{"title":"Incremental SFM 3D reconstruction based on monocular","authors":"Hengyu Yin, Hongyang Yu","doi":"10.1109/ISCID51228.2020.00011","DOIUrl":"https://doi.org/10.1109/ISCID51228.2020.00011","url":null,"abstract":"When using images for 3D reconstruction, the accuracy of feature matching is a very critical. The features of image extraction and the results after matching will directly determine whether the camera pose estimation is reliable. First, in order to get accurate poses, a mismatching filtering algorithm based on local correlation of images is proposed. To make increase the number of matches, SIFT and ORB feature matching are merged as inputs to sparse reconstruction. Then use incremental SFM algorithm to get sparse 3D points from the picture set. Finally use the combination of optical flow and ORB features to densely reconstruct the image. It has been proved by experiments that when filtering and fusion-matched results are used, the number of iterations can be effectively reduced in the BA solution stage. The improved dense reconstruction algorithm can reduce the reconstruction time while ensuring the reconstruction visual effect. (Abstract)","PeriodicalId":236797,"journal":{"name":"2020 13th International Symposium on Computational Intelligence and Design (ISCID)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122569333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Sine Cosine Algorithm Enhanced Spherical Evolution for Continuous Optimization Problems","authors":"Pengxing Cai, Haichuan Yang, Yu Zhang, Yuki Todo, Zheng Tang, Shangce Gao","doi":"10.1109/ISCID51228.2020.00008","DOIUrl":"https://doi.org/10.1109/ISCID51228.2020.00008","url":null,"abstract":"Spherical evolution (SE) is a relatively innovative algorithm. It transforms the original hypercube search into a spherical search. By this novel search style, SE expanded the search range. Sine cosine algorithm (SCA) creates multiple initial random candidate solutions and requires them to fluctuate outwards or towards the best solution using a mathematical model based on sine and cosine functions, which demonstrates that this algorithm can avoid local optima. In this article, we introduce SCA to enhance the convergence ability of SE. The experiment results on CEC2017 benchmark functions indicate the effectiveness of this hybridization, suggesting that the algorithm proposed is able to explore different regions of a search space, avoid local optima, converge towards the global optimum, and exploit promising regions of a search space during optimization effectively.","PeriodicalId":236797,"journal":{"name":"2020 13th International Symposium on Computational Intelligence and Design (ISCID)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123182534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A positioning method of intelligent plastering robot head","authors":"Yongjing Liu, Hongyang Yu","doi":"10.1109/ISCID51228.2020.00077","DOIUrl":"https://doi.org/10.1109/ISCID51228.2020.00077","url":null,"abstract":"When using an intelligent plastering robot to perform plastering operations on a completed room, in order to ensure the final smoothness of the wall, the most important step is to ensure that the plastering robot's wiper head is approximately absolutely parallel to the wall and is away from the wall. The distance is always consistent within the error range. This article uses a low-cost laser liner and CCD module to achieve high-precision real-time tracking, positioning and adjustment of the plastering robot head, and to realize the smoothness plastered walls. the plastering thickness of a whole wall reaches 2mm. The average flatness error is ± 0.2mm.(Abstract)","PeriodicalId":236797,"journal":{"name":"2020 13th International Symposium on Computational Intelligence and Design (ISCID)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117122323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Comparison of black fabric indexes based on computer color measurement and color matching technology","authors":"Jingying Xu, Q. Zhou, Zimin Jin","doi":"10.1109/ISCID51228.2020.00013","DOIUrl":"https://doi.org/10.1109/ISCID51228.2020.00013","url":null,"abstract":"In order to explore the evaluation method of black fabric, this paper uses computer color measurement and color matching technology to select two kinds of polyester knitted white fabrics as raw materials, and utilizes black tubes as standard samples to prepare polyester knitted printed black fabrics. The samples are compared and sorted, and the characteristics of each indicator are analyzed. The results show that it is apt to directly characterize the blackness of polyester knitted printing fabric by DE* value; σb has a reference significance for determining the end value of blackness within a certain range, but when the reflectance value is very low, the difference between different black fabrics is not very obvious.Gray-scale image-assisted visual evaluation can help observers more objectively evaluate blackness, and can achieve a natural transition from the machine to the human eye, which can reduce visual errors to a certain extent.","PeriodicalId":236797,"journal":{"name":"2020 13th International Symposium on Computational Intelligence and Design (ISCID)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121500645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Vibration Characteristics of Plate Structure Based on Simulation System","authors":"Minghui Zhao, Qijun Chen, Shihong Zhang","doi":"10.1109/ISCID51228.2020.00090","DOIUrl":"https://doi.org/10.1109/ISCID51228.2020.00090","url":null,"abstract":"Taking the vibration acoustics analysis of a circular plate as an example, after using ABAQUS, Python and MATLAB software to realize the virtual experiment simulation system based on finite element analysis, computer simulation and data processing, the rules of the size and structure of circular plate, material parameters, external force load and the frequency of sound pressure vibration caused by the vibration of circular plate are analyzed.","PeriodicalId":236797,"journal":{"name":"2020 13th International Symposium on Computational Intelligence and Design (ISCID)","volume":"191 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124245649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiaoli Fan, Ye Yan, Xiaoming Wang, Huijiong Yan, You Li, Liang Xie, E. Yin
{"title":"Emotion Recognition Measurement based on Physiological Signals","authors":"Xiaoli Fan, Ye Yan, Xiaoming Wang, Huijiong Yan, You Li, Liang Xie, E. Yin","doi":"10.1109/ISCID51228.2020.00025","DOIUrl":"https://doi.org/10.1109/ISCID51228.2020.00025","url":null,"abstract":"Emotion recognition plays an important part in interpersonal interaction, especially for Human-Computer Interaction (HCI). Emotions are not only tightly intertwined neurologically with the mechanisms responsible for cognition, but that they also play a pivotal role in decision making, problem solving, communicating, negotiating, and adapting to unpredictable environments. Emotions can be recognized by many measurements such as gesture, facial images, neuro imaging and physiological signals. Among which, the measurement based on physiological signals is considered as a more natural means of emotion recognition because the emotional status is inherently inflected in the activity of the nervous system. In the present paper, it was reviewed that the recent advancements in emotion recognition research using physiological signals, including emotion models and stimulation, signals preprocessing, feature extraction and classification methodologies. It would provide an insight on the current research progress, existing problems, and challenges of emotion recognition based on physiological signals.","PeriodicalId":236797,"journal":{"name":"2020 13th International Symposium on Computational Intelligence and Design (ISCID)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131597633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhen Li, Haichuan Yang, Zhiming Zhang, Yuki Todo, Shangce Gao
{"title":"Spherical Evolution Enhanced with Salp Swarm Algorithm","authors":"Zhen Li, Haichuan Yang, Zhiming Zhang, Yuki Todo, Shangce Gao","doi":"10.1109/ISCID51228.2020.00021","DOIUrl":"https://doi.org/10.1109/ISCID51228.2020.00021","url":null,"abstract":"Recently, a new population-based optimization algorithm called spherical evolution (SE), which is inspired by the traditional hyper-cube search style, has been proposed. It has significant ability of exploration and can avoid local optimum. On the other hand, salp swarm algorithm (SSA) has great advantage in local optimization of current random solutions. In this study, we are devoted to incorporating SSA into SE for solving optimization problems. In this hybrid algorithm, SE contributes to enhance the exploration during its iteration, and SSA is supposed to accelerate the convergence to optimal solutions. The experiment results on IEEE CEC 2017 benchmark functions indicate the effectiveness of this hybridization and show that spherical search style and salp swarm search mechanism are complementary. This study gives not only more insights into both original algorithms, but also a novel construction method of merging different algorithms.","PeriodicalId":236797,"journal":{"name":"2020 13th International Symposium on Computational Intelligence and Design (ISCID)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131667421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Design of Intelligent Waste Recycling System Based on Kano Model","authors":"Huiqian He, Ruiqiu Zhang, Wei-Ling Sun","doi":"10.1109/ISCID51228.2020.00047","DOIUrl":"https://doi.org/10.1109/ISCID51228.2020.00047","url":null,"abstract":"Kano model was applied to the design of intelligent waste recycling systems to increase user satisfaction with waste recycling. Questionnaire method, observation method and interview method were used to analyze the user's operational behavior and user needs, refine the user needs, Kano model was applied to classify the user needs, and distinguish the Attractive Quality, One-dimensional Quality, Must-be Quality, and Indifferent Quality, Reverse Quality. Customer satisfaction index CSI was combined to design the operating mechanism framework and small program interface of the intelligent waste recycling system. The Kano model can be used in the design of intelligent waste recycling systems, and it can more effectively improve the user satisfaction with the waste recycling system.","PeriodicalId":236797,"journal":{"name":"2020 13th International Symposium on Computational Intelligence and Design (ISCID)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123540589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Short Text Classification Model Based on Multi-Attention","authors":"Yunxiang Liu, Qi Xu","doi":"10.1109/ISCID51228.2020.00057","DOIUrl":"https://doi.org/10.1109/ISCID51228.2020.00057","url":null,"abstract":"Short text classification plays an important role in NLP and its applications span a wide range of activities such as sentiment analysis, spam detection. Recently, attention mechanism is widely used in text classification task. Inspired by this, a text classification model based on multi-attention network(MAN) is proposed in this study, which perform well in extracting information related to text category. In our model, we combine the textual information based on multi-attention mechanism, which enables model to focus on global information of the sentence. We tested effectiveness of our model using several standard text classification datasets. Experiment told that our model achieved state-of-the-art results on all datasets.","PeriodicalId":236797,"journal":{"name":"2020 13th International Symposium on Computational Intelligence and Design (ISCID)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124861612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Patent-Based Predictive Price-to-Earnings Ratio on Increasing Investment Performance of China Stock Market","authors":"Zhaohui Li, Guangyun Deng, Hui-Chung Che","doi":"10.1109/ISCID51228.2020.00097","DOIUrl":"https://doi.org/10.1109/ISCID51228.2020.00097","url":null,"abstract":"China listed companies (A-shares) in Shanghai Main Board, Shenzhen Main Board, GE Board, and SME Board are discussed the prediction ability of patent indicators to A-share’s price-to-earnings ratio (PE). We constructed patent leading indicators and patent prediction equations for predicting PE via Granger Causality test and time series regression. We found the stock selection criteria by the higher predictive PE growth rate is useful to build valuable stock portfolios for Shanghai Main Board and Shenzhen Main Board with better performance than the market trend. It also worked well on SME Board though is was seriously impacted by China-US trade conflict.","PeriodicalId":236797,"journal":{"name":"2020 13th International Symposium on Computational Intelligence and Design (ISCID)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123911333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}