targeting the medial branch of the lumbar dorsal rami has been increasingly used in the clinical management of facetogenic low back pain (FLBP). Nonetheless, attention is also being given to complications such as atrophy of the lumbar soft tissues and muscles. Therefore, a more detailed understanding of the innervation pattern on the facet joint may improve the precision of nerve ablation therapy for FLBP. An anatomical study of eight human specimens was carried out. The anatomic characteristics of the medial branch were observed and recorded. The medial branch originates from the lumbar dorsal rami, running close to the root of the posterolateral side of the superior articular process of the inferior cone. When passed through the mamillo-accessory ligament, it turns direction to the medial and caudal side, running in the multifidus muscle. In our study, each medial branch sent out two to five branches along the way. All the medial branches in L1-L4 gave off one to two small branches when crossing the facet joint and innervated the joint of the lower segment. Nineteen medial branches (23.75%) gave off recurrent branches to innervate the joint at the upper segment. The anatomical features of the medial branch remain similar in each lumbar segment. There are two types of joint branches, including the articular fibers that emanate from the medial branch as it runs along the medial border of the facet joint and the recurrent branch from the medial branch that innervates the upper facet joint. Moreover, an anastomotic branch was found in the medial branches between different segments.

Optimized Design of Robotic Arm for Tomato Branch Pruning in Greenhouses

Aiming at the robotic pruning of tomatoes in greenhouses, a new PRRPR configuration robotic arm consisting of two prismatic (P) joints and three revolute (R) joints was designed to locate the end effector to handle randomly growing branches with an appropriate posture. In view of the various spatial posture of the branches, drawing on the skill of manual pruning operation, we propose a description method of the optimal operation posture of the pruning end effector, proposing a method of solving the inverse kinematics of the pruning arm based on the multi-objective optimization algorithm. According to the spatial distribution characteristics of the tomato branches along the main stem, the robotic arm structure is compact and the reachable space is maximized as the objective function, and a method of optimizing the key geometric parameters of the robotic arm is proposed. The optimal maximum length of the arm’s horizontal slide joint was determined to be 953.149 mm and the extension maximum length of its telescopic joint was 632.320 mm. The verification test of the optimal structural parameter showed that the optimized robotic arm could reach more than 89.94% of the branches in the pruning target area with a posture that meets the pruning requirements. This study is supposed to provide technical support for the development of a tomato pruning robot.

Multiple Branch Deep Neural Network and Feature Fusion Model for Underwater Image Enhancement

Underwater imaging faces formidable challenges due to light absorption, scattering, and restricted visibility, demanding sophisticated enhancement methods. This research presents a novel Multiple Branch Deep Neural Network and Feature Fusion (MB-DNN-FF) Model tailored specifically for Underwater Images Enhancement (UWIE), with a focus on its application to the UFO120 dataset. Driven by the limitations of existing techniques, our model harnesses the potential of Deep Learning (DL) and Feature Fusion (FF) to effectively address the intricate complexities present in underwater environments. The innovative architecture incorporates multiple branches, each strategically designed to tackle distinct challenges such as contrast degradation, limited visibility, and color distortion. Central to our model is feature fusion, a critical aspect that harmoniously integrates information from diverse branches, thereby enhancing overall image quality. The training and optimization processes are thoroughly detailed, encompassing unique strategies and loss functions fine-tuned for the nuances of UWIE, with emphasis on the characteristics of the UFO120 dataset. Experimental evaluations leverage the comprehensive UFO120 dataset, employing established performance metrics to quantitatively assess the efficacy of our model. Results exhibit substantial improvements over baseline models and state-of-the-art methods, showcasing the effectiveness and versatility of the proposed multiple branch model, particularly on the UFO120 dataset. The discussion interprets these findings in the context of underwater imaging challenges, highlighting the model's effectiveness and outlining potential applications. This research contributes a valuable asset to the area of UWIE, offering a nuanced and potent solution through the integration of multiple branches and feature fusion, validated on the UFO120 dataset. The conclusions underscore the significance of the MB-DNN-FF in advancing the state-of-the-art in UWIE, opening avenues for future research and practical applications in marine sciences, surveillance, and exploration.

Diverse branch feature refinement network for efficient multi‐scale super‐resolution

AbstractDespite the existence of various super‐resolution (SR) methods, most of them focus on designing models for specific upscaling factors rather than fully exploiting inter‐scale correlation to improve efficiency. In contrast, multi‐scale SR methods can effectively reduce the redundancy of network parameters by aggregating the feature extraction processes corresponding to multiple scales into a unified process. The aim of this study is to enhance the compactness and efficiency of the SR model. Thus, an efficient multi‐scale SR method called the diverse branch feature refinement network (DBFRN) is proposed. By decoupling the training process and inference process based on the idea of structural re‐parameterization, multi‐branch topology is adopted to enrich multi‐scale learning and merge branches to achieve efficient inference with equivalent effects. Specifically, two re‐parameterization strategies are designed and two corresponding feature refinement blocks for different feature levels in multi‐scale SR network. Extensive experiments demonstrate that the proposed multi‐scale SR method is effective and efficient, and it can outperform advanced single‐scale methods in terms of quantity and quality.

Face Forgery Detection with Long-Range Noise Features and Multilevel Frequency-Aware Clues

The widespread dissemination of high-fidelity fake faces created by face forgery techniques has caused serious trust concerns and ethical issues in modern society. Consequently, face forgery detection has emerged as a prominent topic of research to prevent technology abuse. Although, most existing face forgery detectors demonstrate success when evaluating high-quality faces under intra-dataset scenarios, they often overfit manipulation-specific artifacts and lack robustness to postprocessing operations. In this work, we design an innovative dual-branch collaboration framework that leverages the strengths of the transformer and CNN to thoroughly dig into the multimodal forgery artifacts from both a global and local perspective. Specifically, a novel adaptive noise trace enhancement module (ANTEM) is proposed to remove high-level face content while amplifying more generalized forgery artifacts in the noise domain. Then, the transformer-based branch can track long-range noise features. Meanwhile, considering that subtle forgery artifacts could be described in the frequency domain even in a compression scenario, a multilevel frequency-aware module (MFAM) is developed and further applied to the CNN-based branch to extract complementary frequency-aware clues. Besides, we incorporate a collaboration strategy involving cross-entropy loss and single center loss to enhance the learning of more generalized representations by optimizing the fusion features of the dual branch. Extensive experiments on various benchmark datasets substantiate the superior generalization and robustness of our framework when compared to the competing approaches.

Simulation Study of the Effect of Microscopic Disturbances on the Propagation of Initial Streamer and Branching Characteristics in Transformer Oil

Simulation Study of the Effect of Microscopic Disturbances on the Propagation of Initial Streamer and Branching Characteristics in Transformer Oil

Two new species of Callophyllis (Rhodophyta, Kallymeniaceae) from the Russian Pacific coast

ABSTRACT Seven species of Callophyllis have been known off the Pacific coast of Russia; hovewer, molecular data have been obtained only for three species. In this study we re-examined the genus along the Russian Pacific coast using a comparative morphological study and molecular analyses based on rbcL and nrLSU. Five genetic species were identified on the Russian coast based on phylogenetics and species delimitation (ASAP and p-distance) analyses; while C. beringensis, C. papulosa and C. platyna were outscore of the analyses. The results of the molecular analyses uncovered one undescribed species, which we named C. selivanovae sp. nov. The divergence between this species and other species of the genus varied from 1.16% to 5.66%, while intraspecific divergence in the genus was in a range of 0.00%–0.22%. In phylogenetic trees C. selivanovae was recognized as sister to a diverse clade including C. thompsonii, C. beringensis, C. violacea, C. flabellulata and C. variegata from the Pacific coast of Canada. Callophyllis selivanovae from the southeastern coast of Kamchatka is morphologically close to C. beringensis, described from St. Paul Island (Bering Sea); the two species differ in features of branching, shape and size of the terminal branches. We propose a new name, C. perestenkoae sp. nov., for the algae previously listed in the Russian flora as ‘C. flabellata’. Pacific specimens assigned to C. perestenkoae differ from C. flabellata from the type locality (Atlantic, France) in having irregular branching, thicker apical branches, and smaller cystocarps. We also filled in the gaps in the description of C. radula for which procarp and tetrasporangia are described herein for the first time.

A permeability model for the fractal tree-like fracture network with self-affine surface roughness in shale gas reservoirs

The complex natural fracture network with self-affine rough surface and branching characteristics significantly impacts the gas transport in shale gas reservoirs. However, its effects on the permeability have not been studied so far. This study proposes an analytical permeability model for the fractal tree-like fracture network with self-affine surface roughness and branching characteristics. Firstly, the self-affine rough profiles of fracture surface are generated at different fractal dimensions by the Weierstrass–Mandelbrot function and a rough fractal tree-like fracture network is constructed with these surface profiles and branching characteristics. Then, an analytical permeability model is proposed to consider the effects of fracture surface roughness and tree-like branching characteristics on gas flow. This analytical model is verified by numerical simulations. Finally, the velocity distribution of the fracture network and the sensitivity of its structure parameters are analyzed. It is found that eddy flow is more easily formed on rougher fracture surfaces with larger fractal dimension when their fracture aperture is at millimeter scale. The eddy flow disappears when the fracture aperture is at micron scale. Bigger gas flow resistance and more energy loss are observed for smaller fracture aperture and rougher fracture surface. The gas velocity in rough fractures decreases by 60% at micron scale, but decreases by 50% at millimeter scale. Gas flow resistance also increases with the increase of branch angle, branch level and length ratio, but decreases with aperture ratio. As a result, permeability decreases with fractal dimension, branch angle, branch level and length ratio, but increases with aperture ratio.

“If less is more, how you keeping score?” Outlines of a life cycle assessment method to assess sufficiency

It is increasingly clear that reaching environmental sustainability requires not only efficiency (reduced environmental impact per functionality) but also sufficiency measures (reduced environmental impact through reduced or changed functionality). Life cycle assessment (LCA) is a widely used tool to study environmental impacts related to consumption. However, because of the LCA convention of only comparing alternative products with equal functionality, it is currently inept as a method for assessing the environmental impacts of sufficiency measures. Against this background, this short paper aims to stimulate a discussion on how sufficiency measures can be assessed with LCA methodology. By analyzing the very few LCAs of explicit sufficiency measures in terms of the components of a functional unit (what function is provided, how much, for how long, and how well) features of a potential new branch of LCA methodology are outlined, called Sufficiency LCA. In Sufficiency LCA, product alternatives need to be similar enough so that the what component of the functional unit can be equal, while the other components, how much, how long, and how well, are allowed to be non-equal. Thus, a key feature of Sufficiency LCA concerns functional non-equivalence of compared product alternatives, which is not allowed or neglected in conventional LCA, but which could be allowed, acknowledged and quantified in Sufficiency LCA. Developing Sufficiency LCA could be critical considering that sufficiency measures are expected to be required, and that LCA is expected to be serviceable as decision-making support, in the transition toward environmental sustainability.