Space Scales Research Articles

Ecological network resilience evaluation and ecological strategic space identification based on complex network theory: A case study of Nanjing city

Constructing a resilient ecological network (EN) and identifying critical strategic nodes and corridors within the EN, stands as a pivotal approach toward achieving a harmonious equilibrium between regional development and ecological conservation. It is imperative to expand the perspective to encompass the holistic resilience of the EN, thus identifying and safeguarding ecologically strategic nodes and corridors that play pivotal roles throughout the entire network. Therefore, this study takes Nanjing City as a case study and establishes a comprehensive EN resilience assessment framework based on resilience theory and complex network theory, grounded in a foundation of multidimensional indicators. Building upon this, the research develops the ‘regional network simulation - ecological spatial analysis - strategic spatial identification’ investigative framework. The results show that a core EN structure centered around green spaces, rivers, lakes, and similar features has taken shape, encompassing a total of 39 ecological nodes and 69 ecological corridors. Examining from six perspectives, connectivity, integration, complexity, centrality, efficiency, and substitutability, and their integrated assessment, this study analyzed the impact of single and sequential failures in different EN component spaces on the overall resilience of the EN. The study aimed to identify the component space that significantly contributes to the network's resilience. As a result, the strategic space of the EN was divided into three levels. The ecological source areas 1, 2, 7, and 34, along with ecological corridors 1–34, 1–4, 4–11, 19–34, 18–19, and 27–39, emerge as the primary strategic spaces within the study region. Previous research primarily emphasized the individual characteristics of ecological spaces. However, this study adopts a systemic perspective rooted in resilience theory and complex network theory to meticulously explore the pivotal impact of specific ecological spaces on the overall resilience of the ecological system network. Moreover, it amalgamates considerations of both the significance and scale of ecological spaces, conducting a comprehensive assessment of their combined influence on the overall EN resilience. This approach not only aids in identifying and preserving strategic ecological nodes and corridors but also contributes to evaluating, planning, and restoring regional EN resilience. This progression plays a crucial role in establishing an equilibrium between regional advancement and ecological conservation.

Regression generative adversarial network based on bounded losses for prediction of free calcium oxide in cement clinker

The data imbalance problem caused by multi-time scales phenomenon affects the prediction accuracy, validity and robustness of free calcium oxide (fCaO) content in cement clinker calcination process. Focusing on this problem, we propose an regression generative adversarial network model to predict fCaO content, which contains a generator, discriminator and predictor. Generator and discriminator are designed as bounded loss generative adversarial network to solve mode collapse problem and improve the stability. They learn actual data features in adversarial learning style and produce fake data to enlarge the scale and feature space of actual data to train predictor and finally achieve the prediction of fCaO content, which overcomes the problem of data imbalance. For performance assessment, we visually evaluate the validity of generated data from the perspective of univariate distribution and multivariate joint distribution and invent sequence change tendency consistency index (TCI) to evaluate the robustness of fCaO content prediction. Experiments implemented by cement production data demonstrate that the proposed model has advantages in accuracy, availability and robustness in fCaO content prediction, especially TCI is higher 22.69 percentage points than that of without data augmentation.

DV Emotion Net: An Integrated Multimodal Approach for Emotion Recognition

This study introduces a novel approach to emotion recognition by amalgamating information from heterogeneous modalities, specifically audio and video. We employed techniques such as energy, zero crossing rate, and Mel-Frequency Cepstral Coefficients (MFCC) for audio feature extraction, which showed promising results. For video feature extraction, spatialtemporal Gaussian kernels were used to organize video frames within a linear scale space, followed by the application of a Gaussian-weighted function to the second momentum matrix for further feature extraction. The Multimodal Feature Aggregation (MFA) fusion method was employed to unify audio and video features, resulting in a comprehensive dataset. Evaluation through the Fusion of Emotion Recognition Convolutional Neural Network (FERCNN) model, supported by the "TPU VM v3-8" accelerator TPU is a Tensor Processing Unit, showcased notable performance improvements. Using the RAVDESS and CREMAD datasets, accuracies of 94.66%, 95.82%, and 94.36% in the RAVDESS dataset and 79.45%, 96.62%, and 70.14% in the CREMAD dataset for audio, video, and multimodal modalities, respectively, were achieved. These outcomes surpass the capabilities of existing multimodal systems, underscoring the efficacy of our proposed approach. Emotion recognition, particularly through multimodal means, plays a critical role in various domains, including human-computer interfaces, healthcare, legal proceedings, and entertainment. Fusing Audio and Video Modalities to Elevate Human-Computer Interaction and Intelligent System Performance is essential for enhancing communication within these domains. The proposed model is termed "DualVision EmotionNet: DV EmotionNet".

A Temporal Variable-Scale Clustering Method on Feature Identification for Policy Public-Opinion Management

The development of various digital social network platforms has caused public opinion to play an increasingly important role in the policy making process. However, due to the fact that public opinion hotspots usually change rapidly (such as the phenomenon of public opinion inversion), both the behaviour feature and demand feature of netizens included in the public opinion often vary over time. Therefore, this paper focuses on the feature identification problem of public opinion simultaneously considering the multiple observation time intervals and key time points, in order to support the management of policy-focused online public opinion. According to the variable-scale data analysis theory, the temporal scale space model is established to describe candidate temporal observation scales, which are organized following the time points of relevant policy promulgation (policy time points). After proposing the multi-scale temporal data model, a temporal variable-scale clustering method (T-VSC) is put forward. Compared to the traditional numerical variable-scale clustering method, the proposed T-VSC enables to combine the subjective attention of decision-makers and objective timeliness of public opinion data together during the scale transformation process. The case study collects 48552 raw public opinion data on the double-reduction education policy from Sina Weibo platform during Jan 2023 to Nov 2023. Experimental results indicate that the proposed T-VSC method could divide netizens that participate in the dissemination of policy-focused public opinion into clusters with low behavioural granularity deviation on the satisfied observation time scales, and identify the differentiated demand feature of each netizen cluster at policy time points, which could be applied to build the timely and efficient digital public dialogue mechanism.

Improved Demons algorithm for non-rigid medical image alignment

Abstract Medical image alignment is an important research field in medical image processing, which is widely used in clinical diagnosis and treatment, such as surgical navigation, lesion tracking, and treatment evaluation. In this paper, an improved algorithm combining the Demons algorithm and SIFT algorithm is proposed, which uses the SIFT algorithm to represent the feature points in non-rigid medical images as a scale space sequence and normalize the descriptors in the scale space sequence. Then, the two-way alignment strategy and multi-resolution strategy are introduced to improve the accuracy of Demons algorithm in the alignment of non-rigid medical images with complex deformation. The study shows that the improved Demons algorithm can achieve better alignment results when the weights of the feature matching terms are taken as −1 and 1, which makes the improved Demons algorithm with the addition of SIFT feature terms perform optimally. Alignment simulation experiments found that the MSE value of this paper’s improved algorithm is only 0.077. The alignment effect of non-rigid medical images is much better than the comparison algorithm and can maintain a shorter running time. The algorithm in this paper can effectively realize the non-rigid alignment of medical images, which provides a reference method for medical diagnosis and the effective formulation of treatment plans.

Exploration on Data Collection and Analysis System Based on Integrated SIFT Algorithm

With the development of applications related to image processing technology, the target requirements of data acquisition and analysis systems are constantly being optimized. Research on data acquisition and analysis based on the integrated SIFT (Scale Invariant Feature Transform) algorithm is becoming increasingly important. The construction of a data collection and analysis system focuses on ensuring efficient and accurate data collection and analysis to provide valuable insights and decision support. Key priorities include determining data requirements and objectives, designing appropriate data collection methods and tools, establishing reliable data storage and management systems, developing effective data analysis algorithms and models, and ensuring data security and privacy protection. This article analyzed the theoretical analysis of feature point extraction algorithm and the process steps and application of integrated SIFT algorithm. With the help of dimensionality reduction processing, the SIFT algorithm was improved and optimized. Combined with the scale space calculation formula, The conclusion is as follows: On the basis of image processing, the data collection and analysis system using the improved integrated SIFT algorithm on the five selected image file samples has improved the accuracy of feature point matching, with a comprehensive average improvement of 7.6%. The efficiency of feature point extraction has also been improved, with a comprehensive average improvement of about 8%. This indicated that the data collection and analysis system based on the improved integrated SIFT algorithm has good practical application results in feature point matching and extraction.

Accelerating Hyperbolic t-SNE.

The need to understand the structure of hierarchical or high-dimensional data is present in a variety of fields. Hyperbolic spaces have proven to be an important tool for embedding computations and analysis tasks as their non-linear nature lends itself well to tree or graph data. Subsequently, they have also been used in the visualization of high-dimensional data, where they exhibit increased embedding performance. However, none of the existing dimensionality reduction methods for embedding into hyperbolic spaces scale well with the size of the input data. That is because the embeddings are computed via iterative optimization schemes and the computation cost of every iteration is quadratic in the size of the input. Furthermore, due to the non-linear nature of hyperbolic spaces, euclidean acceleration structures cannot directly be translated to the hyperbolic setting. This article introduces the first acceleration structure for hyperbolic embeddings, building upon a polar quadtree. We compare our approach with existing methods and demonstrate that it computes embeddings of similar quality in significantly less time. Implementation and scripts for the experiments can be found at https://graphics.tudelft.nl/accelerating-hyperbolic-tsne.

Identification of reservoir types in deep carbonates based on mixed-kernel machine learning using geophysical logging data

Identification of reservoir types in deep carbonates has always been a great challenge due to complex logging responses caused by the heterogeneous scale and distribution of storage spaces. Traditional cross-plot analysis and empirical formula methods for identifying reservoir types using geophysical logging data have high uncertainty and low efficiency, which cannot accurately reflect the nonlinear relationship between reservoir types and logging data. Recently, the kernel Fisher discriminant analysis (KFD), a kernel-based machine learning technique, attracts attention in many fields because of its strong nonlinear processing ability. However, the overall performance of KFD model may be limited as a single kernel function cannot simultaneously extrapolate and interpolate well, especially for highly complex data cases. To address this issue, in this study, a mixed kernel Fisher discriminant analysis (MKFD) model was established and applied to identify reservoir types of the deep Sinian carbonates in central Sichuan Basin, China. The MKFD model was trained and tested with 453 datasets from 7 coring wells, utilizing GR, CAL, DEN, AC, CNL and RT logs as input variables. The particle swarm optimization (PSO) was adopted for hyper-parameter optimization of MKFD model. To evaluate the model performance, prediction results of MKFD were compared with those of basic-kernel based KFD, RF and SVM models. Subsequently, the built MKFD model was applied in a blind well test, and a variable importance analysis was conducted. The comparison and blind test results demonstrated that MKFD outperformed traditional KFD, RF and SVM in the identification of reservoir types, which provided higher accuracy and stronger generalization. The MKFD can therefore be a reliable method for identifying reservoir types of deep carbonates.

Research on Aging Adaptation of Urban Residential Environment Design in the Era of Artificial Intelligence

Abstract Under the background of aging, how to make the elderly live comfortably and improve the quality of life have all become the main problems solved by the current society. Based on the relevant theoretical foundation, this paper constructs a aging adaptation design model of the urban residential environment. Principal component analysis and factor analysis are employed to simplify the data structure of living environment design and decrease the complexity of data analysis. Regression analysis and structural equations are combined to investigate the relationship between the living environment and age appropriateness. PLS regression analysis was used to solve the external weights or factor loadings to obtain the estimates of the latent variables and the path coefficients among the latent variables. To demonstrate the reasonableness of the factors influencing the quality of the environment, the reliability and validity of the perceived quality are analyzed. Combining the basic attributes and needs of the elderly is the basis of proposing an aging-friendly environment design strategy. The results show that In terms of architectural spatial perception, the master bedroom space scale exceeds 3.92m × 4.61m, which is a relatively optimal choice that can simultaneously meet the diversified needs of the family’s living behavior at different stages. In terms of road accessibility and greening perception, the width of the age-appropriate walkway can vary depending on different locations and the unit time flow of people. In the era of artificial intelligence, the design of the aging-adapted living environment should fully consider the physiological characteristics of the elderly and formulate more suitable living data for the elderly.

‘Paleofloodscapes’: Application of sediment source fingerprinting to track flood regime change over space and time at the Peace-Athabasca Delta, Canada

Deltas are hydrologically dynamic landscapes where river floodwaters create a mosaic of productive ecosystems that provide important services. The flood regime, however, is vulnerable to upstream anthropogenic activities, climate change and geomorphic processes. Deciphering the roles of multiple potential stressors on flood regime change is critical for developing appropriate adaptive and mitigative strategies but requires knowledge of hydrological variability at broader scales of space and time than is typically available from instrumental and observational records. At the globally recognized Peace-Athabasca Delta (Canada), the timing, magnitude and causes of reduced flooding and drawdown of perched basin water levels remain an intense focus of investigation. Here we employ novel ‘paleofloodscapes’, generated from geospatial interpolation of Bayesian mixing model fingerprinting of sediment elemental concentrations, to quantify variation in the delta's flood regime during the past ~140 years. Results reveal that flooding of the delta began to decline several decades before hydroelectric regulation of Peace River flow, not coincident with it, and the influence of floodwaters from the unregulated Athabasca River has declined more than the regulated Peace River. A key discovery is that widespread flooding of perched basins occurs when ice-jam events on the river(s) coincide with a relatively high water-plane in the delta's open-drainage network. Without knowledge of open-drainage water levels, inferred change to the flood regime of perched basins may be inaccurate when derived solely from analyses of Peace River hydrometric data and climatic records. The paleofloodscapes illustrate that rising sediment delivery caused by a natural river avulsion in 1982 may undermine the intended purpose of a proposed weir installation. The most recent paleofloodscape, developed from lake surface sediment sampling shortly after widespread flooding, demonstrates the value of the approach as a landscape hydrological monitoring tool, and is readily transferrable to other floodplains to track flood regime change.

Enhancing medical image object detection with collaborative multi-agent deep Q-networks and multi-scale representation

Object detection holds a crucial role in medical diagnostics. Tasks like organ segmentation and malignancy diagnosis typically necessitate preliminary localization of corresponding anatomical structures. Precise positioning ensures that only pertinent regions require processing, leading to a potential reduction in computational and storage demands. Conventional image detection approaches necessitate numerous candidate boxes, resulting in redundant computations. Developing techniques capable of accurately detecting medical image objects without reliance on candidate boxes holds substantial practical significance. This paper introduces a 2D method for detecting medical image objects, which leverages multi-agent deep Q-network reinforcement learning and a multi-scale image representation. The method constructs a collaborative environment for multiple agents. These agents individually govern the upper-right corner and lower-left corner positions of the object detection frame, progressively converging toward the actual endpoint through iterative interactions. To expedite the detection process, a multi-scale image representation technique is employed. This method segments the process into three scales. Initially, within the coarse-scale space, the agent approximates the region containing the true endpoint, subsequently executing oscillatory movements. Progressively, it refines its approach within the fine-scale space, advancing toward the genuine endpoint with smaller iterative steps. The detection results demonstrate that collaborative detection among agents yields a 2.45%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} higher intersection over union compared to non-collaborative detection. Agents exhibit varying step sizes and fields of view in different scale spaces, leading to a reduction in detection time by 0.12 s compared to single-scale comparison. Experimental outcomes demonstrate the superiority of the medical image target detection method proposed in this study over prevailing mainstream detection algorithms.

A survey of meta-heuristic algorithms in optimization of space scale expansion

Optimization problem of space scale expansion widely exists in practical applications, such as transportation, logistics, scheduling, social networks, etc. According to different expansion directions, the problem of space scale expansion can be divided into three categories: expansion of decision space, expansion of objective space and simultaneous expansion of decision space and objective space. These three types of problems correspond to large-scale global optimization problem, multi/many-objective optimization problem, and large-scale multi/many-objective optimization problem, respectively. Driven by the above problems, meta-heuristic algorithms (MHAs) with scalable characteristics have received extensive attention in this field. This paper summarizes the research progress of MHAs for space scale expansion optimization from three perspectives. Starting from the key difficulties of the optimization problem, the challenges brought by the expansion of the space scale to the existing MHAs are emphatically analyzed. From the perspective of methodology, the optimization methods of MHAs are divided into three modules: simplify problem structure, improve algorithm performance and expand application fields. Based on the review of performance evaluation benchmark problems, the simulation degree of various test suites for different practical application problems is summarized. In addition, some remaining challenges and future research directions on optimization of space scale expansion are discussed and analyzed.

No evidence for chunking in spatial memory of route experience.

Spatial memory is important for supporting the successful completion of everyday activities and is a particularly vulnerable domain in late life. Grouping items together in memory, or chunking, can improve spatial memory performance. In memory for desktop scale spaces and well-learned large-scale environments, error patterns suggest that information is chunked in memory. However, the chunking mechanisms involved in learning new large-scale, navigable environments are poorly understood. In five experiments, two of which included young and older adult samples, participants watched movies depicting routes through building-sized environments while attempting to remember the locations of cued objects. We tested memory for the cued objects with virtual pointing, distance estimation, and map drawing tasks after participants viewed each route. Patterns of error failed to show consistent evidence of chunking in spatial memory across all experiments. One possibility is that chunking in spatial memory relies on visual perceptual grouping mechanisms that are not in play during encoding of large-scale spaces encountered through extended route experiences that do not afford concurrent viewing of target locations. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Asymmetric morphological filter for roughness evaluation of multifunctional surfaces

The scope of multifunctional surfaces in mechanical engineering and instrumentation is constantly expanding. Examples are products with multilayer coatings, products made of composite materials or using additive manufacturing technologies. A feature of multifunctional surfaces is two levels of texture with different parameter values. Various types of filters are used to decomposition and then analyze texture components. Traditionally, for such problems, a robust Gaussian regression filter and a morphological filter are used. The advantage of the morphological filter lies in the lower computational complexity and the ease of removing the shape component from the profile. This research presents generalized analysis of various types of an asymmetric morphological filter based on simulation. The asymmetric filter differs from the standard morphological filter by using different nesting indexes for combinations of morphological opening and closing operations. We have designed a compositional model of profile, which is superposition of two Gaussian distributions with different parameters and waviness. Relative filtering error of the arithmetic mean heights Ra was chosen as evaluation parameter. Based on the Monte Carlo experiments technique, the relative errors of the filters are determined. The main result of the research is algorithm for choosing nesting indexes depending on the type of primary profile. Thus, we give scientifically justified choice of the filter type and its task-specific parameters for applied use. The choice of filter type and two different nesting indexes in accordance with the developed algorithm provide relative error with a coverage interval less 3 % for 95 % coverage probability. The asymmetric morphological filter is effective for scale space analysis of surfaces with significant shape errors and waviness. The results obtained can be used to analyze the tribological properties of multifunctional surfaces of products.

Non-local eddy diffusivity model based on turbulent energy density in scale space

Recently, a non-local eddy diffusivity model for the turbulent scalar flux was proposed to improve the local model and was validated using direct numerical simulation (DNS) of homogeneous isotropic turbulence with an inhomogeneous mean scalar (Hamba, J. Fluid Mech., vol. 950, 2022, A38). The non-local eddy diffusivity was assumed to be proportional to the two-point velocity correlation that was expressed in terms of the energy spectrum. Because the Fourier transform of velocity in the homogeneous directions was used to define the energy spectrum, it is not yet understood whether the proposed model can be applied to inhomogeneous turbulence. Thus, this study aimed to improve the non-local model using the scale-space energy density instead of the energy spectrum. First, the scale-space energy density based on filtered velocities was examined using the DNS data of homogeneous isotropic turbulence to obtain its simple form corresponding to the Kolmogorov energy spectrum. Subsequently, the two-point velocity correlation was expressed in terms of the scale-space energy density. Using these expressions, a new non-local eddy diffusivity model was proposed and validated using the DNS data. The one-dimensional non-local eddy diffusivity obtained from the new model agrees with the DNS value. The temporal behaviour of the three-dimensional non-local eddy diffusivity was improved compared with the previous model. Because the scale-space energy density was already examined in turbulent channel flow, it is expected that the new non-local model can also be applied to inhomogeneous turbulence and is useful for gaining insight into turbulent scalar transport.

Discrete heat conduction equation: Dispersion analysis and continuous limits

The dispersion relation in ω-k space has been derived and analyzed for discrete heat conduction equation (DE). The DE is inherently nonlocal both in time and space and can be used to describe non-Fourier heat transport occurring on ultrashort time and length scales. An important distinction between the DE and the continuum description is that the frequencies and wave numbers available to the discrete system are limited, whereas in the continuum description there are no such limitations. Analytical expressions for the attenuation distance, group and phase velocities have been obtained and analyzed as functions of frequency. In the continuum limit, depending on the basic invariant of the continualization procedure, the dispersion relation for the DE reduces to either dispersion relation for the classical Fourier parabolic equation (PE) or to dispersion relation for the hyperbolic heat equation (HE). However, at the moderate and high frequencies the spectrum of the DE differs significantly from the spectra of the PE and HE. This implies that the continuum-based approaches, including both the PE and HE, unable to describe high-frequency and short-wavelength processes and the DE is preferable. This work provides a relatively simple analytical tool to interpret the transient wave-like behavior of heat transport on ultrashort space and time scales.

Turbulent energy transfers in physical and scale spaces at dissipative length scales

In statistically stationary homogeneous incompressible turbulence, the average energy transfer rate balance which exists at diffusion/dissipation-dominated length scales does not reflect what actually happens locally in space and time. We use a highly resolved direct numerical simulation of forced periodic turbulence to shed some light on the actual fluctuating dynamics which occur at these very small scales and which are rubbed off by averaging. Even though the viscous diffusion in physical space averages to zero and fluctuates less intensely than all other terms (except the energy input rate) in the local (in space–time) two-point energy balance, it fundamentally cannot be neglected. The local unsteadiness and the interspace turbulence transport terms cannot be ignored either in the interscale energy dynamics in spite of the fact that they also average to zero.

A new Meso-Scale coarse-filter indicator for the Canadian boreal forest

Forest management planning and management agencies in Canada have been moving towards an ecosystem-based management (EBM) approach that honours whole ecosystem dynamics over all time and space scales. As part of this evolution, provincial, national, and international agencies have added coarse filter indicators to represent pre-industrial, or ‘natural’ range of variation (NRV) ecosystem conditions as ecologically defendable baselines. The intent was to balance the more traditional species specific (i.e., fine filter) approach to sustainability with a more holistic (i.e., coarse scale) model of ecosystem dynamics. The development and acceptance of coarse filter indicators has been neither linear nor straightforward. One of the more important assumptions inherent in an NRV strategy is that it captures relevant, meaningful patterns at the most appropriate scales in a practical way. To test this assumption, I used a spatially explicit simulation model to compare landscapes created under pre-industrial conditions with those created using four different thresholds of disturbance size commonly used today in boreal Canada. The results suggest that even a 10,000 ha upper size limit create significantly higher levels of homogeneity and fragmentation at intermediate spatial scales relative to pre-industrial landscape patterns. Towards developing a new, more robust coarse filter indicator, the net area burned at four grid sizes over 10 and 20 years was calculated for natural wildfire data from northern Saskatchewan. The results suggest that wildfire tends to cluster at all scales due largely to the influence of large infrequent wildfires. In contrast, data from two forest management areas in Alberta summarized at the same scales confirm that harvesting activity tends to spread out evenly across the landscape. Based on these findings, the NRV data was then refined to capture; 1) the percentage of grid cells where high disturbance levels occur (WHEREs – or WHERE you are) and the proportion where no disturbance occurs (WYNs – or Where You are Not). The WHERE-WYN indicator is unique in that it specifically integrates time as a dimension of landscape dynamics. It is also easily understood and calculated, corresponds directly to management activities, has NRV equivalents, and applicable to most of boreal Canada. Augmenting the current suite of coarse filter indicator with the WHERE-WYN combination addresses a critical gap in our NRV toolkit and will ultimately help create more sustainable landscapes.

AN IMPROVED IMAGE REGISTRATION ALGORITHM FOR THERMAL INFRARED AND PANCHROMATIC IMAGE BASED ON GEOMETRIC STRUCTURAL PROPERTIES

Abstract. In order to improve the image registration accuracy of heterogeneous remote sensing images with large radiation differences, an improved image registration algorithm for thermal infrared and panchromatic images is proposed. This method uses the phase consistency of intensity and direction to construct a geometric structure feature descriptor called the Histogram of Oriented Phase Congruency (HOPC) for image registration. It employs the Curvature Scale Space (CSS) corner detection to concentrate and extract feature points in contour areas, and defines a similarity metric (called HOPCn) based on the Euclidean distance between the descriptors for high-precision heterogeneous images registration. Five sets of panchromatic and thermal infrared images were selected for verification. The results show that the improved algorithm can match the homonymy points around the image contour, and the Correct Matching Rate (CMR) is improved by 2.7% and the Root Mean Square Error (RMSE) is improved by 3.7% compared to the original algorithm. This proves that the proposed method has good robustness under conditions of large radiation differences.

Construction of medical aromatherapy experimental teaching resources based on digital three-dimensional technology

Abstract In this paper, on the basis of the Unity3D engine, image feature points are coarsely extracted, and a quadtree-based division algorithm is applied to filter the optimal FAST corner points. The fast 3D reconstruction technique is constructed through the construction method of nonlinear scale space similar to scale-invariant feature transform (SIFT), which is layer incremented according to the scale level logarithmic layer. The reconstructed 3D virtual teaching laboratory tool is obtained by importing the matched feature points into the model after the diffusion is completed. Finally, the teaching process and teacher-student behavioral data analysis were conducted for TCM and acupuncture students using the medical aromatherapy experimental course “Clinical Experiment of Aromatherapy for Primary Dysmenorrhea” as the teaching objective. The results showed that the maximum value of iFIAS of the experimental group was 100, and the mean value was 79.35, while the maximum value of technical iFIAS of the control group was only 51.32, and the mean value was 21.34, which was a significant difference between the two. It shows that the teaching method improves classroom learning interest and effect. The purpose of this paper is to provide relevant opinions and references for the future development direction of the combination of aromatherapy teaching and 3D virtual reality.