Welcome to Journal of Graphics share: 
Bimonthly, Started in 1980
Administrated: China Association for  Science and Technology
Sponsored: China Graphics Society
Edited and Published: Editorial Board  of Journal of Graphics
Chief Editor: Guoping Wang
Editorial Director: Xiaohong Hou
ISSN 2095-302X
CN 10-1034/T
Current Issue
31 October 2022, Volume 43 Issue 5 Previous Issue   
For Selected: Toggle Thumbnails
Cover
Cover of issue 5, 2022
2022, 43(5): 0. 
Abstract ( 62 )   PDF (1591KB) ( 58 )  
Related Articles | Metrics
Contents
Table of Contents for Issue 5, 2022
2022, 43(5): 1. 
Abstract ( 40 )   PDF (221KB) ( 28 )  
Related Articles | Metrics
Review
A review of the application of illustrative methods in 3D streamline visualization
SHAO Xu-qiang, CHENG Ya , JIN Yi-zhong
2022, 43(5): 753-764.  DOI: 10.11996/JG.j.2095-302X.2022050753
Abstract ( 42 )   PDF (7441KB) ( 21 )  
Streamline visualization is an important method of flow visualization. It can directly represent the structure and flow trend of the flow field. However, when streamline visualization is used in the three-dimensional flow field, inappropriate rendering methods, selection methods, and presentation methods will lead to poor expression ability of visual results, and it is difficult for users to efficiently obtain flow information. In order to fully reflect the research progress of illustrative methods in 3D streamline visualization, this paper systematically reviewed the representative papers at home and abroad over recent ten years ago. First, the related concepts of illustrative visualization methods were introduced, and then the applications of illustrative methods such as visual perception enhancement, visibility management, and focus + context in 3D streamline visualization were summarized and classified, and the advantages and disadvantages of each method are discussed. The illustrative method of visual perception enhancement refers to that when perceiving the world, human beings make full use of all the visual information. Visibility management refers to the improvement of the overall visibility of data by reducing confusion and occlusion through such means as clustering and selective visualization, thus optimizing the visual space. Focus + context emphasizes which part is the area of special interest, that is, focus, and highlights it. For less important areas, namely, context, it is utilized to provide background. Focus + context technology highlights the characteristics of the data rather than the overall structure. Finally, the application of illustrative methods in 3D streamline visualization is summarized and analyzed. The problems and challenges in streamline visualization were presented, and future research directions were prospected. 
Related Articles | Metrics
Review on research of FBS model method 
BAI Zhong-hang, ZHANG Zi-heng, LI Chen-hui, ZHANG Xin-xin , DING Xiao-ying
2022, 43(5): 765-775.  DOI: 10.11996/JG.j.2095-302X.2022050765
Abstract ( 57 )   PDF (615KB) ( 23 )  
The function-behavior-structure (FBS) model has enriched the traditional function-structure (FS) model by introducing behavioral variables (Behavior), and has been widely utilized in the design field. The development and application of the FBS model were reviewed. Firstly, the FBS model was introduced from the definition of FBS model, the proposal and development of the concept of relevant variables, and the optimization and improvement of the FBS model, etc. Secondly, through the analysis of relevant domestic and foreign literature, the research and application of the FBS model were classified. The existing research was mainly concentrated on the development of the FBS model itself, the integration of methods based on the FBS model, and the application of the FBS model mapping mechanism, etc. Finally, for the future research and application of the FBS model, the existing problems of the FBS model were presented and some research suggestions were provided. 
Related Articles | Metrics
Image Processing and Computer Vision
Vehicle target detection based on YOLOv5s fusion SENet  
ZHAO Lu-lu , WANG Xue-ying , ZHANG Yi , ZHANG Mei-yue
2022, 43(5): 776-782.  DOI: 10.11996/JG.j.2095-302X.2022050776
Abstract ( 68 )   PDF (1506KB) ( 57 )  
To address the problem that the vehicle target detection technology of traffic monitoring videos has high rates of false detection and missed detection due to serious vehicle occlusion in traffic congestion periods such as morning and evening peaks, an improved vehicle target detection model based on YOLOv5s network was proposed. The attention mechanism SE module was introduced into the Backbone network, Neck network layer, and Head output of YOLOv5s, respectively, thus enhancing the important features of the vehicle and suppressing the general features. In doing so, the recognition capability of the detection network for the vehicle target was strengthened, and training and tests were performed on the public data set UA-DETRAC and self-built data set. The results show that the three indicators were significantly enhanced compared with the original network, which was suitable for the introduction of the attention mechanism. The evaluation rate, the value, and mean average accuracy were evaluated, and the results showed that compared with the original network, the three indicators were significantly improved, suitable for the introduction of attention mechanisms. To address the imbalance between positive and negative samples and that between difficult and easy samples in YOLOv5s network, the network combined the focus loss function Focal loss and introduced two super-parameters to control the weight of unbalanced samples. Combined with the improvement of attention mechanism SE module and focus loss function, the overall performance of the detection network was improved, and the average accuracy was improved by 2.2 percentage points, which effectively improves the index of false detection and missed detection in the case of large traffic flow. 
Related Articles | Metrics
Research and realization of small target smoke and fire detection technology based on YOLOX  
ZHAO Hui , ZHAO Yao , JIN Lin-lin , DONG Lan-fang , XIAO Xiao
2022, 43(5): 783-790.  DOI: 10.11996/JG.j.2095-302X.2022050783
Abstract ( 43 )   PDF (3117KB) ( 39 )  
 Fire is one of the most common social disasters in daily life, which will pose an enormous threat to human property and life safety. How to accurately and quickly identify small areas of smoke and fire and issue early warnings in real time is important for normal social production significance. The traditional smoke and fire detection algorithm identifies the location of smoke and fire based on various low-dimensional visual features of the images, such as color and texture, so it is of poor real-time performance and low accuracy. In recent years, deep learning has made remarkable achievements in the field of target detection, and various smoke and fire detection methods based on deep neural networks have sprung up one after another. In the case of small areas of smoke and fire, timely identification and early warning should be made to avoid greater economic losses caused by the expansion of the fire. In this regard,  based on the YOLOX model, the activation function and loss function were improved, and a superior small target detection algorithm was realized by combining the data augmentation algorithm and cross-validation training method, and the mAP value of 78.36% was obtained on the smoke and fire detection data set. Compared with the original model, it was enhanced by 4.2%, yielding a better effect of small target detection effect. 
Related Articles | Metrics
An object detection method of falling person based on optimized YOLOv5s 
WU Li-zhan, WANG Xia-li, ZHANG Qian, WANG Wei-hao, LI Chao
2022, 43(5): 791-802.  DOI: 10.11996/JG.j.2095-302X.2022050791
Abstract ( 33 )   PDF (12297KB) ( 101 )  
To address the problems of easy missing, poor robustness and generalization ability when object detection model is detecting a person falling down, a new detection method YOLOv5s-FPD was proposed based on the improved YOLOv5s. Firstly, the Le2i fall detection data set was expanded in various ways for model training to enhance model robustness and generalization ability. Secondly, MobileNetV3 was employed as the backbone network for feature extraction, which could coordinate and balance the relationship between lightness and accuracy of the model. Furthermore, BiFPN (bi-directional feature pyramid network) was utilized to boost model multi-scale feature fusion ability, thereby improving the efficiency and speed of fusion. Meanwhile, the CBAM (convolutional block attention module) lightweight attention mechanism was adopted to realize double focus attention to channel and space, enhancing the effect of attention mechanism on model accuracy. Finally, Focal Loss evaluation was used to pay more attention to hard example mining and alleviate the samples imbalance problem. The experimental results show that the precision, F1 score, and detection speed of YOLOv5s-FPD model were improved by 2.91%, 0.03, and 8.7 FPS, respectively, compared with the original YOLOv5s model on Le2i fall detection dataset, which verified the effectiveness of the proposed method. 
Related Articles | Metrics
Improved YOLOX method for detecting surface defects of drug blister aluminum foil 
HU Hai-tao , DU Hao-chen , WANG Su-qin , SHI Min , ZHU Deng-ming,
2022, 43(5): 803-814.  DOI: 10.11996/JG.j.2095-302X.2022050803
Abstract ( 25 )   PDF (10051KB) ( 14 )  
The surface of aluminum foil in drug blister packaging contains various information on fonts and patterns, and the surface of aluminum foil is uneven, leading to the uneven distribution of light and dark. To address the problem that the YOLOX model cannot more accurately distinguish the defect features from the surface features of aluminum foil, a surface defect detection method based on the improved YOLOX model was proposed. Firstly, in order to enhance the globality of the information input to the Prediction, it was necessary to analyze the global features of the feature map in the Neck network, so the CSP module of the Neck network was replaced with the transformer encoder module. At the same time, the YOLOX model has a deep depth, and to effectively improve the classification accuracy, the Mish activation function was utilized to replace the Swish activation function. Then, focal loss was introduced into the loss function to solve the problem of difficulty in classifying defect regions and background regions due to the similarity of defect features and aluminum foil surface features. The experimental results show that the mAP of the improved model for the detection of aluminum foil surface defects was 90.17%, which was 4.95% higher than the original YOLOX model, and that the improved model can reduce the probability of false detection and missed detection of defects with high similarity to the surface features of aluminum foil.
Related Articles | Metrics
Feature-adaptive filtering for retinopathy grading 
LIANG Li-ming, LEI Kun, ZHAN Tao, ZHOU Long-song
2022, 43(5): 815-824.  DOI: :10.11996/JG.j.2095-302X.2022050815
Abstract ( 5 )   PDF (3932KB) ( 4 )  
To address the difficulty in recognizing features of retinopathy images and the low efficiency of disease grading, a retinopathy grading algorithm based on feature adaptive filtering was proposed. Firstly, the algorithm used the multi-scale filtering branches (MFB) constructed by the ResNet-50 network to extract features of retinopathy images step by step. Secondly, cascade adaptive feature filter blocks (AFFB) was adopted after filtering branches of different scales to perform feature enhancement and filtering on retinopathy images. Then, the feature complementary fusion module (FCFM) was utilized to complement the multiple local enhancement features after feature filtering, and enrich the local details of the retinopathy image by aggregating the complementary information of the local enhancement features. Hierarchical models with different local feature information were trained and experiments were performed on the IDRiD dataset. The experimental results show that the accuracy of the proposed grading algorithm was 80.58%, the weighted kappa coefficient 88.70%, the specificity 94.20%, and the sensitivity 94.10%. The algorithm could effectively identify the subtle lesions in retinopathy images and improve the grading efficiency. 
Related Articles | Metrics
Water supply pipeline leakage intelligent detection algorithm based on small and unbalanced data 
SUN Zong-kang , RAO Mu-min , CAO Yu-ling , SHI Yan-li
2022, 43(5): 825-831.  DOI: 10.11996/JG.j.2095-302X.2022050825
Abstract ( 13 )   PDF (2705KB) ( 11 )  
To address the problems of few and unbalanced data samples in the visual detection of water supply pipeline leakage in energy power plants, an intelligent detection algorithm for water supply pipeline leakage based on small sample unbalanced data was proposed. First, a data enhancement method based on Multi-mask mix was proposed. The original image was extracted and mixed by the mask layer randomly generated, and the support vector machine (SVM) was incorporated into Multi-mask mix to obtain pipeline normal and leakage features, thus providing more accurate prior labels for the hybrid mask blocks. Secondly, an equalization strategy was proposed and applied to the image level and mask level to achieve data equalization. Finally, a deep learning-based Resnet18 network model was utilized to attain pipeline leak detection and identification. The experimental results show that the algorithm can improve the accuracy of the Resnet18 model for pipeline leakage detection by 1.1%–4.4% after processing image data, and can effectively enhance the classification accuracy of the deep learning model for pipeline leakage detection, outperforming other existing algorithms. In addition, the algorithm has now been successfully applied to the leakage detection of water supply pipelines in energy power plants. 
Related Articles | Metrics
Monkey action recognition based on global spatiotemporal encode network 
SUN Zheng, ZHANG Su-cai , MA Xi-bo,
2022, 43(5): 832-840.  DOI: 10.11996/JG.j.2095-302X.2022050832
Abstract ( 16 )   PDF (2580KB) ( 16 )  
Accurate quantification of caged monkeys’ behaviors is a primary goal for the preclinical drug safety assessment. Skeleton information is important to the analysis on the behaviors of monkeys. However, most of the current skeleton-based action recognition methods usually extract the features of the skeleton sequence in the spatial and temporal dimensions, ignoring the integrity of the skeleton topology. To address this problem, we proposed a skeleton action recognition method based on the global spatiotemporal encode network (GSTEN). Based on the spatial temporal graph convolutional network (ST-GCN), the proposed method inserted global token generator (GTG) and several global spatiotemporal encoders (GSTE) in parallel to extract the global features in the spatiotemporal dimension. To verify the performance of the proposed method, we conducted experiments on a self-built monkey action recognition dataset. The experimental results show that the proposed GSTEN could achieve an accuracy of 76.54% without increasing the number of model parameters, which was 6.79% higher than the baseline model ST-CGN. 
Related Articles | Metrics
Self-supervised optical flow estimation with attention module 
AN Feng , DAI Jun, HAN Zhen , YAN Zhong-xing
2022, 43(5): 841-848.  DOI: 10.11996/JG.j.2095-302X.2022050841
Abstract ( 9 )   PDF (3760KB) ( 10 )  
Optical flow estimation is the key module of many computer vision systems, which is widely utilized in motion recognition, robot positioning, and navigation. However, due to the absence of labeled optical flow datasets of real scenes, synthetic datasets were used as the main training data sources, and synthetic data could not fully represent real scenes (such as leaf movement and pedestrian reflection). Unsupervised or self-supervised methods could employ a large amount of video data for training, and at the same time facilitate fine-tuning of supervised training, which was an effective way to solve the lack of datasets. In this paper, a self-supervised learning optical flow calculation network was constructed, in which the “Teacher” module and the “Student” module adopted sparse correlation volume (SCV) network to reduce the redundancy of correlation computation, and the attention model was introduced as a node of the network, in order to enhance the dimension attribute of image feature in terms of channel and space. This paper marks the first endeavor to implement a self-supervised optical flow computing network based on SCV. The test results on the KITTI 2015 dataset could reach or outperform those of the common supervised training networks such as FlowNet and LightFlowNet. 
Related Articles | Metrics
Research on automatic extraction of spherical targets based on SHOT feature descriptor  
WANG Hao, ZHENG De-hua, LIU Cun-tai, CHENG Yu-xiang, HU Chuang
2022, 43(5): 849-857.  DOI: 10.11996/JG.j.2095-302X.2022050849
Abstract ( 1 )   PDF (1990KB) ( 3 )  
To achieve the accurate automatic extraction of spherical targets from 3D laser point clouds in complicated scenes, a method was proposed for the automatic and accurate extraction of spherical targets based on SHOT features. This method designed the processes of rough extraction and refined extraction. In the rough extraction process, SHOT feature descriptor was utilized to extract all spherical target point clouds in the scene; secondly, Euclidean clustering was used to segment spherical target point clouds, and rough spherical target parameters was calculated using the least square. The refined extraction process was based on the iterative least squares method and normal filtering to eliminate the aspherical points, and obtain the spherical target point cloud and accurate spherical target parameters. An experimental scene with 4 spherical targets was designed. The German Z+F Image 5016 scanner was employed to collect the scene data, and the spherical target point cloud and spherical target parameters in the experimental scene were automatically extracted. The results show that in the range of 10 meters, the error of the radius of the spherical target automatically extracted by this method was 0.25–0.33 mm, which was 0.02–0.06 mm less than that of the manually extracted spherical target point cloud, and 0.01–0.09 mm less than that based on the differential method. The proposed method can achieve high positioning accuracy for spherical targets and robustly eliminate noise in the scene point cloud, and can complete the automatic extraction of spherical targets with millions of point clouds within 30 seconds. 
Related Articles | Metrics
Video-based human walking parameter measurement method and application
YAO Peng , ZHOU Xiao-jing , JIN Si-fu , TANG Zhang-feng
2022, 43(5): 858-864.  DOI: 10.11996/JG.j.2095-302X.2022050858
Abstract ( 10 )   PDF (10385KB) ( 11 )  
To address the problems of high complexity and low efficiency of the available methods for human walking parameter measurement, a video-based human walking parameter measurement method was proposed. The supervised learning method was used to estimate the pose of the moving target in the video, and the bone joint points were recognized frame by frame. Then, according to the feature points of head and feet, combined with the conversion relationship between the pixel distance obtained by scene calibration and the actual distance, the walking height measurement was realized. According to the joint feature points, the joint range of motion was calculated by cosine formula. According to the foot feature points, a method to identify the walking step size and pace was proposed by combining the frame difference of front and rear poles and the pixel difference. Finally, a virtual human follow-up control method based on Unity3D was proposed, which could carry out motion simulation in virtual scenes and was convenient for real-time monitoring and human abnormal behavior analysis in videos and early warning issuing. Experiments show that this method is superior in simple operation, high accuracy, and strong real-time performance. 
Related Articles | Metrics
Automatic segmentation algorithm for text lines of Dongba hieroglyphs document image  
KANG Hou-liang , YANG Yu-ting
2022, 43(5): 865-874.  DOI: 10.11996/JG.j.2095-302X.2022050865
Abstract ( 11 )   PDF (2126KB) ( 20 )  
Deep learning technologies represented by convolutional neural networks (CNN) have shown excellent performance in the field of image classification and recognition. However, since there is no standard and public dataset for Dongba hieroglyphs, we cannot draw on or use the existing deep learning algorithms. In order to establish an authoritative and effective Dongba hieroglyphs dataset, the current primary task is to analyze the layout structure of the published Dongba classic documents, and extract the text lines and Dongba hieroglyphs in the documents. Therefore, based on the structural features of Dongba hieroglyphic document images, an automatic text-line segmentation algorithm was proposed for Dongba document images. The algorithm first employed the d-k-means clustering algorithm to determine the classification quantity and classification standard of text lines; then, the wrong results in the segmentation were corrected through the secondary processing of the text blocks, so as to enhance the accuracy of the algorithm. While making full use of the structural features of Dongba characters, the algorithm retained such advantages of the machine-learning model  as objectivity and immunity to subjective experience. Experiments show that the algorithm can be used for the text line segmentation of Dongba document images, offline handwritten Chinese characters, Dongba scriptures, and the segmentation of individual Dongba and Chinese characters in text lines. It is simple in implementation, high in accuracy, and strong in adaptability, thus laying the foundation for the establishment of the Dongba character library. 
Related Articles | Metrics
Dense point cloud reconstruction network using multi-scale feature recursive convolution
WANG Jiang-an, PANG Da-wei, HUANG Le, QING Lin-zhen
2022, 43(5): 875-883.  DOI: 10.11996/JG.j.2095-302X.2022050875
Abstract ( 6 )   PDF (35240KB) ( 10 )  
In the task of 3D reconstruction, it is difficult to deal with the traditional multi view stereo algorithm because of the large photometric consistency measurement error in the weak texture region. To solve this problem, a recursive convolution network of multi-scale feature aggregation was proposed, named MARDC-MVSNet (multi-scale aggregation recursive multi view stereo net with dynamic consistency), which was utilized for dense point cloud reconstruction in weak texture areas. In order to boost the resolution of the input image, this method used a lightweight multi-scale aggregation module to adaptively extract image features, thereby addressing the problem of weak texture or even no texture region. In terms of cost volume regularization, a hierarchical processing network with recursive structure was used to replace the traditional 3D CNN (convolutional neural networks), greatly reducing the occupation of video memory and realizing high-resolution reconstruction at the same time. A depth residual network module was added at the end of the network to optimize the initial depth map generated by the regularized network under the guidance of the original image, so as to produce more accurate expressions of the depth map. The experimental results show that excellent results were achieved on the DTU data set. The proposed network can not only achieve high accuracy in depth map estimation, but also save hardware resources, and it can be extended to aerial images for practical engineering. 
Related Articles | Metrics
A new 3D point clouds feature selection method using specific outliers optimization 
HUANG Xiang, WANG Hong-xing, GU Xu, MENG Yue, WANG Hao-yu
2022, 43(5): 884-891.  DOI: 10.11996/JG.j.2095-302X.2022050884
Abstract ( 4 )   PDF (4286KB) ( 6 )  
With the rapid development of technologies in metaverse, digital twins, virtual and augmented reality, three-dimensional (3D) point clouds have been widely applied to electric power, construction, advanced manufacturing, and other industries. As a result, how to reduce the redundancies of 3D point clouds data and how to effectively select useful point cloud features have played a critical role in the full use of massive point clouds data. Considering that most of the current feature selection methods pay little attention to specific instances, in this paper, we proposed a novel supervised feature selection method, named feature selection based on specific outliers optimization (FSSO). Specifically, in order to obtain accurate specific outliers (SOs), we first optimized the traditional mean center of class, and automatically defined the class majority. Then, we proposed the feature selection algorithm that could compute the intra-class relative deviation of SOs, and score features based on the deviations. Extensive experiments on 3D data clouds classification datasets (ModelNet40, IntrA, and ShapeNetCore), and on four high-dimensional handcrafted datasets show that the proposed FSSO can select discriminative features, and improve the classification accuracy. 
Related Articles | Metrics
Computer Graphics and Virtual Reality
A 3D hand pose estimation method based on improved PointNet++ 
TONG Li-jing, LI Jia-wei
2022, 43(5): 892-900.  DOI: 10.11996/JG.j.2095-302X.2022050892
Abstract ( 10 )   PDF (1367KB) ( 8 )  
To address the problem that the processing of local features of point cloud in PointNet++ network sometimes results in a large amount of computation due to the large grouping range, a 3D hand pose estimation method based on the improved PointNet++ network was proposed. Firstly, the gesture point cloud was triangulated based on the combination of Delaunay triangulation algorithm and K-Median clustering algorithm, thus creating the triangular mesh model of the gesture point cloud. Simultaneously the average edge length of the triangular mesh model was calculated. Then, with the average edge length of the triangular mesh model as the radius, the points sampled by the farthest point sampling (FPS) algorithm were searched by ball query. Then the sampled point cloud was grouped by K-Nearest Neighbors algorithm according to the maximum value of the searched sampled points. Finally, the grouped point cloud was input into the PointNet to perform the 3D hand pose estimation. The improved PointNet++ network can automatically adjust the number of local abstraction points of point cloud grouping according to point cloud density at different levels. Experiments show that, without affecting the accuracy of 3D hand pose estimation, the proposed method can enhance the training speed of PointNet++, as well as effectively reducing the  computation of feature extraction in 3D hand pose estimation, so that the computer can capture the hand pose more quickly. 
Related Articles | Metrics
A fast construction method of 6-DOF field virtual environment based on panoramic video image 
CHEN Tian-xiang, CHEN Bin
2022, 43(5): 901-908.  DOI: 10.11996/JG.j.2095-302X.2022050901
Abstract ( 14 )   PDF (3563KB) ( 17 )  
The virtualization of the field environment is of great research significance. It is necessary to consider the following questions: how to construct field virtual environments more efficiently and conveniently, and how to achieve higher degree of interaction freedom and better immersive experience in the constructed virtual environment. We proposed a fast construction method of field virtual environment based on panoramic videos. Through the processing of depth estimation and photographic modeling of extracted panoramic images, the reconstructed scenes were divided into far and near scenes with various forms. Finally an immersive field virtual environment was produced, which supported 6-DOF roaming within a certain range. The practicability of this method was quantitatively analyzed and verified by the objective indicators of image quality, and a prototype system with the complete process from the construction to the use of the field virtual environment was developed as an application. The results show that the fast construction method of 6-DOF field virtual environment based on panoramic image could achieve high efficiency and excellent applicability, exhibiting promising prospects in fields such as virtual field geological practice and teaching. 
Related Articles | Metrics
Generation method of neighborhoods layout in Hui-style villages with the aid of prediction network 
ZHU Lei, JIANG Fu-lin, LI Lin
2022, 43(5): 909-917.  DOI: 10.11996/JG.j.2095-302X.2022050909
Abstract ( 6 )   PDF (1504KB) ( 5 )  
The layout optimization of traditional villages was an important part of the modeling of outdoor scene-aided design. Thus a generation method was proposed for neighborhoods layout in Hui-style villages with the aid of prediction network. Firstly, a structured data construction method was proposed for neighborhoods layout in Hui-style villages based on CAD mapping. Secondly, prediction networks were designed for each type, location, and orientation of houses in the local layout. Finally, the prediction results were used to predict the type of houses, which was conducted by firstly according to the area and shape classification in the existing house data set, and then by searching for the optimal generation results in the corresponding categories, and could satisfy the non-overlapping constraints within the region and houses. A series of quantitative and qualitative experimental results show that this method can generate a house layout that conforms to the characteristics and rules of the neighborhoods layout in Hui-style villages, so as to provide designers with a creative means for Hui-style settlement scenes. 
Related Articles | Metrics
BIM/CIM
Research of BIM and ontology-based irregular building type checking 
NAZHAER Mulatibieke, SHI Jian-yong, JIANG Liu, PAN Ze-yu, YANG Hai-tao , WANG Jia-liang
2022, 43(5): 918-926.  DOI: 10.11996/JG.j.2095-302X.2022050918
Abstract ( 26 )   PDF (612KB) ( 13 )  
 Irregular building type checking is a significant part of building checking for seismic compliance, which is of immense significance to buildings’ seismic safety. An approach based on building information modeling (BIM) and ontology was proposed for identifying irregular building types, thus boosting efficiency and accuracy. Firstly, the rules for checking irregular building types were analyzed and then translated into semantic compliance checking rules that could be recognized by the computer. Meanwhile, the irregular building type checking ontology was created to represent the checking logic. Secondly, the building information model’s information to be checked was extracted using automatic parsing, such as floor opening area, and such information was extracted from the building finite element analysis result parameters by the pattern matching algorithm, such as torsional displacement ratio. The extracted information was organized on the basis of the proposed irregular building type checking ontology. Next, the sematic reasoning was utilized to obtain the checking results and generate the checking reports. Finally, a designed building was taken as an example to verify the feasibility and strong expansion ability of the proposed method, which could lay a technical foundation for further realizing the automatic building checking for seismic compliance. 
Related Articles | Metrics
Industrial Design
Design and evaluation of offshore oil spill recovery devices based on morphological bionics 
ZHANG You-wei, SUN Hu
2022, 43(5): 927-935.  DOI: 10.11996/JG.j.2095-302X.2022050927
Abstract ( 11 )   PDF (5901KB) ( 8 )  
 In order to address the problem of the single function and form of the offshore oil recovery device, a method of bionic design, which was constructed using the bionic design program from bottom to up, was proposed. Firstly, in order to determine the bionic target set, the set of intentional images of the biological features was obtained using the synectics method. Secondly, the Harris chart was employed to screen the target set to determine the bionic prototype. Thirdly, the biological simplification and optimization method was utilized to analyze the structural feature relationship of the bionic prototype, and couple the structural features and the main design elements obtained using the approach of morphology analysis, thereby producing a preliminary design plan of bionic modeling. Fourthly, the concept of fuzzy sets in fuzzy mathematics was used to rank the design plans to determine the priority. Fifthly, the best design plan was selected for modal analysis to verify whether the plan could meet the requirements of structural dynamics, thus establishing a bionic design method that could shed light on the whole system. Based on this method that could guide the design, we could obtain the oil spill recovery device of manta ray bionic style, which could meet the design requirements and was of high coupling degree between function and form. By applying the constructed design model to the bionic design of products, it can provide effective theoretical guidance for the design of the marine application product, and help elevate the overall level of marine technological products. 
Related Articles | Metrics
Color matching study of ASD children intervention APP based on PCCS color system
ZHANG Bing-chen, ZHAO Jia-bao, LI Xun, YANG Yu-ling, WEI Yi-yang
2022, 43(5): 936-947.  DOI: 10.11996/JG.j.2095-302X.2022050936
Abstract ( 8 )   PDF (2196KB) ( 10 )  
In order to enhance the rehabilitation effect of intervention APP for autism spectrum disorder (ASD) children, and shed reasonable and effective light on the designers, this paper proposed an interface color matching evaluation method for ASD children intervention APP based on the system of PCCS (practical color coordinate system) color. Firstly, the literature analysis and focus group methods were used to construct the interface color matching evaluation system of ASD children intervention APP based on the PCCS color system. Secondly, the AHP method was used to obtain the weight of each evaluation index. Then eight interface color design schemes were selected based on the PCCS color system, experts were invited to offer their scores, and the initial judgment matrix was obtained. Then the ranking results of each scheme were obtained through the TOPSIS method. Finally, the results were analyzed. The results showed that ASD children were more likely to recognize green, blue, and other cool colors, as well as colors with higher lightness and purity. In the PCCS tonal figure, ASD children would prefer gentle tone, light color tone, the collocations of adjacent colors and complementary colors. In the interface color design, the color collocation should  be livelier, clear, harmonious, and stable. The evaluation method was applied to the evaluation of interface color matching experiments for intervention APP, and could boost the scientificity and objectivity in the process of design evaluation, and provide a reference for designers to make decisions, thus advancing the development of intervention APP for ASD children. 
Related Articles | Metrics
Design and research of a weight-reducing backpack to protect the health of adolescents’ spine
QIN Rong , TU Xi-kai, GAN Chang , LI Xiao
2022, 43(5): 948-956.  DOI: 10.11996/JG.j.2095-302X.2022050948
Abstract ( 14 )   PDF (4731KB) ( 11 )  
At present, in the case of backpacks for the youth on the market, weight is mainly designed to be carried by shoulders, which ignores the role of the waist in load-carrying. Long-term improper loading of backpacks can affect the growth of one’s spine. In order to balance the load on shoulders, waist, and hip, a weight loss backpack was designed to change the way of gravity transmission through the hip belt and elastic bar structure. Firstly, the biomechanical analysis of the state of the human backpack and the spine was carried out, and the weight-reducing principle of the backpack was achieved according to the force analysis. Then, the torque analysis was carried out on shoulders, waist, and hip of the weight-reducing backpack, and a design plan was proposed. Next, the traditional backpack was analyzed by ADAMS. The dynamic simulation of human shoulders, waist, and hip loads was carried out with the weight-reducing backpack under three road conditions of even ground, uphill, and downhill conditions, and the moments of shoulders, waist, and hip in the cases of the two backpacks were analyzed by MATLAB. The results show that the weight-reducing backpack could reduce the shoulder moment by 6.1% and the waist by 5.4%; the ratio of the shoulder moment of the weight-reducing backpack to the combined moment of the waist and hip was 4.17, and the ratio of the traditional backpack was 6.58. A conclusion could be drawn that the weight-reducing backpack could reduce the load on shoulders and waist. At the same time, it was found that the smaller the ratio of the shoulder moment and the combined moment of the waist and hip is, the greater the moment transferred to the hip, and the better the balance of the backpack, indicating that the weight-reducing backpack outperforms the traditional ones. 
Related Articles | Metrics
Published as
Published as 5, 2022
2022, 43(5): 957-957. 
Abstract ( 13 )   PDF (116675KB) ( 18 )  
Related Articles | Metrics