Table of Contents

31 October 2018, Volume 39 Issue 5 Previous Issue    Next Issue

---

For Selected:

Download Citations EndNote Ris BibTeX

Toggle Thumbnails

Select

A Review of BIM-Based Artificial Intelligence Methods LENG Shuo1, HU Zhenzhong2 2018, 39(5): 797-805.  DOI: 10.11996/JG.j.2095-302X.2018050797 Abstract ( 862 )   PDF (378KB) ( 1009 )   As an emerging technology in the construction field, building information modeling/model (BIM) technology is making profound influence on the development of the construction industry, while the cross-disciplinary application of artificial intelligence (AI) technology has become increasingly widespread. The combination of BIM with AI methods is characterized with good feasibility and broad prospects. However, related research and application at home and abroad are still at the initial stage. Based on extensive literature review, this paper summarizes previous studies on BIM-based AI from the perspective of technology, system and application, and introduces commonly used AI technologies, typical development platforms and methods, as well as the successful applications in different construction stages such as design, construction, operation and maintenance. In this light, the problems and challenges in the field are analyzed, the causes of the problems summarized, and the future direction of development anticipated. Related Articles | Metrics

Select

Present and Future of Integrated Applications of BIM, Cloud Computing,  Big Data and Internet of Things Present and Future of Integrated Applications of BIM, Cloud Computing, Big Data and Internet of Things 2018, 39(5): 806-816.  DOI: 10.11996/JG.j.2095-302X.2018050806 Abstract ( 606 )   PDF (382KB) ( 618 )   Recently, increasing attention has been paid to cloud computing, big data and internet of things and their integration with building information modeling (BIM) technology in construction projects. However, a unified integrated application framework has not been established. Based on extensive literature review, this paper holds that cloud computing, big data, internet of things and BIM are all necessary to serve construction project management. In this light, a unified integrated application framework was built. Additionally, we reviewed previous studies and applications of integration of BIM and related technologies, as well as the state of art of key technology and software development, giving a summary of existing applications. Finally, this paper discusses the challenges and future trends, pointing out that further research needs to focus on basic theory and multi-technology integration. Related Articles | Metrics

Select

Researches and Applications of Cloud-Based BIM Architectures GUI Ning1, GE Danni1, MA Zhiliang2 2018, 39(5): 817-828.  DOI: 10.11996/JG.j.2095-302X.2018050817 Abstract ( 204 )   PDF (560KB) ( 366 )   With the growing application of the building information model (BIM) in the buildings’ life-cycle, the building projects are characterized with growing complexity and explosively increasing data size. It has become a great challenge for the construction industry as to how to efficiently support the applications of BIM. It has been widely acknowledged in academic and industry circles that with a short life, cloud computing and big data technology can cope with numerous challenges in applications of BIM. This paper reviews existing studies and applications of cloud technology-based BIM (i.e. Cloud-BIM), approaching its applications at three layers: the data layer, the service layer and the application layer. Then the paper discusses and explains the present studies and practices of the three layers, pointing out the progress and obstacles in different layers. Finally, the current research limitations and prospects of future research trends are summarized in the conclusion section, shedding new light on potential researches and applications. Related Articles | Metrics

Select

A Review on the Research Using Building Information Model Technology in Multi-Hazards Topic ZHENG Ming, XUE Qiaorui, WEI Wei, XU Zhen 2018, 39(5): 829-834.  DOI: 10.11996/JG.j.2095-302X.2018050829 Abstract ( 177 )   PDF (2140KB) ( 382 )    Building information model (BIM) is a popular technology in the field of building industry, while the topic of multi-hazards is the forefront in the field of disaster prevention of buildings. If BIM technology is applied to the multi-hazards research, it can provide a sharing and consistent data model for this field, which improves the utility rate of the data and ensure the conformity of analysis models for different disasters. Based on the database of CNKI and Web of Science, the domestic and international researches focusing on BIM, earthquake, wind and fire are investigated, and the key words of different research directions are summarized. In general terms, the research on BIM and multi-hazards is in a start-up stage and needs to be developed further. Related Articles | Metrics

Select

Research on Cloud Storage and Retrieval Method of  BIM Spatial Relational Data JIANG Shaohua, WU Zheng 2018, 39(5): 835-842.  DOI: 10.11996/JG.j.2095-302X.2018050835 Abstract ( 166 )   PDF (739KB) ( 255 )   With the increase of engineering project volume, the spatial relationships existing in the model have been more complicated and diversified, thus the existing methods for storing and retrieving the building information modeling (BIM) data cannot meet the requirements of the users. In order to improve the efficiency of storing and retrieving the large number of BIM spatial relationships data, the solution of BIM distributed load balancing cluster is proposed by integrating BIM and cloud computing technologies. Based on the solution, Elastic Search and graph database Neo4j are adopted to accomplish the storage and retrieval for IFC spatial relationships data, and to provide a faster and more efficient method of cloud storage and retrieval for the massive BIM spatial relationships data. Related Articles | Metrics

Select

Research on Dimensional Construction Method of 3D Process Model HOU Zengxuan, LI Lin, HUANG Lei, ZHANG Yan 2018, 39(5): 843-848.  DOI: 10.11996/JG.j.2095-302X.2018050843 Abstract ( 82 )   PDF (353KB) ( 166 )   According to the TTRS theory, the characteristics of all surfaces in the 3D process model are identified, TTRS of the parts and the geometric and topological information of the corresponding MGDE are obtained, and the process model dimension elements are extracted. According to the relative position of the data, the dimension elements are classified to construct the annotation dimension. Owing to the existence of the redundancies in the elements, the corresponding rules of eliminating the redundant dimension elements are proposed for the three kinds of redundancies, and eventually the elimination is accomplished based on the rules. For the six dimension types, the method for calculating their weights is porposed, and accordingly the dimension order is determined. For the case that there may be redundancy in the generated dimension, the graph theory method is adopted to eliminate the redundant dimensions, and to provide the flow chart of the algorithm for eliminating redundant dimensions. A complete set of dimension is constructed so that the dimensional construction of 3D process model is accomplished. Based on UG/Open Grip, the 3D dimension construction and display module is developed to implement the above algorithm. Related Articles | Metrics

Select

A Rapid Structure Modeling Method Based on Skeleton Model in Ship Design ZHANG Zhou, XI Ping, HU Bifu 2018, 39(5): 849-854.  DOI: 10.11996/JG.j.2095-302X.2018050849 Abstract ( 128 )   PDF (949KB) ( 179 )   Aimed at the problem that there are many iterations in China’s ship structure design and there are different designs in different national regions, a rapid modeling method of hull structure is proposed. The method takes “Top-Down design” as the design idea and the skeleton model as the carrier. After analyzing and summarizing the characteristics of the hull structure, a skeleton model for ship structure is built and the definition of the model is made. The rapid layout design is realized through the skeleton model of the ship structure and the parameter coordinate system. The relationship between the parameter coordinate system and the ship plates is established to achieve the rapid modeling and adjustment of the ship structure, and to give the corresponding algorithm. The organized design information is integrated into the skeleton model in order to realize the integrity definition and rapid modeling for hull structure. Finally, the rapid modeling system is developed based on the CATIA V6 platform, and the feasibility of the method turns out to be verified by the longitudinal skeleton structure. Related Articles | Metrics

Select

Research on Prognostics and Health Management System HUANG Zhongshan1,2, TIAN Ling1,2 2018, 39(5): 855-861.  DOI: 10.11996/JG.j.2095-302X.2018050855 Abstract ( 145 )   PDF (1288KB) ( 279 )   To solve the problems existing in the intelligent maintenance of intelligent equipment such as low-level intelligentization, networking and the difficulty of establishing physical model, the research is made on the framework, key technologies and system development methods of the data-driven remote prognostics and health management system (PHM) for intelligent equipment. The operating mode of the data-driven PHM system is specifically described. Based on it, the software architecture and key technologies of the PHM system are analyzed. First, the EEMD is used to denoise and reconstruct the original signal, and the reconstructed signal is applied as the input to establish the diagnostic model based on RBF neural network. Then the fault prediction model based on time series is established by dynamic neural network, and the fault alarm mechanism based on the fault threshold is set up. Finally, the hybrid programming and networking are employed to develop the data-driven remote PHM system. The practical application results show that the system, with a good practicability, can efficiently perform the core functions of fault diagnosis and prediction. Related Articles | Metrics

Select

Method and Implementation of Design of Glass Bottle Mould Component Based on Model Retrieval CHEN Gengxin1, ZHU Xingyuan1, CUI Haihua2, MA Jianhua3, WANG Huajun1 2018, 39(5): 862-866.  DOI: 10.11996/JG.j.2095-302X.2018050862 Abstract ( 83 )   PDF (4822KB) ( 118 )   Based on the analysis on the structure of glass bottle product and the standard of mould design for enterprises, a method of glass bottle mould component design based on model retrieval is proposed on the NX software platform. Applying the image recognition algorithm of polar-radius- invariant moment for feature recognition, a library case that contains features of glass bottle models and their corresponding scheme for mould component assembly is constructed with the index of bottle products. After retrieving and matching the most similar molds in the case library, the successfully-matched components are designed based on experts’ knowledge and experience in the knowledge base of system. The feasibility of the design method turns out to be verified by the design example of the blank and blow mould of 400 ml jar in the article. Related Articles | Metrics

Select

Research on Product Deep Personalized Customization  Based on User Requirements TIAN Qiaoping, LV Jian, PAN Weijie, WANG Weiyi, YUAN Tao 2018, 39(5): 867-878.  DOI: 10.11996/JG.j.2095-302X.2018050867 Abstract ( 131 )   PDF (3114KB) ( 186 )   In order to solve the problems of complex user requirements analysis, low demand fit and insufficient user participation in the customization of existing products, the product deep-personalized customization method based on user requirements is proposed. The method maps the user requirements into the customized requirements by combining the user personality requirements expression model and the Quality Function Deployment (QFD), and it solves the product configuration by case retrieving and matching. The user can provide real-time feedback and adjustment to the customization solution through the visual interface, and deepen product customization degree with variant design. Finally, the optimal solution is provided to the users through the priority-degree evaluation so as to achieve a customization loaded with higher user participation and satisfaction. The method provides an effective way for deep-personalized customization and the feasibility of it turns out to be verified by the example of the product customization on cape. Related Articles | Metrics

Select

Rapid Modeling of Lattice Support Structures for Selective Laser Melting ZHENG Xiaolong1, LIU Yuan1, ZHENG Guolei1, ZHOU Min2 2018, 39(5): 879-885.  DOI: 10.11996/JG.j.2095-302X.2018050879 Abstract ( 75 )   PDF (928KB) ( 119 )    Aimed at the support structures in laser selective melting, a rapid modeling method is proposed that the lattice cells can be automatically filled to generate support structures. First of all, the parameterized modeling is applied on the units of two typical lattice support structures-struss structures and porous structures, and the digitalized model of the support structures is established. Secondly, the design and implementation are made on the modeling algorithm of struss and porous unit. Finally, a rapid filling for supporting spaces is realized through a cell natural growth algorithm. The results of the examples show that the lattice structure can provide effective and stable support for different types of structures. Compared with the solid materials, lattice structure’s material consumption can be saved by 72% on average, which has an important engineering significance. Related Articles | Metrics

Select

Person Re-Identification Based on Transfer Learning HU Bin1,2, PAN Yu1, DING Weiping1, SHAO Yeqin3, YANG Cheng1 2018, 39(5): 886-891.  DOI: 10.11996/JG.j.2095-302X.2018050886 Abstract ( 73 )   PDF (516KB) ( 179 )   The person re-identification refers to matching pedestrian images observed from different cameras in a non-overlapping multi-camera surveillance systems. In this article, a person re-identification method based on transfer learning is proposed. The deep convolutional neural network model pre-trained on ImageNet is adopted to fine-tune the parameters for person re-identification, and the Re-ID model is used to extract the features from person image. The simple cosine distance is applied to measure similarities between person pairs. The approach is evaluated by operating in-depth experiments in three benchmarks, including CUHK03, Market-1501 and DukeMTMC-reID, and the experimental results on the benchmarks show significant and consistent improvements over parallel methods. Related Articles | Metrics

Select

Features Integration Based Visual Tracking with Re-Detection Method LI Zhongke1, WAN Changsheng2 2018, 39(5): 892-900.  DOI: 10.11996/JG.j.2095-302X.2018050892 Abstract ( 53 )   PDF (2500KB) ( 213 )   Taking the gradient features and color features of an image into consideration, an improved visual tracking algorithm based on correlation filter tracking is proposed in this paper. The algorithm uses the Bayesian theory to model the color information, and carries out object tracking with the combination of gradient features’ correlation filter output and object confidence integral map which is obtained from dense object posterior probability. Meanwhile, the algorithm conducts a quality assessment of the results of the object tracking. Once the tracking quality turns out to be unreliable, the object re-detection process will start, which is based on the object confidence integral to determine the candidate objects. As to the video frame with unreliable tracking quality or no reliable object after re-detection, the tracking model will not be updated online. Experiments show that the proposed algorithm can effectively avoid the problem of unreliable tracking and model drift caused by circumstances varying, and its tracking performance is obviously improved compared with those of several state-of-the-arts correlation filters. Related Articles | Metrics

Select

Pedestrian Object Detection Based on Faster RCNN and  Similarity Measurement LI Zongmin1, XING Minmin1, LIU Yujie1, LI Hua2 2018, 39(5): 901-908.  DOI: 10.11996/JG.j.2095-302X.2018050901 Abstract ( 69 )   PDF (3094KB) ( 332 )   Pedestrian detection has become a hot topic in the field of computer vision. Non-maximal suppression combined with hard threshold is the most common post-process method in pedestrian detection, whereas it is easy to cause false positive and false negative. As to this problem, this paper presents a pedestrian-object detection method based on similarity measurement. Firstly, Faster RCNN is used to build a series of candidate proposals among which initial selection is made based on non-maximal suppression. Then the authors create feature templates by target areas with high confidence, and make a further selection in the low-confidence proposals according to the feature similarity. Lastly, the detection results are composed of the reserved proposals and the templates. The experimental results from VOC, INRIA, Caltech datasets demonstrate that similarity measurement method can achieve higher pedestrian detection performance. Related Articles | Metrics

Select

Blind Restoration of Focus Blur Based on Spectrum Preprocessing and Improved Hough Transform LI Zhe, LI Jianzeng, HU Yongjiang, ZHANG Yan 2018, 39(5): 909-916.  DOI: 10.11996/JG.j.2095-302X.2018050909 Abstract ( 61 )   PDF (11901KB) ( 167 )   To improve the resolution of defocused blurred images, the paper presents a blind restoration algorithm of focus blur based on spectrum preprocessing and improved Hough transform. Firstly, the spectrum preprocessing strategy is improved to deal with the blur image spectrum map, and the impacts of noise on the detection of zero point dark circle is reduced. Then the algorithm of Hough transform circle detection is improved to reduce its complexity, meanwhile the accuracy of the estimation of the blur radius is enhanced. Finally, the authors take advantage of the mixed characteristic regularized restoration image model to restore the blur image iteratively, which makes the edge details of the restored image more focused. The experimental results show that the proposed method of blur radius estimation has less average error than other methods. The improved spectrum preprocessing strategy is more advantageous to the detection of zero dark circles. The improved algorithm of the Hough transformation circle detection algorithm has higher accuracy of the blur radius estimation. The proposed algorithm has a better recovery effect on defocused images taken by a small UAV out of focus on the camera. As for the blind restoration of focus blur images, the theoretical analysis and experiment validate the good robustness of the improved blur radius estimation method in this paper. Related Articles | Metrics

Select

An Infrared Image Colorization Algorithm Based on Local Linear Embedding and Fuzzy C- Means Clustering TIAN Jianyong, SHI Linjiang 2018, 39(5): 917-925.  DOI: 10.11996/JG.j.2095-302X.2018050917 Abstract ( 62 )   PDF (1435KB) ( 206 )   To deal with the problems of low definition and unnatural color after infrared image colorization, this paper introduces an improved local linear embedding algorithm into the application of infrared image colorization, and proposes an infrared image colorization that features local linear embedding and fuzzy c-means clustering. Firstly, by enlarging the neighborhood range and adding weight information, the algorithm improves the defect of the local linear embedding algorithm which is sensitive to sparse matrix. In the space characterized by pixel vectorization of infrared and color template, Nearest Neighbor Search is used to figure out the best match coefficient. The color of color template can be mapped onto the specific areas on infrared image by computing color value, then color transfer from the template to the targeted infrared image done. The improved fizzy C-average clustering is carried out to conduct color clustering on infrared image, and on the color clustering set, histogram equalization to equalize segmented color, after which equalized image is finally synthesized. After the simulation comparison between this algorithm and the other two infrared colorization algorithms, the result shows that the proposed infrared image colorization algorithm can achieve clearer and target-prominent colorization only by target infrared images and color templates. Related Articles | Metrics

Select

Study on Semantic-Tag System Constructing  Based on National Costume Pattern YIN Yukun1, ZHAO Haiying1,2 2018, 39(5): 926-932.  DOI: 10.11996/JG.j.2095-302X.2018050926 Abstract ( 59 )   PDF (729KB) ( 143 )   Due to the great diversity and rich connotation of national costume patterns, it’s super challenging to come up with a scientific and standard semantic-tag system. This paper proposes a semantic-tag system based on the folk classification model. Firstly, this is a hierarchical tagging system. Secondly, professional and public annotations are added into this system based on the folk classification model, which not only reflects the collaboration concept for tag system, but also enhances the professionality of tags. At last, this paper annotates the Phoenix pattern from Zhuang by the newly-created tag system, and makes an analysis and comparison in terms of the practicability and progressiveness of tag systems. Related Articles | Metrics

Select

Research on the Method of Tobacco Leaf Disease Spot Segmentation Based on Morphology and Wavelet Transform LIU Jianxin1, ZENG Qiang1, XU Ke2, WANG Yawei1 2018, 39(5): 933-938.  DOI: 10.11996/JG.j.2095-302X.2018050933 Abstract ( 106 )   PDF (455KB) ( 134 )   Tobacco leaf disease and insect spot segmentation is an important guarantee to improve the quality of tobacco leaves. The traditional segmentation method falls short of the desired accuracy and efficiency. Aimed at this problem, a method of Otsu combining morphological and wavelet transform to divide tobacco leaf spot is presented. Firstly, the background area is processed by mathematical morphology in Otsu to get the image of tobacco leaf. Then the leaf image is decomposed by wavelet coefficients, after which the decomposed image is to be reconstructed with low-frequency so as to undo noise effects. Finally, the disease spots will emerge after the quadratic segmentation of the image in Otsu. Thanks to the morphological opening-and-closing operation that can extract the brightness details of the image, thus this method can effectively reduce the impacts from background onto the disease-spot area, which is to improve the accuracy and efficiency of segmentation. Meanwhile, segmentation precision can be further raised by multi-scale wavelet resolving to overcome the effects from redundancy and noise. The images of different sorts of tobacco leaf spots experimented, the results show that Otsu can effectively segment the tobacco disease spot, and operate on the lesions in other plants. Related Articles | Metrics

Select

Feature Fusion Adaptive Target Tracking ZHONG Guochong, CHU Jun, MIAO Jun 2018, 39(5): 939-944.  DOI: 10.11996/JG.j.2095-302X.2018050939 Abstract ( 68 )   PDF (2227KB) ( 335 )   The classical visual single-target tracking method usually describes the tracking target with a single feature. But in the actual scene, the target is changed by the external factor such as light or its own changes such as deformation. In order to better describe the target, the HOG feature and CN feature are introduced firstly, and the traditional feature extraction method is used to train the respective correlation filter, and then the response graph is obtained by correlating filter with the respective feature. Finally, the weights of each response graph are obtained by using the difference method between actual response and expected response, and the final position of the target is obtained by adaptively fusion with each response graph, and their models are updated adaptively. The experiment selected 34 color video frame sequences from the common data set OTB 2013 to analyze and prove the different algorithms qualitatively and quantitatively. Compared with the best DSST algorithm, the average center error is reduced by 7.8 pixels. The success rate is improved by 1.2% and the accuracy is improved by 2.3%. The experimental results show that the algorithm has good tracking robustness and accuracy. Related Articles | Metrics

Select

An Efficient and Robust Method for Profile Error Evaluation of  Freeform Curves LI Yuehua, ZHOU Jingbo, LIU Lijian 2018, 39(5): 945-950.  DOI: 10.11996/JG.j.2095-302X.2018050945 Abstract ( 45 )   PDF (1030KB) ( 123 )   To obtain the profile error of the freeform curves, an efficient evaluation method is brought out which is based on root-finding of polynomial equations and real coded genetic algorithm (RCGA). Firstly, the optimization model for the profile error evaluation was established based on the least squares criterion. Then, the polynomial equations were constructed and the point to curve distance can be obtained effectively by solving the polynomial equations via the Halley iteration. After that, the optimization model was solved by the RCGA and the profile error was obtained. The computation results were also compared with the subdivision method. From the evaluation process, it can be seen that the proposed method is efficient and robust. The computing time is about 5% of that the subdivision method needs under the same condition. Thus, it is more suitable for evaluating the profile error of the freeform curves. Related Articles | Metrics

Select

Research of Three-Dimensional Drawings Expression and  System Implementation Based on MBD LV Cheng, GONG Lian, LIU Hui, WU Guoguo 2018, 39(5): 951-957.  DOI: 10.11996/JG.j.2095-302X.2018050951 Abstract ( 61 )   PDF (1024KB) ( 317 )   The main problems existing in the practical application of the existing three-dimensional drawing technology are analyzed. The design view, model and annotation partition display, integration annotation and other specific methods are proposed to solve the key problems such as lacking of clarity of three-dimensional drawings information and the definition of complex product information. In combination with the requirements of product information expression and data consistency in the digital environment, the relationship between geometry and non-geometry information is guaranteed by using the information structure tree. The detailed design scheme of the three-dimensional drawing system and the concrete realization method of the corresponding visualization function are given, and the three-dimensional drawing software system development based on ACIS and HOOPS joint platform is realized. In the three-dimensional drawing software system, the precision design of typical parts is realized, and the practicability of the system is verified. Related Articles | Metrics

Select

A New Algorithm for Extending B-Spline Curve with a Reference Curve ZHANG Zhiwei1, MU Guowang1, ZANG Ting1, DAI Shijie2 2018, 39(5): 958-962.  DOI: 10.11996/JG.j.2095-302X.2018050958 Abstract ( 75 )   PDF (1767KB) ( 137 )   For the problem of B-spline curve extension in computer aided geometric design (CAGD), a new algorithm is proposed such that the extended curve is similar to a given reference curve in shape. Firstly, the knot vector of the extended curve is determined by unifying the knot vector of the original curve and that of the reference curve. Secondly, the control vertices corresponding to the original curve are determined with B-spline unclamping algorithm. Finally, the new control vertices are determined with optimization method. The aim is to minimize the sum of squared distances between the control vertices of affine transformed reference curve and those of the extended curve. A two-stage algorithm is presented to solve this optimization problem. At the first stage, the affine transformation is determined with optimization method. And at the second stage, the new control vertices are calculated by applying the affine transformation. As a further improvement to the algorithm, a smoothing term is introduced at the second stage to make the extended curve smoother. Experimental results show that the extended curve by the proposed algorithm has similar shape to the reference curve to some extent, and the algorithm is practical and flexible. Related Articles | Metrics

Select

Retrieval of 2D Engineering CAD Drawings Based on Hashing YE Ying, ZHANG Qi, SU Zhiyong 2018, 39(5): 963-969.  DOI: 10.11996/JG.j.2095-302X.2018050963 Abstract ( 78 )   PDF (1018KB) ( 152 )   In the process of design innovation, a large number of companies use existing computer aided design (CAD) drawings as the basis for design reuse. In this paper, hash algorithm is applied to the retrieval of 2D engineering CAD drawings. The algorithm extracts geometry features of each component in the engineering CAD drawing based on ring partition, and the topology of local vector quantization pattern (T-LVQP) is proposed to extract the topological features of each component based on LBP operator. Then, all components in the drawings are classified into groups according to geometric features by the LBG algorithm, and the feature vector of each drawing is obtained via fused features based on the co-variance descriptor. Finally, the Hash sequence is generated by iterative quantization Hashing. The experimental results show that the algorithm has good performance in speed and accuracy for the retrieval of 2D engineering CAD drawings. Related Articles | Metrics

Select

Laplace’s Grid Deformation 3D Face Modeling Based on Kinect HOU Shouming1, DU Chengfei1, WANG Yang1,2, ZHANG Yuzhen1 2018, 39(5): 970-975.  DOI: 10.11996/JG.j.2095-302X.2018050970 Abstract ( 116 )   PDF (1337KB) ( 173 )   In order to create a realistic 3D face model in a fast speed, a Laplacian mesh deformation modeling method based on Kinect is proposed. The Kinect is used to obtain color and depth image information, perform bilateral filtering on the depth image, perform low-level vertex positioning on the color image, construct a standard 3D face model, and establish low, middle, and high levels for the vertices in the face model. In the hierarchical structure, Sibson local coordinate constraints are created through the positional relationship of the vertices in the low and middle levels; this constraint is used to construct the middle level vertices of the color image and the Laplacian mesh deformation of the standard 3D face model is combined with the depth information to obtain a realistic 3D face model. The experimental results show that the proposed algorithm is improved in the realism of modeling, and compared with the comparative algorithms, the length of modeling time is greatly optimized. Related Articles | Metrics

Select

A Blueprint of Graphics Subject 1. Department of Computer Science, Shanghai Jiao Tong University, Shanghai 200240, China; 2. College of Mechanical Engineering, Donghua University, Shanghai 201620, China; 3. School of Urban Design, W 2018, 39(5): 976-983.  DOI: 10.11996/JG.j.2095-302X.2018050976 Abstract ( 61 )   PDF (337KB) ( 165 )   China has made a strategic decision of “Double First-Class” construction in relation to university development, half of which refers to first-class discipline construction. Generally speaking, there are two dimensions for discipline assessment: One is academic dimension (scientific principle), or academic logic, which means that a discipline must have a clear research subject, a highly effective research method and a relatively independent knowledge system; the other is experience dimension (practical principle), or social need logic, which means that a discipline must meet a certain social demand. Based on a discipline, the First-class discipline is founded upon proper definition, orientation and classification. Thus, this paper will comprehensively explain some key issues toward sbuilding big graphics and draw a blueprint for developing a big graphics. Related Articles | Metrics

Select

Graphics Discipline Based on the Graphical Evolution PENG Zhenghong1, YU Haiyan2, JIAO Hongzan1, CAI Hongming3, HE Yuanjun3 2018, 39(5): 984-989.  DOI: 10.11996/JG.j.2095-302X.2018050984 Abstract ( 50 )   PDF (1740KB) ( 151 )   The paper reviews the need of graphs in the course of human adaptation to nature and transformation of nature, and the role graphs played in social development by looking back at how script and number originated from graphs. The paper explains the features, status and functions of the graph based on a four dimensional descriptive structure, including “shape”, “meaning”, “element” and “utility”, and also analyzes the evolution of graphs on these four dimensions. It is shown that the “shape” dimension is characterized with height, the “meaning” dimension with depth, the “element” dimension with fusion and “utility” dimension with penetration. Along this line of graphic evolution, the present study explicates the formation, transformation, and development of graphics, as well as what graphics refers to. In this sense, a framework of graphics is proposed based on elements of the graph. Related Articles | Metrics

Select

Changing and Developing of Connotation on Engineering Graphics YU Haiyan1, PENG Zhenghong2, HE Yuanjun3, WANG Shengze1 2018, 39(5): 990-995.  DOI: 10.11996/JG.j.2095-302X.2018050990 Abstract ( 128 )   PDF (331KB) ( 189 )   Engineering graphics is a discipline for technological expression and communication with engineering drawings. The rapid development of graphics computing as well as digital manufacturing has been changing engineering graphics for its present medium, application scope, communicating objects and even the definition of engineering drawing. These tremendous changes are refreshing the connotation of engineering graphics and at the same time are remodeling our conception of engineering representation and communication. This paper will try to discover common fundamental theory and analyze regularity and trend in the changing complex. The development orientation of engineering graphics is discussed and a knowledge system is constructed in line with digital manufacturing. Finally, suggestions for education orientation, series textbook planning and teaching pattern for engineering graphics are proposed. Related Articles | Metrics

Select

Research on the International Teaching System of Engineering Drawing CAO Qingyuan, NIU Wenjie, ZHAO Junyou, LI Jing 2018, 39(5): 996-1003.  DOI: 10.11996/JG.j.2095-302X.2018050996 Abstract ( 97 )   PDF (721KB) ( 149 )   The construction of international teaching system of engineering drawing aims at solving two problems: improving students’ ability to solve problems related to international projects, and improving the teaching quality of foreign students. This study conforms to the trend of manufacturing digitization, integrates 3D modeling and reconstructs the engineering drawing teaching contents, focusing on different national drawing standards including the model-based definition (MBD) drawing standards and their engineering applications. Different international teaching modes are respectively designed for the students both at home and broad. And based on the cloud classroom platform, online and offline mixed teaching program are designed. Related Articles | Metrics

Select

Practice Training Method Study of Machine 3D Surveying and Mapping  Based on Reverse Engineering XIA Hongmei, ZHEN Wenbin 2018, 39(5): 1004-1008.  DOI: 10.11996/JG.j.2095-302X.2018051004 Abstract ( 72 )   PDF (1282KB) ( 127 )   Carrying out machine 3D surveying and mapping practice training can help consolidate parts measuring and drawing skills, improve students’ ability to analyze and design expression, and enhance students’ ability of engineering practice. By introducing reverse engineering measurement technology, the objective of surveying and mapping practice, implementation process and the specific requirements were put forward. The principle of selecting surveying and mapping objects was put forward, measuring tools were selected, and 3D feature modeling and reverse reconstruction method were determined. The team leader’s responsibility system was planned. The comprehensive evaluation strategy of the group evaluation, the group self-assessment and the teacher’s evaluation was established. The detailed scoring criteria for group evaluation and teacher evaluation were formulated. The application of the practice training method shows that it is an effective way to enhance the students’ ability of utilizing modern design techniques and methods as well as their employability. Related Articles | Metrics

Select

Research and Practice on the Integration of CAD into Civil Engineering Drawing Teaching Through Assignment-Driven Approach WANG Yeming 2018, 39(5): 1009-1013.  DOI: 10.11996/JG.j.2095-302X.2018051009 Abstract ( 110 )   PDF (498KB) ( 186 )   Based on the assignment-driven approach, this paper studies and practices the civil engineering CAD teaching content integration to the civil engineering drawing course by optimizing the teaching system and improving teaching methods. Teaching practice shows that the integration of teachings by the assignment-driven approach can ensure the teaching quality of civil engineering drawing course, and the total class hours can be appropriately reduced. At the same time, the pertinence of CAD teaching is strengthened, the goal is more clear, and the students’ CAD practical ability has been greatly improved. Related Articles | Metrics