Table of Contents

28 February 2021, Volume 42 Issue 1 Previous Issue    Next Issue
---
Contents
Image Processing and Computer Vision
Computer Graphics and Virtual Reality
Digital Design and Manufacture
BIM/CIM
Industrial Design
Total to Discuss


For Selected:

Download Citations EndNote Ris BibTeX

Toggle Thumbnails

Contents

Select

Contents of the 1st Issue of 2021 2021, 42(1): 0-0.  Abstract ( 443 )   PDF (220KB) ( 122 )   CONTENTS Image Processing and Computer Vision Locally adjusted age estimation based on deep learning and directed acyclic graph SVM ······································································································ LI Jun, YANG Ya-zhi (1) Multimodal sentiment analysis of short videos based on attention ················································ HUANG Huan, SUN Li-juan, CAO Ying, GUO Jian, REN Heng-yi (8) A combined classifier based on CNN and SVM for LCD character recognition ································································· LIU Chang, XU Chao-yuan, ZHANG Xin, XUE Lei (15) Salt and pepper noise denoising using high-order overlapping group sparsity with Lp-pseudo-norm ································································ CHENG Zhu-yuan, NI Wan-zhen, CHEN Ying-pin (23) Attention-guided Dropout for image classification ··································· CHANG Dong-liang, YIN Jun-hui, XIE Ji-yang, SUN Wei-ya, MA Zhan-yu (32) 3D object detection algorithm combined with sparse point cloud completion ················································································ XU Chen, NI Rong-rong, ZHAO Yao (37) Generative adversarial network-based local facial stylization generation algorithm ··············································································· FAN Lin-long, LI Yi, ZHANG Xiao-qin (44) Method for moving object detection of underwater fish using dynamic video sequence ············· ZHANG Ming-hua, LONG Teng, SONG Wei, HUANG Dong-mei, MEI Hai-bin, QIN Xue-biao (52) An underwater image comprehensive enhancement algorithm based on color compensation ····················································· YANG Miao, WANG Hai-wen, HU Ke, YIN Ge, HU Jin-tong (59) Image stabilization repair method combining time series network and pyramid fusion ···································· LIU Qing, LI Shi-chao, WANG Wen-shan, SHI Wen-xi, CHENG Ke-yang (65) Computer Graphics and Virtual Reality Human-computer interaction method in previz based on Leap Motion ····························································· ZHAO Jian-jun, HUANG Jun-peng, CHEN Jun-liang (71) Immersive physics learning environment with force feedback ······················ ZHENG Ming-yu, LI Jia-he, ZHANG Han, LUO Yan-lin, SHEN Jia-li, ZHU Xiao-ming (79) Simulation of magnetic lines in AR physics experiments ·································· MIAO Jin-da, LUO Tian-ren, CAI Ning, ZHANG Ming-min, PAN Zhi-geng (87) A svBRDF modeling pipeline using pixel clustering ·················· FENG Jie, LI Bo, ZHOU Bing-feng (94) Temporal anti-aliasing algorithm based on sparse super-sampling ······································································· LI Gen, CHEN Wen-qian, ZHANG Yan-ci (101) A subdivision algorithm for changeable degree spline curves of low degrees ··················································································· SHEN Wan-qiang, ZHANG Hu (110) Digital Design and Manufacture Deep learning based manufacturability analysis approach for hole features ································································· ZHANG Hang, ZHANG Shu-sheng, YANG Lei (117) DIM/CIM Research on multi-objective optimization of passive building energy-saving factor based on BIM ······················································································ SUN Shao-nan, WU Jia-wei (124) Code compliance checking of structural design based on BIM model ······························· ZHANG Ji-song, ZHAO Li-hua, CUI Ying-hui, REN Guo-qian, LI Hai-jiang (133) Projection-based registration overlay method of construction image and BIM model ························································ HOU Xue-liang, XUE Jing-guo, WANG Yi, ZENG Ying (141) Industrial Design Design of wearable rehabilitation manipulator based on FBS extended model ································ SUN Li, ZHANG Peng, WU Jian-tao, DAI Cheng, JIANG Nan, LU Zhi-bin (150) Innovative design of luggage case based on TRIZ theory ········································· YANG Qin, LI Wei-lao, ZHOU Ai, LIU Da-shuai, WANG Wei-xing (158) Related Articles | Metrics

Image Processing and Computer Vision

Select

Locally adjusted age estimation based on deep learning and directed acyclic graph SVM   LI Jun , YANG Ya-zhi 2021, 42(1): 1-7.  DOI: 10.11996/JG.j.2095-302X.2021010001 Abstract ( 211 )   PDF (1469KB) ( 334 )    In order to further enhance the accuracy of age estimation, we proposed a locally adjusted age estimation algorithm based on deep learning and directed acyclic graph-support vector machine (SVM). In the training phase, the SE-ResNet-50 network, pre-trained on the VGGFace2 data set, was first fine-tuned. When it converged, the fully connected layer was extracted, and the vector formed by its end-to-end connection was employed as a representation and further trained multiple one-versus-one SVM. In the testing phase, we first sent the face image into SE-ResNet-50 to obtain a rough age result, then set the specific neighborhood, finally integrated the trained SVM into a directed acyclic graph SVM, and conducted accurate age estimation centering on the global estimation value. In order to show the universality of the algorithm, the results of experiments undertaken in MORPH and AFAD datasets of different races can verify the effectiveness of the algorithm.  Related Articles | Metrics

Select

Multimodal sentiment analysis of short videos based on attention HUANG Huan , SUN Li-juan, CAO Ying , GUO Jian, REN Heng-yi 2021, 42(1): 8-14.  DOI: 10.11996/JG.j.2095-302X.2021010008 Abstract ( 653 )   PDF (1073KB) ( 442 )   The existing sentiment analysis methods lack sufficient consideration of information in short videos, leading to inappropriate sentiment analysis results. Based on this, we proposed the audio-visual multimodal sentiment analysis (AV-MSA) model that can complete the sentiment analysis of short videos using visual features in frame images and audio information in videos. The model was divided into two branches, namely the visual branch and the audio branch. In the audio branch, the convolutional neural networks (CNN) architecture was employed to extract the emotional features in the audio atlas to achieve the purpose of sentiment analysis; in the visual branch, we utilized the 3D convolution operation to increase the temporal correlation of visual features. In addition, on the basis of ResNet, in order to highlight the emotion-related features, we added an attention mechanism to enhance the sensitivity of the model to information features. Finally, a cross-voting mechanism was designed to fuse the results of the visual and audio branches to produce the final result of sentiment analysis. The proposed AV-MSA was evaluated on IEMOCAP and Weibo audio-visual (Weibo audio-visual, WB-AV) datasets. Experimental results show that compared with the current short video sentiment analysis methods, the proposed AV-MSA has improved the classification accuracy greatly.  Related Articles | Metrics

Select

A combined classifier based on CNN and SVM for LCD character recognition  LIU Chang, XU Chao-yuan, ZHANG Xin, XUE Lei 2021, 42(1): 15-22.  DOI: 10.11996/JG.j.2095-302X.2021010015 Abstract ( 116 )   PDF (1971KB) ( 232 )   A combined classifier based on convolution neural network (CNN) and support vector machine (SVM) was proposed for the recognition of liquid crystal displayer (LCD) characters. Two basic classifiers were utilized to build a combined classifier for recognition. One was CNN with a parallel structure, and the other was SVM using histogram of oriented gradients (HOG) features of the character image. If a sample’s responses from two basic classifiers conflicted with each other, the maximum component of the softmax vector outputted from CNN classifier was employed to determine the final result. If it was greater than a threshold, the CNN result was adopted, otherwise the SVM result. An error model for LCD character image was presented and adopted to construct a simulation dataset for the algorithm training and test. An optimal threshold estimation algorithm based on voting principle was proposed. The combined classifier was tested on both MNIST dataset and an LCD character simulation dataset. The experimental results show that the threshold estimation result was reliable, and that the combined classifier outperformed both CNN and SVM basic classifiers. Using the method on a real test system, the accuracy rate was 99.81%. The results prove the method’s effectiveness for LCD character recognition. The experimental results on CIFAR-10 dataset show that the method can also be applied to other kinds of classifications.  Related Articles | Metrics

Select

Salt and pepper noise denoising using high-order overlapping group sparsity with Lp-pseudo-norm CHENG Zhu-yuan , NI Wan-zhen , CHEN Ying-pin 2021, 42(1): 16-31.  DOI: 10.11996/JG.j.2095-302X.2021010023 Abstract ( 142 )   PDF (1240KB) ( 109 )   The total variation (TV) model is widely employed to remove salt and pepper noise. However, there is a serious staircase effect on the TV model. Recently, low-order overlapping group sparsity (LOGS) has received increasing attention due to the great performance in the suppression of the staircase effect. It is necessary to point out that there is still room for the improvement of LOGS total variation denoising model. In fact, the LOGS-based denoising model only takes into account the prior of the first-order image gradients and ignores the prior of the high-order image gradients. To further improve the quality of the recovery image, the author proposed a high-order OGS with the Lp-pseudo-norm. On the one hand, the overlapping group sparsity constraint of the high-order gradient can better describe the prior sparsity of image. On the other hand, the Lp-pseudo-norm was adopted to describe the sparsity of the salt and pepper noise, because of the strong sparsity inducing capacity. The alternating direction method of multipliers was employed to separate the proposed model into several sub-problems for the solving process. Finally, the numerical experiments were carried out to verify the proposed model, while the peak signal to noise ratio (PSNR), structural similarity (SSIM), and gradient magnitude similarity deviation (GMSD) were incorporated to evaluate the recovery performance. The experimental results prove that the proposed method is more competitiveness than some state-of-the-art denoising models.  Related Articles | Metrics

Select

Attention-guided Dropout for image classification CHANG Dong-liang , YIN Jun-hui , XIE Ji-yang , SUN Wei-ya , MA Zhan-yu 2021, 42(1): 32-36.  DOI: 10.11996/JG.j.2095-302X.2021010032 Abstract ( 154 )   PDF (465KB) ( 131 )   When a large-scale neural network is trained on a small training set, it typically yields “overfitting”, i.e., the model performs poorly on held-out test data. Therefore, various Dropout techniques have been proposed to alleviate this problem. However, the aforementioned methods cannot directly encourage the model to learn the less discriminative parts, which is also important to reducing overfitting. To address this problem, we proposed an attention-guided Dropout (AD), which utilized the self-attention mechanism to alleviate the co-adaptation of feature detectors more effectively. The AD comprised two distinctive components, the importance measurement mechanism for feature maps and the Dropout with a learnable probability. The importance measurement mechanism calculated the degree of importance for each feature map in whole by a Squeeze-and-Excitation block. The Dropout with a learnable probability can force the “bad” neurons to learn a better representation by dropping the “good” neurons. Therefore, it will diminish the co-adaptation and encourage models to learn the less discriminative part. The experimental results show that the proposed method can be easily applied to various convolutional neural network (CNN) architectures, thus yielding better performance.  Related Articles | Metrics

Select

3D object detection algorithm combined with sparse point cloud completion XU Chen, NI Rong-rong, ZHAO Yao, 2021, 42(1): 37-43.  DOI: 10.11996/JG.j.2095-302X.2021010037 Abstract ( 513 )   PDF (5702KB) ( 312 )    The 3D object detection method based on radar point cloud effectively solves the problem that the 2D object detection based on RGB images is easily affected by such factors as light and weather. However, due to such issues as radar resolution and scanning distance, the point clouds collected by lidar are often sparse, which will undermine the accuracy of 3D object detection. To address this problem, an object detection algorithm fused with sparse point cloud completion was proposed. A point cloud completion network was constructed using encoding and decoding mechanisms. A complete dense point cloud was generated from the input partial sparse point cloud. According to the characteristics of the cascade decoder method, a new composite loss function was defined. In addition to the loss in the original folding-based decoder stage, the compound loss function also added the loss in the fully connected decoder stage to ensure that the total error of the decoder network was minimized. Thus, the point cloud completion network could generate dense points with more complete information Ydetail, and apply the completed point cloud to the 3D object detection task. Experimental results show that the proposed algorithm can well complete the sparse car point cloud in the KITTI data set, and effectively improve the accuracy of object detection, especially for the data of moderate and high difficulty, with the improvement of 6.81% and 9.29%, respectively.  Related Articles | Metrics

Select

Generative adversarial network-based local facial stylization generation algorithm  FAN Lin-long , LI Yi , ZHANG Xiao-qin 2021, 42(1): 44-51.  DOI: 10.11996/JG.j.2095-302X.2021010044 Abstract ( 190 )   PDF (5877KB) ( 147 )   In view of the localized facial contour features, combining with the extraction of key feature points and the fusion of adjacent color regions of the face, we presented a CycleGAN-based local facial stylization generation algorithm, and constructed the deep learning network with the attention mechanism to generate the local facial cartoon stylization. The sample facial images were marked by using the local area binarization method to constrain the key features and points. In order to naturally match the generated image with the extracted features, the mean filtering operation was utilized to smooth and feather the edge contour of the extracted region. Finally, the generative adversarial networks (GAN) network was constructed, and the training data set was employed to generate cartoon stylization images in the local contour feature area of facial images. The experiment results show that the presented algorithm exhibits high robustness for generating facial stylization, and that it can be applied to the generation of stylized facial images of various scales.  Related Articles | Metrics

Select

Method for moving object detection of underwater fish using dynamic video sequence  ZHANG Ming-hua , LONG Teng , SONG Wei , HUANG Dong-mei, MEI Hai-bin , QIN Xue-biao 2021, 42(1): 52-58.  DOI: 10.11996/JG.j.2095-302X.2021010052 Abstract ( 180 )   PDF (2507KB) ( 121 )   In order to overcome the problems of underwater videos, such as low quality, blurring and even unrecognizability, using the computer vision technology for fast detection of underwater fish targets, an underwater video object detection method was proposed based on background removal methods. An object detection framework for underwater fish was designed, using the partial least squares (PLS) classifier for object detection. Input video sequences were collected from underwater fish data sets, and individual frames were extracted. After the format conversion of RGB to HSI and median filter denoising pretreatment, using the GMG background removal process, the texture and the characteristic of the gray scale coefficient were extracted based on local binary (LBP) pattern. At last, with the above extracted characteristics, the object detection of underwater fish in the daytime and night was realized using the PLS classifier. The results show that the method can achieve the object detection accuracy of 96.89% using the underwater fish video datasets, which improves the detection efficiency of underwater fish and reduces the labor cost. It can also provide some guidance for the monitoring, protection and sustainable development of underwater fish and other biological resources.  Related Articles | Metrics

Select

An underwater image comprehensive enhancement algorithm based on color compensation  YANG Miao, WANG Hai-wen , HU Ke , YIN Ge , HU Jin-tong 2021, 42(1): 59-64.  DOI: 10.11996/JG.j.2095-302X.2021010059 Abstract ( 257 )   PDF (1217KB) ( 318 )   A novel underwater image compositive enhancement method was proposed to improve the quality of underwater images, thereby synthetically boosting the performance of high-level visual analysis. A series of operations, including color compensation and correction, gamma correction in the HSV space, and final brightness de-blurring, were combined to realize color restoration, contrast and clarity improvements for underwater images. A method of brightness channel de-scattering based on Gauss filtering was proposed, and the comprehensive enhancement parameters of typical underwater images were analyzed. The experiments in this paper compared the processing results of the compositive enhancement method and other enhancement methods for the bluish, greenish, yellowish, and whitish nearshore shoal underwater images, and trained and tested the underwater image data sets enhanced by seven algorithms through the target detection network. Comparisons were also made between the average underwater target recognition accuracy rate and the ratio of the number of detected targets to the actual target number, so as to evaluate the effect of each enhancement algorithm on underwater target recognition and detection tasks. The experiment results demonstrate that the proposed method can achieve substantial image clarity improvement and color restoration, and is widely applicable, compared with the existing methods. At the same time, it can effectively improve the accuracy of underwater target recognition and the number of the detected objects.  Related Articles | Metrics

Select

Image stabilization repair method combining time series network and pyramid fusion  LIU Qing, LI Shi-chao, WANG Wen-shan , SHI Wen-xi , CHENG Ke-yang, 2021, 42(1): 65-70.  DOI: 10.11996/JG.j.2095-302X.2021010065 Abstract ( 114 )   PDF (4228KB) ( 80 )   To address the problems of the poor filling effect of the video image defect in video image stabilization, which seriously affects the visual effect and causes the black edge filling of the video after image stabilization processing, an image repair method was proposed based on time series network prediction and pyramid fusion. First, the pre-cutting mechanism was employed to adaptively determine whether the current frame needed to be repaired. Then all frames up to the current moment were sent to the model combining convolutional neural networks (CNN) and gated recurrent unit (GRU) to predict the part to be filled. Next, the improved weighted optimal stitching was used for stitching and image fusion reconstruction in the Gaussian Laplace pyramid. Finally, the size was cut after the completion of reconstruction. The experimental results show that the average peak signal to noise ratio (PSNR) of the method was 2–5 dB higher than that of the compared algorithm, and that the average structural similarity (SSIM) was improved by about 2%–7%. In addition, the video defect repaired by this method exhibits a natural filling effect and a relatively stable visual effect. Even in the cases of large black areas, the repair performance remains stable, which can be applied to a variety of camera platforms and different scenarios.  Related Articles | Metrics

Computer Graphics and Virtual Reality

Select

Human-computer interaction method in previz based on Leap Motion  ZHAO Jian-jun, HUANG Jun-peng, CHEN Jun-liang 2021, 42(1): 71-78.  DOI: 10.11996/JG.j.2095-302X.2021010071 Abstract ( 122 )   PDF (3018KB) ( 111 )   With the development of virtual reality (VR) technology, previz has gradually become an indispensable part of the film production. To improve the experience of filmmakers in previz, the utilization of natural multi-modal interaction, combined with 3D real-time rendering engine, has become increasingly important. At present, most of the interactive methods employed in previz are optical motion capture methods, which are expensive, difficult to operate, and poor in portability. This paper presented a human-computer interaction method based on Leap Motion. In addition to obtaining accurate captured data, it greatly reduced cost and the difficulty of operation. Filmmakers can interactively control the trajectory and switch between different motion states of virtual characters through gestures. With the help of motion capture data, filmmakers can directly participate in previz. The verification through previz schemes shows that this method is more natural, friendly, direct and efficient.  Related Articles | Metrics

Select

Immersive physics learning environment with force feedback  ZHENG Ming-yu, LI Jia-he, ZHANG Han, LUO Yan-lin, SHEN Jia-li, ZHU Xiao-ming 2021, 42(1): 79-86.  DOI: 10.11996/JG.j.2095-302X.2021010079 Abstract ( 136 )   PDF (907KB) ( 99 )   With the development of virtual reality (VR) technology, the immersive learning environment can play a great role in the field of education. However, most of the existing immersive environments can only provide visual and auditory interactions, and are unable to provide force and touch interactions, which are the drawbacks. Our project described a complete framework and development process of an immersive physics learning environment with force feedback. Using the Touch force-feedback device, along with the Unity3D software and OpenHaptics function library, the gravity and friction experiments were designed. Through the evaluation experiment, it can be concluded that the immersive physics learning environment with force feedback can provide a better sense of immersion and more natural interactions, which can deepen students’ understanding of abstract physical concepts and improve their interest in learning.  Related Articles | Metrics

Select

Simulation of magnetic lines in AR physics experiments  MIAO Jin-da , LUO Tian-ren , CAI Ning , ZHANG Ming-min , PAN Zhi-geng 2021, 42(1): 87-93.  DOI: 10.11996/JG.j.2095-302X.2021010087 Abstract ( 210 )   PDF (2429KB) ( 142 )   This paper proposed a virtual-real fusion simulation method of magnetic lines suitable for middle school experiments, and explored a set of algorithms applicable to the properties of magnetic lines in 3D space. It was applied to the multi-modal natural interactive augmented reality (AR) experiment system. This algorithm employed RK4 to generate magnetic induction lines and adopted the minimum energy method to revise them when necessary. The AR system utilized augmented reality based on physical kits and the multi-camera cooperative AR three-dimensional registration to overcome the traditional problem of two-dimensional MARK tracking failure. Finally, an electro-magnetic experiment commonly conducted in middle school teaching was taken as an example to test this magnetic induction line generation algorithm. Tests results show that these magnetic induction lines conform to the laws of physics and can better facilitate the electromagnetics-related physical experiments, which is of practical significance. By magnifying the phenomenon of the experiment, it is conducive to students’ understanding of physical concepts.  Related Articles | Metrics

Select

A svBRDF modeling pipeline using pixel clustering  FENG Jie, LI Bo , ZHOU Bing-feng, 2021, 42(1): 94-100.  DOI: 10.11996/JG.j.2095-302X.2021010094 Abstract ( 87 )   PDF (8733KB) ( 78 )   We presented a lightweight pipeline for modeling spatially varying bidirectional reflectance distribution functions (svBRDFs) of planar materials, which only required a mobile phone for data acquisition. With a minimum of two photos under an ambient and a point light source, the proposed pipeline produced svBRDF parameters, a normal map, and a tangent map for the material sample. The BRDF fitting was achieved via a pixel clustering strategy to reduce the complexity, namely, the pixels with similar appearance and structural characteristics were assumed to be the same material. Then, with a multi-stage optimization scheme, the parameters were fitted and formed a group of high-resolution BRDF texture maps. This method was not reliant on special equipment or massive data collection. The result shows that the proposed method is easy-to-use and capable of producing high-quality BRDF textures for a wide range of materials, including metallic or anisotropic materials.  Related Articles | Metrics

Select

Temporal anti-aliasing algorithm based on sparse super-sampling  LI Gen, CHEN Wen-qian, ZHANG Yan-ci 2021, 42(1): 101-109.  DOI: 10.11996/JG.j.2095-302X.2021010101 Abstract ( 159 )   PDF (3494KB) ( 115 )   In order to deal with the problems of the temporal anti-aliasing algorithm, such as ghosting, blurring, flickering, and loss of sub-pixel details when processing multiplexing between frames, in the cases of many high-frequency color regions or fine models in the scene, this paper proposed the temporal anti-aliasing algorithm based on sparse super-sampling. The core idea was that, based on the temporal anti-aliasing algorithm, for pixels that cannot reuse historical frames, super-sampling in the spatial domain was re-introduced, and the culling algorithm proposed in this paper was employed to avoid unnecessary drawing overhead and achieve sparse super-sampling. Experimental results show that the algorithm in this paper can obtain the anti-aliasing effect comparable to the super-sampling algorithm, and achieve higher rendering efficiency, which can effectively avoid the problems of ghosting, blurring, flickering, and loss of sub-pixel details.  Related Articles | Metrics

Select

A subdivision algorithm for changeable degree spline curves of low degrees SHEN Wan-qiang, ZHANG Hu 2021, 42(1): 110-116.  DOI: 10.11996/JG.j.2095-302X.2021010110 Abstract ( 82 )   PDF (594KB) ( 92 )   A subdivision scheme of changeable degree spline curves was proposed, in which the degree of each segment and the continuity between different segments can be specified before subdivision. In the algorithm, the degree of each segment can be selected from [1,4], the continuity between different degree segments was optional from C0 or C1 , and the continuity between the same degree segments was the degree minus 1. The scheme was based on the knot insertion of changeable degree spline. The midpoints were inserted into all non-zero knot intervals, and the relation of basis functions before and after the subdivision process were given accurately. At the same time, the length of each knot interval was proportional to its degree, which simplified the interpolation coefficients of different degree segments in the subdivision process. The subdivision process can be expressed in the form of linear interpolation, but it is different from the asymmetric local interpolation method for each segment. Instead, it is a global interpolation method, which is similar to the Lane-Riesenfeld subdivision of uniform B-spline. Therefore, the Lane-Riesenfeld subdivision scheme with degree ≤4 is included.  Related Articles | Metrics

Digital Design and Manufacture

Select

Deep learning based manufacturability analysis approach for hole features  ZHANG Hang, ZHANG Shu-sheng, YANG Lei 2021, 42(1): 117-123.  DOI: 10.11996/JG.j.2095-302X.2021010117 Abstract ( 118 )   PDF (1346KB) ( 98 )   In view of the current situation that the traditional methods of manufacturability analysis based on knowledge and rules are not flexible and the existing methods of manufacturability analysis based on deep learning are unable to give the specific reasons for the non-manufacturability of parts, a method of manufacturability analysis based on deep learning was proposed. Firstly, a large number of CAD models with manufacturability category labels were constructed through digital modeling technology, and the point cloud was extracted to build the data set needed for deep learning. Then, based on the PointNet network, a deep learning network for hole feature manufacturability analysis was built, and the network training and parameter adjusting process were completed. Then, compared with the 3D-convolutional neural networks (3D-CNN), the deep learning network constructed in this paper exhibits better robustness and lower time complexity. Finally, the manufacturability analysis of hole feature in a sample part was carried out to identify the non-manufacturable hole feature, and the reason of non-manufacturability was explained. The experimental results show that the method can not only ensure high recognition accuracy, but also identify the reason why the feature cannot be manufactured, which is of greater application value.  Related Articles | Metrics

BIM/CIM

Select

Research on multi-objective optimization of passive building energy-saving factor based on BIM SUN Shao-nan, WU Jia-wei 2021, 42(1): 124-132.  DOI: 10.11996/JG.j.2095-302X.2021010124 Abstract ( 141 )   PDF (3961KB) ( 170 )   Building energy models on the basis of the original building information modeling (BIM) model were established to research the passive energy-saving strategies. This model adopted the gbXML data standard for data sharing, which imported a parametric building performance simulation model on the Grasshopper platform. In addition, the solar radiation analysis was performed on the outer surface of the target building to determine the variables index of the passive energy-saving technology, such as the angle and depth of the west overhangs, the window-to-wall ratio on the south and west sides, and the thickness of the insulation board. This platform established the objective function based on the spatial daylight autonomy (sDA300/50%), annual cooling and heating energy consumption, which employed OpenStudio for building energy analysis and Daysim for annual dynamic natural lighting analysis. Finally, using the NSGA-II algorithm for multi-objective optimization, the Pareto solution set was obtained. The result shows that on cold zone B, the fixed shading cannot balance cooling and heating energy  Related Articles | Metrics

Select

Code compliance checking of structural design based on BIM model  ZHANG Ji-song , ZHAO Li-hua , CUI Ying-hui , REN Guo-qian , LI Hai-jiang 2021, 42(1): 133-140.  DOI: 10.11996/JG.j.2095-302X.2021010133 Abstract ( 285 )   PDF (779KB) ( 249 )   Building information modeling (BIM), as the digital expression of construction engineering, is becoming an important means to realize the informatization, industrialization, and intelligence of the whole life of building. The utilization of BIM model as a design delivery represents the future trend of construction design. However, currently, the compliance checking of structural design is conducted manually, which tends to be subjective, inefficient and error-prone. As a result, this paper carried out a case study of the compliance checking of the frame structure, analyzed the BIM model data using the relational database, and employed Java programming to translate the provisions of structure design code, thereby proposing an approach to compliance checking of structural design based on the BIM model. The process can be divided into three main steps: ① Model preparation and information mapping; ② Provision classification and translation; ③ Development of connection and code execution. The results show that the proposed method can partially realize the automatic compliance checking of structural design, improve the scientificity, reliability, and standardization of conformance checking, and provide a technical basis and alternative method for the automation and intelligence of code compliance checking in the future.  Related Articles | Metrics

Select

Projection-based registration overlay method of construction image and BIM model HOU Xue-liang , XUE Jing-guo , WANG Yi , ZENG Ying 2021, 42(1): 141-149.  DOI: 10.11996/JG.j.2095-302X.2021010141 Abstract ( 201 )   PDF (6006KB) ( 222 )   In order to visually compare the deviation between the actual construction progress and the planned progress during the construction of the building structure by combining the planned building information modeling (BIM) construction process simulation with the progress at the construction site, a projection model-based registration overlay method of construction images and the BIM model was proposed. Firstly, based on the analysis of the camera projection model and the camera calibration method, the coordinate mapping relationship between the construction site image and the camera imaging plane was established. Secondly, the Navisworks application programming Interface was employed to develop the construction image overlay management system, which realized the superposition of the construction image and the BIM model plane field. Then, an evaluation model for judging the registration effect was proposed based on the deformation characteristics between the superimposed image groups. Finally, an empirical analysis was carried out by taking the construction site of a commercial and residential building as an example. The experimental results show that the best way of superimposing is to highlight the to-be-observed BIM components in shading mode, and to set the transparency of the upper image between 35% and 65%; in the case of eyelevel shot, the registration effect is significantly better than that of low-angle shot; the deviation of the superimposed effect of all cameras is within the acceptable error. The proposed method can effectively achieve the registration of the construction image and the BIM model, and visually reflect the deviation between the planned model and the actual construction progress during the construction of the building structure.  Related Articles | Metrics

Industrial Design

Select

Design of wearable rehabilitation manipulator based on FBS extended model SUN Li, ZHANG Peng, WU Jian-tao, DAI Cheng, JIANG Nan, LU Zhi-bin 2021, 42(1): 150-157.  DOI: 10.11996/JG.j.2095-302X.2021010150 Abstract ( 234 )   PDF (1596KB) ( 279 )    Rehabilitation manipulator is a combination of rehabilitation medicine and robotics. Its purpose is to restrict the range of motion of injured limbs with external aids and to rebuild the function of the hand movement system, so as to perform rehabilitation treatment on the affected limbs of patients. This paper expanded the function-behavior-structure (FBS) model, started with the design knowledge flow theory, and incorporated the user needs and principle space to construct a rehabilitation manipulator design scheme based on the FBS expansion model. Through the demand-function-principle-behavior-structure (PFWBS) iterative design decoupling, combined with the biological structure of the hand, this paper systematically analyzed the mapping process of the conceptual model of the rehabilitation manipulator, and constructed a strategy for solving the functional structure of the rehabilitation manipulator. A wearable rehabilitation manipulator was designed for the patient. The simulation analysis and working space solution of the rehabilitation manipulator verified the rationality of the rehabilitation manipulator mechanism. The research analysis shows that the mapping solution strategy based on the FBS extended model provides a certain theoretical basis and practical strategy for the design research of rehabilitation manipulators, which can effectively improve the user experience.  Related Articles | Metrics

Select

Innovative design of luggage case based on TRIZ theory  YANG Qin , LI Wei-lao , ZHOU Ai , LIU Da-shuai , WANG Wei-xing 2021, 42(1): 158-164.  DOI: 10.11996/JG.j.2095-302X.2021010158 Abstract ( 1196 )   PDF (7682KB) ( 908 )   Combined with the methods of network and on-the-spot user investigation, user behavior simulation analysis, and functional system analysis, this paper analyzed the problems in the usage of luggage case, utilized TRIZ innovation and invention theory to convert the problems into TRIZ standard problems. The design research was conducted by adopting the corresponding principles of invention measures, combined with the actual usage of luggage case, and the rationality of the design was verified by the Jack simulation. As a result, the existing problems of luggage case were resolved, and the innovative design solution of luggage case was obtained. Through the simulation analysis and function analysis of user behavior habits, combined with TRIZ invention principles, the luggage case design process and users’ usage model were optimized, thus improving users’ experience.  Related Articles | Metrics

Total to Discuss

Select

Vol.42，No.1，2021 2021, 42(1): 165-165.  Abstract ( 50 )   PDF (60851KB) ( 84 )   Related Articles | Metrics