Haixiang Su, Junping Wang, Yaning Li, Xinge Hong, Peng Li
In image stitching, well performed stitching result is hard to achieve for images with large difference of contrast. This paper proposes a method based on histogram equalization by enhancing the contrast of stitching images. On the basis of image enhancement this method uses the algorithm of SURF (Speeded Up Robust Feature) feature points, K-Nearest Neighbor and bilateral matching method to match the feature points. Further, in order to get more stable and accurate homography, the method uses RANSAC (RANdom SAmple Consensus) algorithm. During the image fusion, as the traditional linear weighting method may generate ghost in the final image, this paper proposed a new method called four-section linear weighting method. Experimental results show that the method of the paper not only can realize image stitching with large difference of contrast, but also eliminate ghost phenomenon to a certain extent.
{"title":"An Algorithm for Stitching Images with Different Contrast and Elimination of Ghost","authors":"Haixiang Su, Junping Wang, Yaning Li, Xinge Hong, Peng Li","doi":"10.1109/ISCID.2014.75","DOIUrl":"https://doi.org/10.1109/ISCID.2014.75","url":null,"abstract":"In image stitching, well performed stitching result is hard to achieve for images with large difference of contrast. This paper proposes a method based on histogram equalization by enhancing the contrast of stitching images. On the basis of image enhancement this method uses the algorithm of SURF (Speeded Up Robust Feature) feature points, K-Nearest Neighbor and bilateral matching method to match the feature points. Further, in order to get more stable and accurate homography, the method uses RANSAC (RANdom SAmple Consensus) algorithm. During the image fusion, as the traditional linear weighting method may generate ghost in the final image, this paper proposed a new method called four-section linear weighting method. Experimental results show that the method of the paper not only can realize image stitching with large difference of contrast, but also eliminate ghost phenomenon to a certain extent.","PeriodicalId":385391,"journal":{"name":"2014 Seventh International Symposium on Computational Intelligence and Design","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123705545","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}
String comparison function is very important in the course of entity identification. Those existing comparison functions seldom considers the feature of Chinese string and the result is unsatisfied when ther are applied in Chinese string's comparison. To improve the. The experiment result indicates that our function can get higher efficient, higher recall ratio and higher precision ratio than function based on edit distance. The function we proposed can be applied to compute the similarity of strings which includes Chinese string.
{"title":"Comparison Function for Chinese String in Entity Identification","authors":"Jianfang Zhou","doi":"10.1109/ISCID.2014.142","DOIUrl":"https://doi.org/10.1109/ISCID.2014.142","url":null,"abstract":"String comparison function is very important in the course of entity identification. Those existing comparison functions seldom considers the feature of Chinese string and the result is unsatisfied when ther are applied in Chinese string's comparison. To improve the. The experiment result indicates that our function can get higher efficient, higher recall ratio and higher precision ratio than function based on edit distance. The function we proposed can be applied to compute the similarity of strings which includes Chinese string.","PeriodicalId":385391,"journal":{"name":"2014 Seventh International Symposium on Computational Intelligence and Design","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130617941","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}
Yang Yaqing, Ma Yizhong, Zhong Jianlan, Zhu Lianyan
With the rapid development of economic and technology, the demand of market changes in a fluctuating way. Many researches use statistical methods to describe the demand rate while in economic order quantity (EOQ) optimization. Exponential distribution has been widely recognized as an effective model for describing the demand rate especially for new items and deteriorating items. However, in most simulation optimization for EOQ, the distribution of the demand rate is set as normal distributed. Based on the assumption that the demand rate follows exponential distribution, we conduct robust simulation for EOQ model by incorporating Kriging model and Taguchi's robust view and then estimate the pareto frontier. The result suggests the robust optimization requires different order quantity from that of classic EOQ.
{"title":"A Robust Simulation for EOQ Model with Exponential Distributed Demand","authors":"Yang Yaqing, Ma Yizhong, Zhong Jianlan, Zhu Lianyan","doi":"10.1109/ISCID.2014.230","DOIUrl":"https://doi.org/10.1109/ISCID.2014.230","url":null,"abstract":"With the rapid development of economic and technology, the demand of market changes in a fluctuating way. Many researches use statistical methods to describe the demand rate while in economic order quantity (EOQ) optimization. Exponential distribution has been widely recognized as an effective model for describing the demand rate especially for new items and deteriorating items. However, in most simulation optimization for EOQ, the distribution of the demand rate is set as normal distributed. Based on the assumption that the demand rate follows exponential distribution, we conduct robust simulation for EOQ model by incorporating Kriging model and Taguchi's robust view and then estimate the pareto frontier. The result suggests the robust optimization requires different order quantity from that of classic EOQ.","PeriodicalId":385391,"journal":{"name":"2014 Seventh International Symposium on Computational Intelligence and Design","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132059438","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}
Recognizing human actions in video has gradually attracted much attention in computer vision community, however, it also faces many realistic challenges caused by background clutter, viewpoint changes, variation of actors appearance. These challenges reflect the difficulty of obtaining a clean and discriminative video representation for classification. Recently, VLAD (Vector of Locally Aggregated Descriptors) has shown to be a simple and efficient encoding scheme to obtain discriminative video representations. However, VLAD uses only the nearest visual word in codebook to aggregate each descriptor feature no matter whether it is appropriate or not. Inspired by visual word ambiguity and salience encoding in image classification, we propose Uncertain VLAD (UVLAD) encoding scheme which aggregates each local descriptor feature by considering multiple nearest visual words. The proposed UVLAD scheme ensures each descriptor to be aggregated or discarded appropriately. We evaluate our method on two different benchmark datasets: KTH, and YouTube. Results from experiments show that our encoding scheme outperforms the state-of-arts methods in most cases.
视频中人体动作识别逐渐受到计算机视觉界的重视，但同时也面临着背景杂乱、视点变化、演员外貌变化等诸多现实挑战。这些挑战反映了获得用于分类的清晰和有区别的视频表示的困难。近年来，局部聚合描述子向量(Vector of local Aggregated Descriptors, VLAD)被证明是一种简单而有效的编码方案，可以获得有区别的视频表示。然而，VLAD只使用码本中最接近的视觉词来聚合每个描述符特征，而不管它是否合适。受图像分类中视觉词歧义和显著性编码的启发，我们提出了不确定VLAD (UVLAD)编码方案，该方案通过考虑多个最接近的视觉词来聚合每个局部描述子特征。提出的UVLAD方案确保每个描述符被适当地聚合或丢弃。我们在两个不同的基准数据集上评估我们的方法:KTH和YouTube。实验结果表明，我们的编码方案在大多数情况下都优于目前最先进的方法。
{"title":"Action Recognition with Uncertain VLAD","authors":"Xianzhong Wang, Hongtao Lu","doi":"10.1109/ISCID.2014.238","DOIUrl":"https://doi.org/10.1109/ISCID.2014.238","url":null,"abstract":"Recognizing human actions in video has gradually attracted much attention in computer vision community, however, it also faces many realistic challenges caused by background clutter, viewpoint changes, variation of actors appearance. These challenges reflect the difficulty of obtaining a clean and discriminative video representation for classification. Recently, VLAD (Vector of Locally Aggregated Descriptors) has shown to be a simple and efficient encoding scheme to obtain discriminative video representations. However, VLAD uses only the nearest visual word in codebook to aggregate each descriptor feature no matter whether it is appropriate or not. Inspired by visual word ambiguity and salience encoding in image classification, we propose Uncertain VLAD (UVLAD) encoding scheme which aggregates each local descriptor feature by considering multiple nearest visual words. The proposed UVLAD scheme ensures each descriptor to be aggregated or discarded appropriately. We evaluate our method on two different benchmark datasets: KTH, and YouTube. Results from experiments show that our encoding scheme outperforms the state-of-arts methods in most cases.","PeriodicalId":385391,"journal":{"name":"2014 Seventh International Symposium on Computational Intelligence and Design","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130971223","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}
With the progress of construction technology, the modern buildings become more and more complicated and large-sized. It is difficult to avoid sudden and catastrophic emergency events for interior buildings. Hence, it is very important to establish an evacuation model to simulate evacuation behavior of pedestrians under real condition and make a scientific and effective evacuation plan. For handling with the problems of emergency evacuation path in buildings, an improved cellular automata model based on ant colony optimization algorithm (ACO) is proposed. The proposed model considers the neighbors moving rules of cellular automata and law of export selection rule is used as heuristic information of ant colony optimization algorithm, it reflects the behavior of personnel path choice more really. Finally, the model has been applied to simulate the whole evacuation process in a classroom. By simulating the process of pedestrian evacuation with the model, the results show that the proposed model could achieve shorter evacuation time than basic ACO, it's feasible for solving evacuation planning problem.
{"title":"An Optimization Model for Evacuation Based on Cellular Automata and Ant Colony Algorithm","authors":"Z. Ye, Yujie Yin, Xinlu Zong, Mingwei Wang","doi":"10.1109/ISCID.2014.160","DOIUrl":"https://doi.org/10.1109/ISCID.2014.160","url":null,"abstract":"With the progress of construction technology, the modern buildings become more and more complicated and large-sized. It is difficult to avoid sudden and catastrophic emergency events for interior buildings. Hence, it is very important to establish an evacuation model to simulate evacuation behavior of pedestrians under real condition and make a scientific and effective evacuation plan. For handling with the problems of emergency evacuation path in buildings, an improved cellular automata model based on ant colony optimization algorithm (ACO) is proposed. The proposed model considers the neighbors moving rules of cellular automata and law of export selection rule is used as heuristic information of ant colony optimization algorithm, it reflects the behavior of personnel path choice more really. Finally, the model has been applied to simulate the whole evacuation process in a classroom. By simulating the process of pedestrian evacuation with the model, the results show that the proposed model could achieve shorter evacuation time than basic ACO, it's feasible for solving evacuation planning problem.","PeriodicalId":385391,"journal":{"name":"2014 Seventh International Symposium on Computational Intelligence and Design","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130496539","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}
The short-term energy is widely used in various speaker discriminating applications (such as speaker verification system, diarization system and etc). However, unlike the well-known loundness measurement, its calculation takes no considerations on the human auditory properties. Since it has been shown that PLP is, to some extent, better than MFCC due to its well approximation of the excitation pattern to the human hearing system, the perceptual energy is thus introduced in this paper to replace the short-term energy, which is calculated to the PLP framework. It has been demonstrated that the newly introduced energy measurement exhibits more disseminating power with less computational overhead than the classical short-tem loudness. Its effectiveness is further verified in the application of speaker diarization.
{"title":"The Use of Perceptual Energy in Speaker Discrimination","authors":"Zhao Sun, Lei Wang","doi":"10.1109/ISCID.2014.128","DOIUrl":"https://doi.org/10.1109/ISCID.2014.128","url":null,"abstract":"The short-term energy is widely used in various speaker discriminating applications (such as speaker verification system, diarization system and etc). However, unlike the well-known loundness measurement, its calculation takes no considerations on the human auditory properties. Since it has been shown that PLP is, to some extent, better than MFCC due to its well approximation of the excitation pattern to the human hearing system, the perceptual energy is thus introduced in this paper to replace the short-term energy, which is calculated to the PLP framework. It has been demonstrated that the newly introduced energy measurement exhibits more disseminating power with less computational overhead than the classical short-tem loudness. Its effectiveness is further verified in the application of speaker diarization.","PeriodicalId":385391,"journal":{"name":"2014 Seventh International Symposium on Computational Intelligence and Design","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127898596","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}
Semantic relation extraction is an important part of information extraction, it has application value in the automatic question answering system, retrieval system, ontology learning, semantic web annotation, and many other areas. Pattern representation method is context pattern in previous semi-Supervised semantic relation extraction based on bootstrapping, but it did not consider the role of the keywords in the semantic relation. This paper presents an improved context pattern, which has a stronger semantic expressiveness, which is used to extract semantic relations and makes the semantic relation extraction more accurate. First of all, the sentence context pattern is obtained by lexical analysis. Then, the syntax tree model is obtained by syntactic analysis, calculate words weight using the syntax tree pattern. Finally, extract semantic relations using semi-Supervised machine learning method based on bootstrapping. The experimental results show that this method can effectively extract the semantic relations.
{"title":"Research on Pattern Representation Method in Semi-supervised Semantic Relation Extraction Based on Bootstrapping","authors":"Fei-yue Ye, Hao Shi, Shanpeng Wu","doi":"10.1109/ISCID.2014.154","DOIUrl":"https://doi.org/10.1109/ISCID.2014.154","url":null,"abstract":"Semantic relation extraction is an important part of information extraction, it has application value in the automatic question answering system, retrieval system, ontology learning, semantic web annotation, and many other areas. Pattern representation method is context pattern in previous semi-Supervised semantic relation extraction based on bootstrapping, but it did not consider the role of the keywords in the semantic relation. This paper presents an improved context pattern, which has a stronger semantic expressiveness, which is used to extract semantic relations and makes the semantic relation extraction more accurate. First of all, the sentence context pattern is obtained by lexical analysis. Then, the syntax tree model is obtained by syntactic analysis, calculate words weight using the syntax tree pattern. Finally, extract semantic relations using semi-Supervised machine learning method based on bootstrapping. The experimental results show that this method can effectively extract the semantic relations.","PeriodicalId":385391,"journal":{"name":"2014 Seventh International Symposium on Computational Intelligence and Design","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131425760","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}
A stability analysis of Networked Control Systems based on the Industry Ethernet Ring Network is presented in this paper. The frame loss of the Industry Ethernet Ring Network is regarded as a random event. The sufficiency conditions for asymptotically stability of the stochastic discrete linear time-variant system are presented and proved using a new method in this paper. A Networked Control System based on an Industry Ethernet Ring Network is simulated in MATLAB and the simulation agrees well with Theorem 1.
{"title":"Stability Analysis of Networked Control Systems Based on Industry Ethernet Ring Networks","authors":"Yu-Hui Zhang, Di Li, Q. Chu, Haidong Guo, Yu Zhang, Le-Lun Jiang","doi":"10.1109/ISCID.2014.165","DOIUrl":"https://doi.org/10.1109/ISCID.2014.165","url":null,"abstract":"A stability analysis of Networked Control Systems based on the Industry Ethernet Ring Network is presented in this paper. The frame loss of the Industry Ethernet Ring Network is regarded as a random event. The sufficiency conditions for asymptotically stability of the stochastic discrete linear time-variant system are presented and proved using a new method in this paper. A Networked Control System based on an Industry Ethernet Ring Network is simulated in MATLAB and the simulation agrees well with Theorem 1.","PeriodicalId":385391,"journal":{"name":"2014 Seventh International Symposium on Computational Intelligence and Design","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128839016","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}
Based on BHR composite network, a visualization processing model for underground space deformation safety level is proposed. First, the monitoring data acquired by sensors are normalized. Then BHR composite network is proposed to classify the normalized data automatically. The classification results are mapped into a color space to form different colors afterwards, with which different deformation safety levels are distinguished. The model is applied to an experiment of deformation safety level monitoring, and the deformation safety levels are visualized with deformation values displaying synchronously.
{"title":"A Visualization Processing Model for Underground Space Deformation Safety Level Based on BHR Composite Network","authors":"Wei Zheng, Xiaoya Zhang, Qi Lu","doi":"10.1109/ISCID.2014.71","DOIUrl":"https://doi.org/10.1109/ISCID.2014.71","url":null,"abstract":"Based on BHR composite network, a visualization processing model for underground space deformation safety level is proposed. First, the monitoring data acquired by sensors are normalized. Then BHR composite network is proposed to classify the normalized data automatically. The classification results are mapped into a color space to form different colors afterwards, with which different deformation safety levels are distinguished. The model is applied to an experiment of deformation safety level monitoring, and the deformation safety levels are visualized with deformation values displaying synchronously.","PeriodicalId":385391,"journal":{"name":"2014 Seventh International Symposium on Computational Intelligence and Design","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125369375","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}
Tao He, Nan Jiang, Qing Gu, Shaohua Sun, Huijun Zhang
GPS multi-channel common-view is a technique of time and frequency transfer with high accuracy, which can be used to achieve traceability for local time and frequency reference. The conception of time and frequency traceability is presented in this paper. The general principles of GPS multi-channel common-view and the detailed analysis of traceability in time and frequency metrology based on this technique are described. The measurement uncertainty of common-view is evaluated according to a long baseline comparison experiment, including the time measurement uncertainty of traceability to a national and international standard as well as the frequency measurement uncertainty of traceability to a national standard. Moreover, rather than time deviation, a new method is put forward to evaluate Type A time uncertainty via GPS multi-channel common-view technique. According to experimental results and analysis, time is measured with the combined expanded uncertainty of less than 15ns (2s) with respect to the UTC of a national standard, and is less than 18ns (2s) when it is trace to international standard. Meanwhile, frequency is measured with the combined expanded uncertainty of less than 10-13 (2s) after Day of averaging when it is trace to a national standard.
{"title":"GPS Multi-channel Common-View Based Experimental Research of Time and Frequency Traceability and Measurement","authors":"Tao He, Nan Jiang, Qing Gu, Shaohua Sun, Huijun Zhang","doi":"10.1109/ISCID.2014.215","DOIUrl":"https://doi.org/10.1109/ISCID.2014.215","url":null,"abstract":"GPS multi-channel common-view is a technique of time and frequency transfer with high accuracy, which can be used to achieve traceability for local time and frequency reference. The conception of time and frequency traceability is presented in this paper. The general principles of GPS multi-channel common-view and the detailed analysis of traceability in time and frequency metrology based on this technique are described. The measurement uncertainty of common-view is evaluated according to a long baseline comparison experiment, including the time measurement uncertainty of traceability to a national and international standard as well as the frequency measurement uncertainty of traceability to a national standard. Moreover, rather than time deviation, a new method is put forward to evaluate Type A time uncertainty via GPS multi-channel common-view technique. According to experimental results and analysis, time is measured with the combined expanded uncertainty of less than 15ns (2s) with respect to the UTC of a national standard, and is less than 18ns (2s) when it is trace to international standard. Meanwhile, frequency is measured with the combined expanded uncertainty of less than 10-13 (2s) after Day of averaging when it is trace to a national standard.","PeriodicalId":385391,"journal":{"name":"2014 Seventh International Symposium on Computational Intelligence and Design","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126410282","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：