Table of Contents

31 December 2018, Volume 39 Issue 6 Previous Issue    Next Issue

---

For Selected:

Download Citations EndNote Ris BibTeX

Toggle Thumbnails

Select

Quartic Bézier Surface with Shape Parameters on Triangular Domain YAN Lanlan1, FAN Jiqiu1, MA Li2 2018, 39(6): 1015-1021.  DOI: 0.11996/JG.j.2095-302X.2018061015 Abstract ( 48 )   PDF (272KB) ( 105 )   This paper aims at adjusting the shape of the quartic triangular Bézier surface without changing the control points. Based on the idea of defining adjustable surfaces by adjustable control points, starting from a geometric perspective, a set of quartic bivariate basis functions with two parameters are constructed and a new triangular patch determined by fifteen control points is defined. The new surface not only inherits the properties of the quartic triangular Bézier surface, but also possesses two parameters which can be used to adjust its shape. Compared with the existing method of constructing triangular Bézier surface whose shape is adjustable, the method provided here defines the new surface from a geometric rather than an algebraic perspective, hence the introduced parameters have definite geometric effect, and the method here does not increase the degree of the basis functions. For convenient application, the G1 smooth join condition of the surface is given. The legends show the correctness and validity of the method. Related Articles | Metrics

Select

Superpixel Generation Algorithm of SAR Image Based on Edge Strength Feature and Linear Spectral Clustering CHEN Yuan1, ZHAO Lingjun1, KUANG Gangyao1, ZHAO Liwen2 2018, 39(6): 1022-1027.  DOI: 10.11996/JG.j.2095-302X.2018061022 Abstract ( 80 )   PDF (928KB) ( 124 )   In the face of massive data of high-resolution SAR images, the academic community widely simplifies image analysis processing through the superpixel-based approach. The superpixel segmentation algorithm which is generally suitable for optical images is not ideal for SAR images with speckle noise. Improving the existing superpixel generation algorithms for SAR image has been a hot topic among the scholars. In this paper, we discussed the feasibility of introducing edge strength feature into the superpixel segmentation algorithm. By combining the edge strength feature with the linear spectral clustering method, a novel superpixel generation algorithm (e-LSC) for SAR image was proposed. Compared with several typical superpixel generation algorithms on the simulated SAR image and the real SAR image, it is verified that the segmentation performance of e-LSC algorithm on the boundary adherence and the regularization of the homogeneous area is improved. Related Articles | Metrics

Select

Multiple Instance-Based Learning Method for Imbalanced Data in Hyperspectral Target Representation SHAN Jiaxin, GONG Zhiqiang, ZHONG Ping 2018, 39(6): 1028-1035.  DOI: 10.11996/JG.j.2095-302X.2018061028 Abstract ( 83 )   PDF (1353KB) ( 193 )    Target representation is the key process for hyperspectral target detection. Many methods have been proposed for better target representation. Among these methods, multiple instance-based learning method (MIL) is an effective one as it does not require pixel-level semantic labels. However, traditional MIL-based hyperspectral target representation methods usually cause the instance-level data imbalance because of the limited target instances and too many background instances in positive bags, leading to poor performance on hyperspectral target representation. To overcome this problem, a data imbalanced multiple instance learning-based method is proposed in this paper. First, a positive sample set with the most probably positive sample in each package will be constructed; then, new positive samples will be synthetized to increase the proportion of positive samples in the positive packages, balancing the positive and negative samples in positive packages, improving the representational ability. Experiments over real-world hyperspectral dataset validate the effectiveness of the proposed method and the experiment results show that the proposed method can enforce the balance of the positive packages and learn target representation more accurately which improves the target detection performance. Related Articles | Metrics

Select

Research of Supervised Feature Selection Algorithm Based on  Structured Multi-View Sparse Regularization SHI Caijuan, DUAN Changyu, GU Zhibing 2018, 39(6): 1036-1041.  DOI: 10.11996/JG.j.2095-302X.2018061036 Abstract ( 54 )   PDF (407KB) ( 113 )    In order to effectively utiliz the multi-view data information and enhance the feature selection performance, the structured multi-view sparse regularization was constructed, based on which a novel supervised feature selection method, namely structured multi-view supervised feature selection (SMSFS), was proposed. SMSFS could simultaneously consider the importance of each view features and the importance of individual feature in each view to combine the multi-view data information effectively in the feature selection process, and then to boost the supervised feature selection performance. Because the objective function of SMSFS is non-convex, an effective iterative algorithm was proposed to solve the objective function. The proposed structured multi-view supervised feature selection method SMSFS was applied into image annotation task and extensive experiments were performed on NUS-WIDE and MSRA-MM2.0 image datasets. The proposed method SMSFS was compared with other feature selection methods and the experimental results demonstrated the effectiveness of SMSFS, which means that it could effectively utilize the multi-view data information to boost the feature selection performance. Related Articles | Metrics

Select

A Fall Detection Method Based on CNN and Motion Features  of Human Elliptical Contour DENG Zhifeng, MIN Weidong, ZOU Song 2018, 39(6): 1042-1047.  DOI: 10.11996/JG.j.2095-302X.2018061042 Abstract ( 103 )   PDF (1437KB) ( 296 )   In order to solve the problems of the instability of the traditional method of using geometric features to detect falls, and  the difficulty to distinguish some similar activities, a fall detection method based on convolution neural network (CNN) and the motion features of the elliptical contour of  human body is proposed. First, this method uses the Gauss mixture model to detect the human target and find out the minimum external elliptical contour. Then, the three features of the long and short axis ratio, the orientation angle and the vertical velocity of the human body’s centroid extracted in each frame’s elliptical contour, are fused into a motion feature based on time series. Last, a shallow CNN is then trained to detect falls and distinguish some similar activities. Experiment results show that our method overcomes the instability of geometric features and therefore enhances the detection rate compared with the existing methods. Related Articles | Metrics

Select

A Detail Enhancement and Denoising Algorithm of High Dynamic Range Infrared Image Based on Double Guided Image Filter LIU Kejia, MA Rongsheng, PANG Yuning 2018, 39(6): 1048-1054.  DOI: 10.11996/JG.j.2095-302X.2018061048 Abstract ( 139 )   PDF (2957KB) ( 246 )   Focusing on the noise amplification, insufficient enhancement of small details and excessive enhancement of edge in the process of high dynamic range infrared image compression and detail enhancement, a novel detail enhancement and denoising method based on double guided image filtering is proposed in the present study. We first applied GIF to obtain two groups of base images and detail images. The base image with low ε is used as an estimate of denoised base component and correspondingly the detail image as the noise estimation. Thus, the difference between the two detail images can be logically used to estimate the denoised detail. After the two estimated components are processed and compressed into the display range by our modified automatic gain control method respectively, we recombine the two parts and obtain the enhanced and denoised image. An optimization model based on classification statistics of gray value convergency in detail pixels is also presented, which provides reasonable numerical range of the critical parameter ε in GIF. The experimental evaluation shows that the algorithm can accurately choose key parameters and improve the slight details and enhance edges while highlighting details and reducing noises. Furthermore, our proposed method is characteristic of being real-time, requiring simpler models and fewer parameters. Related Articles | Metrics

Select

Salient Detection of 360 Panorama Based on Multi - Angle Segmentation SU Qun1,2, LIN Chunyu1,2, ZHAO Yao1,2, LI Yaru1,2, LIU Meiqin1,2 2018, 39(6): 1055-1061.  DOI: 10.11996/JG.j.2095-302X.2018061055 Abstract ( 125 )   PDF (1703KB) ( 241 )   Unlike conventional 2D images, 360 panorama contains all the visual information of the current space, so it has a wide range of applications in video surveillance and virtual reality. However, a certain angle is available at a certain time. Therefore, the significant region detection of the 360 panorama is very important to visual angle prediction. To solve this problem, we  propose a multi-angle segmentation based 360 panoramic image saliency detection. Firstly, the panoramic images are cut at multiple angles, and the segmentation results are projected to the cube to remove certain distortion. Then, the salient calculation is conducted for each cube surface through dense and sparse reconstruction. Finally, the saliency images of each surface are projected to the rectangular of the warp and weft mapping, and multi-angle fusion is made to obtain the final salient figure. The results of the 360 panorama test by manual annotation show that the algorithm can accurately detect the saliency and is better than the other methods for the saliency detection of the 360 panorama. Related Articles | Metrics

Select

Hyperspectral Images Classification Based on Multiview Marginal  Discriminant Projection PAN Heng, HE Jinrong, LING Yu, REN Silin 2018, 39(6): 1062-1068.  DOI: 10.11996/JG.j.2095-302X.2018061062 Abstract ( 87 )   PDF (605KB) ( 156 )   Hyperspectral images classification is a research hotspot in the remote sensing field. The key point is to improve the classification accuracy by taking the advantage of spectral-spatial features of hyperspectral images, which fuse the spectral information and spatial information of each pixel in the hyperspectral image simultaneously. This paper employed multiview subspace learning for feature reduction with the problems of high feature dimension and redundant information of hyperspectral images, and proposed a graph regularized multiview marginal discriminant projection (GMMDP) algorithm. The multiview feature reduction algorithm took the spectral features of each pixels as a view and spatial features as another view, then searched the optimal discriminant common subspace by optimizing the projection direction of each view. Experiments on the open dataset showed that multiview learning had a significant advantage in spectral-spatial classification of hyperspectral images. Among all multiview dimensionality reduction algorithms, our GMMDP had the highest classification accuracy. Related Articles | Metrics

Select

Semantic Segmentation of Multi-Scale Fusion Aerial Image Based on  Attention Mechanism ZHENG Guping, WANG Min, LI Gang 2018, 39(6): 1069-1077.  DOI: 10.11996/JG.j.2095-302X.2018061069 Abstract ( 114 )   PDF (1339KB) ( 207 )    In aerial images, there is significant difference between the scales of different objects in the same scene, single-scale segmentation often hardly achieves the best classification effect. In order to solve the problem, we proposes a multi-scale fusion model based on attention mechanism. Firstly, extract multi-scale features of the aerial image using dilated convolutions with different sampling rates; then utilize the attention mechanism in the multi-scale fusion stage, so that the model can automatically focus on the appropriate scale, and learn to put different weights on all scale and each pixel location; finally, the weighted sum of feature map is sampled to the original image size, and each pixel of aerial image is semantically labeled. The experiment demonstrates that compared with the traditional FCN and DeepLab method, and other aerial image segmentation model, the multi-scale fusion model based on attention mechanism not only has higher segmentation accuracy, but also can analyze the importance of different scales and pixel location by visualizing the weight map corresponding to each scale feature. Related Articles | Metrics

Select

Rail Detection Algorithm Based on Hough Transform and  Catmull-Rom Spline Curve JIANG Ze, DONG Yu 2018, 39(6): 1078-1083.  DOI: 10.11996/JG.j.2095-302X.2018061078 Abstract ( 115 )   PDF (1375KB) ( 223 )   Focusing on the problem of low accuracy of the rail identification in the existing rail detection algorithm, this paper proposes an algorithm based on Hough transform and Catmull-Rom spline curve. Firstly, the image is denoised and pre-processed, and Canny edge detection algorithm is used for edge detection. Then Hough transform is used to detect the straight track, and the track model is determined according to the vanishing point of the straight track. Finally, the curved track is searched for the characteristic points of the curved track using the bifurcation window. The selected feature points are fitted with Catmull-Rom spline curve fitting curves. Experiments show that the algorithm not only can accurately fit the rail curve, but also displays good accuracy and robustness. Related Articles | Metrics

Select

Design and Implementation of Tsinghua University Occlusion Image Database GAO Lei, LIU Chenhao, MA Huimin 2018, 39(6): 1084-1091.  DOI: 10.11996/JG.j.2095-302X.2018061084 Abstract ( 75 )   PDF (4567KB) ( 196 )   Occlusion is a common phenomenon in images characteristic of complex scenes. Discovering the pattern of how occlusion affects image cognition and establishing a cognition model insusceptible to occlusion is closely related to the utilization of computer vision technologies, and it is also an important and pressing scientific problem to be solved. By analyzing occlusion in complex scenes and how occlusion affects image cognition, this paper established the Tsinghua University Occlusion Image Database for evaluating the anti-occlusion performance of algorithms and studying image cognition model. Firstly, based on occlusion’s impact on image cognition, this paper proposed a 4-dimension occlusion attribute including occluded part, occluded area, occlusion relationship and occlusion complexity, as well as a quantification standard for the extent of occlusion. Then we proposed a novel hierarchical dataset structure, based on which the database could be constructed. This paper established TUOD database which consists of 2 100 images extracted from PASCAL VOC and Image Net databases. Those images covered 4 major object types: aeroplane, car, person and animal. An experiment was conducted to analyze the influence of each dimension of occlusion attribute on the performance of Faster R-CNN using images in TUOD. As is shown in the aforementioned experiment, TUOD database can provide quantitative criteria for the anti-occlusion performance of algorithms and thus it is highly practical and lays the foundation for improving the anti-occlusion performance of object recognition algorithms in complex scenes. Related Articles | Metrics

Select

A New Denoising Algorithm of Total Variation Block Matching Sonar Images XU Huipu, ZHU Lijuan 2018, 39(6): 1092-1097.  DOI: 10.11996/JG.j.2095-302X.2018061092 Abstract ( 91 )   PDF (2289KB) ( 137 )   The multiplicative speckle noise is widely found in sonar images, which seriously affects the image quality. The noise is characterized by rayleigh distribution. Aiming at this kind of noise, in combination of a total variation algorithm and the design ideas of the denoising algorithm of three dimensional block matching image (BM3D), a new denoising algorithm of total variation block matching sonar images is proposed. First, the algorithm uses 2-norm to complete the block matching group of noise sonar images. Then, the total variation algorithm is used for filtering and denoising of image block after grouping, due to the characteristics of fuzzy sonar image, less information of texture details, etc. Finally, the image after denoising is obtained by means of weighted clustering of the filtered image block. The experimental results show the effectiveness of denoising about the proposed algorithm in this paper. Moreover, it has better denoising effect compared with the classical Lee filter, Frost filter, BM3D and total variation algorithm. Related Articles | Metrics

Select

A Registration Method for Large-Angle PointClouds LI Jian1, YANG Jingru1, HE Bin2 2018, 39(6): 1098-1104.  DOI: 10.11996/JG.j.2095-302X.2018061098 Abstract ( 79 )   PDF (1425KB) ( 181 )   To the problem of traditional registration algorithm are difficult to get the desired effect in large-angle pointcloud registration. We proposed a registration method based on exact correspondence feature point pairs and its K-neighbour pointclouds. Firstly, calculate the FPFH of the pointclouds separately, establishing correspondences between point clouds According to the eigenvalues; Then remove the erroneous matching point pairs by RANSAC, and obtain a relatively accurate set of feature point pairs; Moreover, using KD-tree search get the R-Rad region of the feature point pairs respectively, and applying ICP to obtain the optimal convergence of pointclouds. Finally, applying the ICP relative position relationship to the original pointclouds to get the final registration result. Through registration testing and comparison of the Stanford Dragon, Happy Buddha pointcloud models, and Gypsum data scanned by Kinect, The experiment shows that this method can effectively solve the registration problem of pointclouds with large angle transformation, its a 3D pointclouds registration method with high accuracy and robustness. Related Articles | Metrics

Select

A Self-Adaptive Genetic Algorithm for Labeling Line Drawings of  Planar Objects XIONG Siying, DONG Lijun 2018, 39(6): 1105-1111.  DOI: 10.11996/JG.j.2095-302X.2018061105 Abstract ( 56 )   PDF (666KB) ( 114 )   This paper improves the genetic algorithm for labeling line drawings presented by Richard Myers in the following areas: self-adaption parameter adjustment method was used, the hybridization rate and mutation rate of individuals with high fitness in the same generation were dynamically changed, and the rate of hybridization and mutation of individuals with lower fitness was set as a fixed value; the constraints were established when the initial population was created, with the aim of improving the uncertainty of the initial population coverage space and the relative irrationality of the individual distribution; the fitness function of the genetic algorithm was modified so that the selection operator with the individual fitness as the index could correctly guide the algorithm to search the solution space. The genetic algorithm was employed to mark six different line drawings, the parameter a and c in the formula of hybridization rate and mutation rate were used as experimental variables, the change tendency of the algorithm’s mark success rate curve was analyzed, and the influence of operator parameter setting on the performance of genetic algorithm was discussed. The results show that c belongs to interval [0, 0.05] and a belongs to interval [0.8, 1.0] and a is the optimal parameter setting of the genetic algorithm for labeling line drawings. Related Articles | Metrics

Select

The Strategy of Web Interface Design Based on Internet Emotion GUO Wenjing, LI Yueqiong 2018, 39(6): 1112-1116.  DOI: 10.11996/JG.j.2095-302X.2018061112 Abstract ( 66 )   PDF (6796KB) ( 155 )   The rapid development of network technologies and hardware devices has brought a great change in reading and thinking habits of Internet users, which shows more and more feminine thinking characteristics, namely, sensibility, experience and the decentralization of the Internet. Actually, the feminine thinking of the Internet reveals the user’s needs in the aspects of visual perception, emotional interaction and multiple accesses. The innovation of web interface design is to provide users with better immersive experience and service. Therefore, grounded on the examination of the core process of user behavior, this paper explores innovative web interface design strategies and implementation methods, focusing on the phenomenon of feminine thinking in the Internet, investigating the characteristics of Internet users’ needs, and analyzing examples  in relation to  improvement of information appeal, promotion of user emotional resonance, and establishment of diversified and intelligent services. Related Articles | Metrics

Select

3D Model Registration Based on SURF Feature Extraction of  Projection Images TONG Lijing, LIU Bowen 2018, 39(6): 1117-1122.  DOI: 10.11996/JG.j.2095-302X.2018061117 Abstract ( 112 )   PDF (1991KB) ( 246 )   In order to solve the problems with the traditional 3D model registration methods, such as the higher requirements for the initial locations of the two point clouds and the lower accuracy of model registration sometimes, a 3D model registration method based on SURF feature extraction of the two 3D model projection images is proposed. Firstly, the range of the projection image is determined by the 3D model data, and the model grid which each projection image pixel belongs to is deduced. Thus the two-dimensional projection image can be calculated by the mapping relationship from the projected image to the texture image. Then, the SURF feature points and the eigenvalues are calculated for the two projection images respectively. The feature matching is performed according to the SURF eigenvalues. Next, the feature point pairs in the two 3D models are extracted through the mapping relations between the 3D models’ grid vertices and the projection image pixels. Finally, the two 3D model registration is implemented through the transformation matrix which is calculated from the matched feature point pairs in the two 3D models. The experimental results show that this method can improve the registration accuracy effectively and has good robustness under the condition of little change in registration time. Related Articles | Metrics

Select

3D Scene Reconstruction System Based on Depth Image ZHANG Zhilin, MIAO Lanfang 2018, 39(6): 1123-1129.  DOI: 10.11996/JG.j.2095-302X.2018061123 Abstract ( 82 )   PDF (830KB) ( 153 )   The reconstruction of three-dimensional scenes is currently a research hotspot in computer graphics and visual fields. Firstly, this paper analyzes the principle of depth image acquisition by Kinect v2 (Kinect for Windows v2 sensor), and explain the source of depth image noise. Then according to the principle of obtaining the depth image, an algorithm is designed to crop the point cloud sampling range. Secondly, the point cloud outliers are removed to fill the voids of the cloud to improve the reconstruction quality. Common three-dimensional scene reconstruction mostly uses a global three-dimensional body scheme of Kinect Fusion. This scheme can only reconstruct scenes in a small area. An ICP algorithm for point cloud matching of large scenes is designed for this purpose. Finally, surface reconstruction is performed on the point cloud to realize a low-cost and accurate three-dimensional reconstruction system for large scenes. Related Articles | Metrics

Select

Uncertainty Network Visualization Method Based on  Multilevel Graph Layout Algorithm CHEN Bingkun, ZHOU Hong 2018, 39(6): 1130-1138.  DOI: 10.11996/JG.j.2095-302X.2018061130 Abstract ( 99 )   PDF (1691KB) ( 144 )   Visualizing uncertainty networks has become a hot topic in the field of data visualization in recent years, because more and more data contains uncertainties. In the uncertainty visualization research, a method based on the probability graph layout is fairly effective by using an anchoring algorithm to make good visualization of uncertain networks and reflect the probability distribution of the networks. However, the method has two limitations, the high time complexity and unstable layout. To address these issues, we propose an uncertainty network visualization method based on multilevel graph layout algorithm. This method combines the multilevel graph layout algorithm with anchoring algorithm, and improves the limitations of the original method. Experimental results demonstrate that our improved algorithm has higher time efficiency compared with the original method, and the generated graph structure is more stable. Related Articles | Metrics

Select

Review of OpenBIM and Its Engineering Application JIANG Shaohua, WU Zheng, WANG Na, JIANG Liping, HAN Yunwei 2018, 39(6): 1139-1147.  DOI: 10.11996/JG.j.2095-302X.2018061139 Abstract ( 153 )   PDF (325KB) ( 434 )   The expansion of scale and the increase of complexity of buildings have imposed higher requirements onto collaboration among different stakeholders. How to realize a better information interaction among multiple disciplines and different software platforms becomes a key problem in the collaborative process. OpenBIM, as the common standard of information exchange, can well meet the needs of information interaction among different softwares and improve the efficiency and accuracy of collaboration. At present, research related to OpenBIM has received extensive attention from scholars at home and abroad, but there is still lack of comprehensive review on OpenBIM. In this paper, OpenBIM and its related standards and softwares are introduced by analyzing related websites and papers. Furthermore, the application of OpenBIM in engineering projects is analyzed from the perspectives of design, construction and operation. Finally, the paper discusses the deficiencies of OpenBIM in the application process and the direction of further development. The systematic analysis of the theory and practice of OpenBIM in this paper can provide support for its further research and application. Related Articles | Metrics

Select

Application of BIM Technology in the Manufacturing Stage of Precast Elements of Prefabricated Construction XU Zhao, ZHAN Xinkui, ZHANG Xing 2018, 39(6): 1148-1155.  DOI: 10.11996/JG.j.2095-302X.2018061148 Abstract ( 228 )   PDF (404KB) ( 379 )   In order to have a systematic and clear understanding of the application of BIM technology in the production stage of prefabricated building components, based on a large number of literature, we reviewed the production process and process flow of prefabricated components. Combined with the statistical analysis of the literature, the application of BIM related information technology in the production stage of prefabricated components is introduced, and the research status of information delivery in the production stage of prefabricated components is systematically concluded. Finally, this paper summarizes the gap of related researches between home and abroad, and puts forward the corresponding research suggestions. By reviewing the previous study on the application of BIM and information technologies, the paper also discusses the challenges and bottlenecks for information management in the manufacturing stage of precast elements, as well as future orientation of BIM technology application. Related Articles | Metrics

Select

A Review on Research and Applications of BIM-Based Construction Safety Compliance Checking WU Songfei, DENG Yichuan, SHEN Qiyu, LUO Dehuan 2018, 39(6): 1156-1164.  DOI: 10.11996/JG.j.2095-302X.2018061156 Abstract ( 157 )   PDF (367KB) ( 220 )   Automatic safety compliance checking integrated with BIM can significantly enhance management efficiency and reduce the occurrence of safety accidents. Currently, the high frequency of construction accidents are not alleviated, which has seriously affected the life and property security of our people. Although research on safety management has been increasing in recent years, there is no review for the current research on safety compliance checking. This paper reviews the related literature in ten years. Domestic and foreign researches and safety checking platforms based on BIM are reviewed on rules translation, BIM model preparation, rule execution and checking results from the perspective of relevant technology and application. The application domain and platform of safety compliance checking were introduced. Finally, the existing problems in the process of safety compliance checking were discussed and the corresponding solutions proposed for facilitating further automation of safety compliance checking. Related Articles | Metrics

Select

Research on Service Composition Execution Engine Framework for  Cloud Manufacturing XIAO Gang1,2, XIANG Zherui1, ZHANG Yuanming2, ZHANG Zhenjie1, LU Jiawei2, GAO Fei2 2018, 39(6): 1165-1174.  DOI: 10.11996/JG.j.2095-302X.2018061165 Abstract ( 49 )   PDF (820KB) ( 120 )   In the cloud manufacturing model, manufacturing resources are encapsulated into manufacturing services and they meet users’ complex needs in service composition. Aiming at the efficiency, correctness and dynamic of the implementation requirements of cloud manufacturing service composition, Service Composition Execution Engine Framework for Cloud Manufacturing are proposed. By parsing cloud manufacturing service composition description file, this paper constructs service composition nodes and service composition dependencies and establishes the service composition node parameter association relationship and summarize the corresponding execution rules. The dynamic implementation of Manufacturing Service Compositions is carried out through service composition execution algorithm based on execution status change. Finally, an example of a cloud manufacturing service composition execution engine for the elevator industry alliance is given, which verifies the feasibility and effectiveness of the framework. Related Articles | Metrics

Select

Research on Shape Design Method of Ceramic Tea Set Based on User Intention WANG Nianwen1, QU Ruidan2 2018, 39(6): 1175-1182.  DOI: 10.11996/JG.j.2095-302X.2018061175 Abstract ( 139 )   PDF (5427KB) ( 185 )   Focusing on the problems of the old and single shape of ceramic tea set molding, the design method of ceramic tea set based on user’s perceptual intention is put forward. According to the theory of the perceptual intention, the quantitative relationship between user’s perceptual intention and the form elements of ceramic tea set is examined by adopting qualitative and quantitative research methods. Through the analysis of the shape elements of the ceramic tea sets, the teapot is defined as the main research object. We combine semantic differential method, factor analysis method, and multiple linear regression analysis method to detect the consumers’ perceptual evaluations on the form of ceramic teapot. The data statistics and analysis are employed to quantify the corresponding relationship between the user’s perceptual intention and the form design of ceramic teapot, and the correctness of the method is s verified by a design example. The results of the research providea new method of user-centered product form design, which has some implications for the form design of ceramic tea set for the users’ intention preferences. Related Articles | Metrics

Select

Metadata Construction of Digital Collection of Traditional Costumes ZHOU Wei1, ZHAO Haiying1,2 2018, 39(6): 1183-1191.  DOI: 10.11996/JG.j.2095-302X.2018061183 Abstract ( 113 )   PDF (645KB) ( 155 )   In the process of current traditional national costume metadata digital collection, there is no uniform standard and specification, and the collected metadata does not carry on the deep excavation of cultural connotation. Firstly, based on the international common DC metadata, the basic elements of digital collection of traditional national costume are extracted. Then the basic elements of the traditional national costume culture are deeply excavated and expanded. At the same time, a contrastive mapping with clothing, embroidery and textile picture metadata is made, and a set of cultural ontology, connotation mining, and the excavation of the connotation are constructed. The metadata of multi-layer and extensible national costumes is described in digital color. Finally, with the bat pattern batik back fan as an example, the annotation process of digital collection metadata of traditional national costume is illustrated. Through the RDF/XML metadata annotation and SparQL query metadata simulation, the paper implements a set of more operational specifications on  the digital collection of traditional national costumes. Related Articles | Metrics

Select

Research on Personalized Product Configuration in Cloud  Manufacturing Environment TONG Xiaowei1, ZENG Sitong1, LIU Yanbin2 2018, 39(6): 1192-1199.  DOI: 10.11996/JG.j.2095-302X.2018061192 Abstract ( 62 )   PDF (641KB) ( 119 )   A personalized product configuration technology framework for cloud manufacturing is proposed in this article,analyzing the typical process of product configuration under cloud manufacturing, and  summarizing the characteristics of participants and manufacturing resource organizations in the cloud manufacturing environment, including the need to balance the interests of different participants in the product configuration process and cover the different attributes of different manufacturing service instances during product configuration solution. In addition, we also expound on solutions to the three key issues, including cloud service model for product configuration, preliminary product configuration based on association rule mining, and product integrity configuration based on ant colony algorithm, providing a new idea for personalized product configuration in the cloud manufacturing environment. The product configuration of the wheel loader is used as an example in the process of model design and case solving, which demonstrates the effectiveness and feasibility of this method. Related Articles | Metrics

Select

Application of Middle-out Design Based on Multi-Body Method SONG Hongxia 2018, 39(6): 1200-1206.  DOI: 10.11996/JG.j.2095-302X.2018061200 Abstract ( 58 )   PDF (1195KB) ( 116 )    Generally, there are two alternative design approaches: top-down and bottom-up. At present, the skeleton top-down design has been widely studied, but it is too abstract and not easy to grasp, and meanwhile often ignores the application of existing resources and the role of the location and features of the parts in the design of related parts. In addition, the bottom-up design is detached from the design layout, resulting in low efficiency. To solve the problems, a modular middle-out design method based on 3D multi-body is proposed. Firstly, in accordance with structure characteristics of different kinds of products, types of multi-body layouts are described, and layout approaches are introduced briefly. Then, the most important issue of parameter correlation in middle-out design is discussed in detail, and subsequently the problem of how to embed the design results generated by the design accelerator into the smart layout part is explored, so the reverse design idea is realized as the terminal design requirements control the front-end design. Consequently, the correlation between dynamic characteristics and structure as well as parameters is created effectively. Finally, combined with the typical design case, the application of middle-out design method is illustrated. The result shows that the middle-out modeling approach is feasible and effective. Related Articles | Metrics

Select

Design and Development of Engineering Graphics Teaching System on Mobile Devices Based on the Augmented Reality Technology YI Peng, LIU Yancong, SHI Yongjun, QIN Zhen, ZHANG Zongbo 2018, 39(6): 1207-1213.  DOI: 10.11996/JG.j.2095-302X.2018061207 Abstract ( 96 )   PDF (5502KB) ( 176 )    Supported by the currently rapid development of virtual reality technology, in order to improve the sense of drawing set as the goal in engineering graphics course, the augmented reality technology was introduced into curriculum teaching and auxiliary teaching system on mobile devices as application platform was developed. In this system, the real scene of plane view was combined with virtual 3D models. The coupling and interaction experience reality was enhanced by a high level visual superposition. The sense of drawing can be set up as an efficient conversion bridge between the imaging and three-dimensional solid. By using such bridge, the acceptable degree of abstract three dimensional model and the learning interest were promoted. With the lecture and the guidance after class, students will consciously strengthen sense of figure interpretation in the view of cognitive function. The reform of teaching mode and resource discovery will help to promote the development of engineering graphics education in future. Related Articles | Metrics

Select

The Teaching Reform and Practice of Engineering Drawing Based on  the System Engineering CHEN Liang, WU Lingling, ZHANG Ruiqiu, XIONG Wei, QIN Zhinan 2018, 39(6): 1214-1219.  DOI: 10.11996/JG.j.2095-302X.2018061214 Abstract ( 98 )   PDF (15298KB) ( 92 )   By combining the Hall three-dimensional structure with the teaching system of engineering drawing, this paper analyzes the interrelationships among course hours, teaching contents and teaching methods through the perspectives of time dimension, knowledge dimension and logical dimension in a systematic and comprehensive way. Moreover, under the guiding of new engineering disciplines, we present some new teaching methods and teaching skills in engineering drawing course, including mobile learning, seminar teaching, innovative case teaching, immersive learning and so on. Our teaching practice has demonstrated that these reform measures can significantly improve teaching quality and effectiveness. Related Articles | Metrics

Select

Construction of Assessment System of CAID Course Aiming at Training Comprehensive Quality of Students LIU Jing, LIU Yancong, CAO Qingyuan, ZHANG Zheng 2018, 39(6): 1220-1224.  DOI: 10.11996/JG.j.2095-302X.2018061220 Abstract ( 62 )   PDF (681KB) ( 120 )    In order to adapt to the requirements of the development of industrial design discipline, a diversified assessment system of CAID course aiming at training comprehensive quality of students is proposed to solve the problems in the current assessment mode. Through establishing the process assessment mechanism and implementing diversified assessment guidelines, the present study incorporates process evaluation, design theory examination, assessments on practicing ability and comprehensive quality into the entire teaching process, aiming to improve students’ learning autonomy and enthusiasm in connection with students’ interest, so as to nurture and improve industrial design students’ comprehensive quality and innovativeness. Related Articles | Metrics

Select

Teaching Resource Construction of Graphics Based on  the Characteristics of Contemporary College Students WANG Shaoqin, YANG Zhun, LIU Xiaoran 2018, 39(6): 1225-1230.  DOI: 10.11996/JG.j.2095-302X.2018061225 Abstract ( 83 )   PDF (6844KB) ( 87 )   With the development of the times, computers, network and mobile phones have become important learning tools for students. Based on the characteristics of contemporary college students, Beijing University of Civil Engineering and Architecture combines the traditional teaching methods and internet media, classroom teaching and afterschool activities, as well as teaching content and contemporary development, and conducts various teaching resource constructions of graphics to create the modern graphic learning environment and fully stimulate the learning interest of students. In addition, through the participation in and practice of various kinds of graphic resource constructions, the comprehensive quality of students can also be enhanced while they make progress in course learning. Related Articles | Metrics

Select

Teaching and Practice Reform of Steel Structure Bridge Based on  BIM+VR Technology WEI Xing, JU Yunhua 2018, 39(6): 1231-1238.  DOI: 10.11996/JG.j.2095-302X.2018061231 Abstract ( 104 )   PDF (2191KB) ( 247 )   In order to improve the existing teaching effect of the steel structure bridges course in undergraduate colleges, and adapt to the new trends of information reform and development in the fields of education and construction industry, concerning professional, practical and difficult characteristics of the course, exploratory reform of the course’s teaching practice with combining building information models (BIM) and virtual reality (VR) technology was researched in our school. The BIM technology and VR technology were integrated into all aspects of classroom teaching and practice teaching to establish a new interactive teaching system where students autonomously study and actively explore with teachers collaboration and guidance. Taking a steel truss practical design which is a very important part of the steel structure Bridges course as an example, the necessity, feasibility and effectiveness of introducing BIM and VR technology into the steel structure bridge curriculum reform were demonstrated. The application of Revit, Navisworks and Fuzor software to establish building information model, carry out structural analysis, construction process simulation and collision check, as well as establish the practical path and practice process of virtual reality experience environment was introduced. The difficulties in applying the BIM technology and VR technology into the teaching and practice curriculum of steel bridges were summarized, and some effective countermeasures were proposed in order to optimize the teaching environment. It is hoped that this can break through the current teaching predicament, improve the effectiveness of teaching and learning, and enhance the quality of teaching and learning. At the same time, these useful explorations and practices will provide reference and guide for teaching practice of other similar related courses reform, and point out the direction for the subsequent reform and exploration of curriculum teaching practices. Related Articles | Metrics