Pub Date : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570570
Yudong Chi, Weifeng Liu
This paper considers the problem of tracking multiple resolvable group targets using the labeled random finite set framework. While the generalized labeled multi-Bernoulli (GLMB) filter is an efficient multi-target tracking filter, it cannot capture the the dependence or correlation between members of each group. In this paper, we introduce a group target model by incorporating graph theory into the labeled random finite set framework, which accounts for dependence between group members. We then propose a GLMB approximation of the prediction and update step of the Bayes filter for multiple resolvable group targets. Simulation are presented to benchmark the proposed filter against the GLMB filter.
{"title":"Resolvable Group State Estimation with Maneuver Movement Based on Labeled RFS","authors":"Yudong Chi, Weifeng Liu","doi":"10.1109/ICCAIS.2018.8570570","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570570","url":null,"abstract":"This paper considers the problem of tracking multiple resolvable group targets using the labeled random finite set framework. While the generalized labeled multi-Bernoulli (GLMB) filter is an efficient multi-target tracking filter, it cannot capture the the dependence or correlation between members of each group. In this paper, we introduce a group target model by incorporating graph theory into the labeled random finite set framework, which accounts for dependence between group members. We then propose a GLMB approximation of the prediction and update step of the Bayes filter for multiple resolvable group targets. Simulation are presented to benchmark the proposed filter against the GLMB filter.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"331 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115973195","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}
Pub Date : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570434
Junjie Wang, Lingling Zhao, Xiaohong Su, Chunmei Shi
Particle flow filter implementations of random finite set filters have been proposed to tackle the issue of jointly estimating the number of targets and states. However, errors resulting from linearization are unavoidable. This paper presents a progressive Gaussian implementation of the probability hypothesis density filter, called the PG-PHD filter. The PG-PHD filter employed the progressive Gaussian filter to predict and update instead of the particle flow filter. The proposed algorithm addresses the drawback of Gaussian particle flow filter by using the progressive Gaussian method to migrate particles to the dense regions of the posterior while no need to linear the measurement function. The simulation results show that the performance of proposed PG-PHD improved significantly compared with the particle flow PHD filter.
{"title":"Multi-Target Tracking with the Progressive Gaussian Probability Hypothesis Density Filter","authors":"Junjie Wang, Lingling Zhao, Xiaohong Su, Chunmei Shi","doi":"10.1109/ICCAIS.2018.8570434","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570434","url":null,"abstract":"Particle flow filter implementations of random finite set filters have been proposed to tackle the issue of jointly estimating the number of targets and states. However, errors resulting from linearization are unavoidable. This paper presents a progressive Gaussian implementation of the probability hypothesis density filter, called the PG-PHD filter. The PG-PHD filter employed the progressive Gaussian filter to predict and update instead of the particle flow filter. The proposed algorithm addresses the drawback of Gaussian particle flow filter by using the progressive Gaussian method to migrate particles to the dense regions of the posterior while no need to linear the measurement function. The simulation results show that the performance of proposed PG-PHD improved significantly compared with the particle flow PHD filter.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126164575","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}
Pub Date : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570341
Yongze Jin, Guo Xie, Qing Zang, Le Fan, Tao Wen, Linfu Zhu
In this paper, the mechanism of pure air emergency braking for high speed train is analyzed. Considering the influence of the actual train running environment on the braking performance, an emergency braking model based on the environment is established. The expectation maximization identification of braking model for high speed train based on sliding window is proposed, and the unobserved time varying adhesion coefficient is identified. Firstly, the position and size of the sliding window are determined. Then the adhesion coefficient is identified by expectation maximization based on sliding window. Finally, combined with gradient optimization, the optimal identification of adhesion coefficient is obtained. The simulation results show that the online identification proposed in this paper can be used to identify the adhesion coefficient quickly and accurately. Under uniform noise, the identification error and relative error of adhesion coefficient are ±0.0015 and 1.8705% respectively. The relative error and root mean square error of braking speed are 0.4038% and 0.1018 respectively. It is satisfied with the actual needs of the braking system, and the accuracy of the model and effectiveness of the online identification method can be verified.
{"title":"Modeling of Train Braking Based on Environment and Online Identification of Time Varying Parameters","authors":"Yongze Jin, Guo Xie, Qing Zang, Le Fan, Tao Wen, Linfu Zhu","doi":"10.1109/ICCAIS.2018.8570341","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570341","url":null,"abstract":"In this paper, the mechanism of pure air emergency braking for high speed train is analyzed. Considering the influence of the actual train running environment on the braking performance, an emergency braking model based on the environment is established. The expectation maximization identification of braking model for high speed train based on sliding window is proposed, and the unobserved time varying adhesion coefficient is identified. Firstly, the position and size of the sliding window are determined. Then the adhesion coefficient is identified by expectation maximization based on sliding window. Finally, combined with gradient optimization, the optimal identification of adhesion coefficient is obtained. The simulation results show that the online identification proposed in this paper can be used to identify the adhesion coefficient quickly and accurately. Under uniform noise, the identification error and relative error of adhesion coefficient are ±0.0015 and 1.8705% respectively. The relative error and root mean square error of braking speed are 0.4038% and 0.1018 respectively. It is satisfied with the actual needs of the braking system, and the accuracy of the model and effectiveness of the online identification method can be verified.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130324907","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}
Pub Date : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570334
Feng Yang, Yujuan Luo, Litao Zheng, Shaodong Chen, Jie Zou
The cubature Kalman filter (CKF) algorithm is not suitable for non-Gaussian environments. The cubature particle filter (CPF) algorithm can solve the problem of the CKF algorithm, but it will introduce the problem of a large computational complexity. To solve the above problems, a Double-Layer Cubature Kalman Filter (DLCKF) algorithm is proposed. The DLCKF algorithm uses the state estimation of the inner CKF to replace the state transition density function of the outer CKF and updates the weights of each deterministic sampling point of the outer CKF with the latest measurements. Finally, the state estimation at each time is obtained. Simulation results show that, compared with the CKF and the CPF, the proposed algorithm not only has a low computational complexity, but also has very good estimation accuracy.
{"title":"Double-layer Cubature Kalman Filter","authors":"Feng Yang, Yujuan Luo, Litao Zheng, Shaodong Chen, Jie Zou","doi":"10.1109/ICCAIS.2018.8570334","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570334","url":null,"abstract":"The cubature Kalman filter (CKF) algorithm is not suitable for non-Gaussian environments. The cubature particle filter (CPF) algorithm can solve the problem of the CKF algorithm, but it will introduce the problem of a large computational complexity. To solve the above problems, a Double-Layer Cubature Kalman Filter (DLCKF) algorithm is proposed. The DLCKF algorithm uses the state estimation of the inner CKF to replace the state transition density function of the outer CKF and updates the weights of each deterministic sampling point of the outer CKF with the latest measurements. Finally, the state estimation at each time is obtained. Simulation results show that, compared with the CKF and the CPF, the proposed algorithm not only has a low computational complexity, but also has very good estimation accuracy.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125627411","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}
Pub Date : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570610
H. You, Kenwoo Kim, Dongwon Jung
This paper presents a real-time simulator environment for hardware-in-the-Ioop simulation for small satellites. Based on mathematical orbit model and attitude dynamics model running in real-time, the simulator virtually enables simulating various mission scenarios for small satellites reflecting realistic orbit conditions in conjunction with the high fidelity sensor and actuator models.
{"title":"A Real-Time Simulator for Processor-In-the-Loop Simulation of Small Satellites","authors":"H. You, Kenwoo Kim, Dongwon Jung","doi":"10.1109/ICCAIS.2018.8570610","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570610","url":null,"abstract":"This paper presents a real-time simulator environment for hardware-in-the-Ioop simulation for small satellites. Based on mathematical orbit model and attitude dynamics model running in real-time, the simulator virtually enables simulating various mission scenarios for small satellites reflecting realistic orbit conditions in conjunction with the high fidelity sensor and actuator models.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115153429","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}
Pub Date : 2018-10-01DOI: 10.1109/iccais.2018.8570528
{"title":"The Seventh International Conference on Control Animation and Information Sciences","authors":"","doi":"10.1109/iccais.2018.8570528","DOIUrl":"https://doi.org/10.1109/iccais.2018.8570528","url":null,"abstract":"","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"38 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114043847","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}
Pub Date : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570435
Wenjing Zhang, Lihua Tian, Chen Li, Haojia Li
Pedestrian detection has become a significant research topic in the field of computer vision. The performance of existing methods based on deep learning is not so good in pedestrian detection for complex background. Considering the problem of pedestrian detection in complex scenes with small and crowded objects, we propose a SSD-based crowded pedestrian detection method in this paper. Firstly, we increase density of default boxes on the horizontal direction by setting an offset, which can effectively eliminate the influence of missing matching default boxes and separate a person from the crowd much easier. So our detector is more suitable for complex scenes. Secondly, SSD is designed for general object detection, thus it is unfit for pedestrian detection because of the large aspect ratio of pedestrians. Therefore, we adopt abnormal 5*1 convolutional kernels instead of the standard 3*3 ones in order to adapt to pedestrian detection. Finally, we present experimental results on public benchmark datasets including Caltech dataset and INRIA dataset, which indicate that our method has better performance for pedestrian detection.
{"title":"A SSD-based Crowded Pedestrian Detection Method","authors":"Wenjing Zhang, Lihua Tian, Chen Li, Haojia Li","doi":"10.1109/ICCAIS.2018.8570435","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570435","url":null,"abstract":"Pedestrian detection has become a significant research topic in the field of computer vision. The performance of existing methods based on deep learning is not so good in pedestrian detection for complex background. Considering the problem of pedestrian detection in complex scenes with small and crowded objects, we propose a SSD-based crowded pedestrian detection method in this paper. Firstly, we increase density of default boxes on the horizontal direction by setting an offset, which can effectively eliminate the influence of missing matching default boxes and separate a person from the crowd much easier. So our detector is more suitable for complex scenes. Secondly, SSD is designed for general object detection, thus it is unfit for pedestrian detection because of the large aspect ratio of pedestrians. Therefore, we adopt abnormal 5*1 convolutional kernels instead of the standard 3*3 ones in order to adapt to pedestrian detection. Finally, we present experimental results on public benchmark datasets including Caltech dataset and INRIA dataset, which indicate that our method has better performance for pedestrian detection.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"24 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116406872","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}
Pub Date : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570421
Mingli Lu, Shuo Cheng, Weijian Qing, Jinliang Cong, Jian Shi
Cell migration is an important process in normal tissue, organ or entire organism development and disease. This paper proposes an ant algorithm based on cardinality estimation for clustered cells state and number estimator simultaneously. Cardinality prediction and updating model based on the existence probability of pheromone field are derived for effectively estimating the number of cells. In order to separate clusters cells, an ant work model based on the pheromone gradient information is developed to guide ants movement towards center of interested cells. Experiment results show that our algorithm could automatically track clustered cells in various scenarios, and, it is more accurate than other popular tracking methods.
{"title":"A Novel Ant-Based Multiple Cells Tracking Approach with Cardinality Estimation","authors":"Mingli Lu, Shuo Cheng, Weijian Qing, Jinliang Cong, Jian Shi","doi":"10.1109/ICCAIS.2018.8570421","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570421","url":null,"abstract":"Cell migration is an important process in normal tissue, organ or entire organism development and disease. This paper proposes an ant algorithm based on cardinality estimation for clustered cells state and number estimator simultaneously. Cardinality prediction and updating model based on the existence probability of pheromone field are derived for effectively estimating the number of cells. In order to separate clusters cells, an ant work model based on the pheromone gradient information is developed to guide ants movement towards center of interested cells. Experiment results show that our algorithm could automatically track clustered cells in various scenarios, and, it is more accurate than other popular tracking methods.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128712076","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}
Pub Date : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570416
Liang Ma, Yadong Zhang, Xiaomin Wang
The safety-critical discrete operation system is safety-critical, discrete and flow driven. The application of dispatching command system and process control system reduces the work intensity. However, information isolation and human operation may lead to insecurity, inefficiency and high cost. In order to ensure production safety, reduce attrition and increase efficiency, firstly, based on the unified multi-dimensional information integration platform, a broader safety-critical management-control integration (SCMCI) theory was put forward. Then, the hierarchical information interlocking (HII) model of SCMCI was established. Finally, the principles, rules and constraints of SCMCI model were proposed. SCMCI technology can realize automatic management of operation planning, automatic execution of control system, and automatic feedback of execution status. The SCMCI technology has been used in production operations management of metro rolling stock base to validate the feasibility of structure, model and algorithm.
{"title":"Management-Control Integration for Safety-Critical Integration for Safety-Critical Discrete Operation System","authors":"Liang Ma, Yadong Zhang, Xiaomin Wang","doi":"10.1109/ICCAIS.2018.8570416","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570416","url":null,"abstract":"The safety-critical discrete operation system is safety-critical, discrete and flow driven. The application of dispatching command system and process control system reduces the work intensity. However, information isolation and human operation may lead to insecurity, inefficiency and high cost. In order to ensure production safety, reduce attrition and increase efficiency, firstly, based on the unified multi-dimensional information integration platform, a broader safety-critical management-control integration (SCMCI) theory was put forward. Then, the hierarchical information interlocking (HII) model of SCMCI was established. Finally, the principles, rules and constraints of SCMCI model were proposed. SCMCI technology can realize automatic management of operation planning, automatic execution of control system, and automatic feedback of execution status. The SCMCI technology has been used in production operations management of metro rolling stock base to validate the feasibility of structure, model and algorithm.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126317054","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}
Pub Date : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570447
Yidan Sun, Benlian Xu, Shiqin Sun, Zhen Sun
The estimate of cell morphological parameter provides a fundamental basis for the diagnosis of diseases. Contour, as a key element of morphology, encapsulates a large number of details during cell growth, which assists biologist in judging the pathological state of cells. With this application in mind, we propose a novel multi-cell tracking algorithm fully based on the prediction and update of contour pheromone field. To accelerate the formation of pheromone field at the current frame, the pheromone field in the previous frame is predicted and obtained by a general linear model in the current frame. During the update, to ensure that the pheromone field keeps in consistence with the true cell contour, a gray-scale variance based decision model is developed and a gray gradient based model of pheromone propagation are designed as well. Experiment results show that the proposed approach can accurately and automatically estimate cell contours, and shows the superiority compared with other methods.
{"title":"A Multi-Cell State Estimator Based on Contour Pheromone Field Prediction and Update","authors":"Yidan Sun, Benlian Xu, Shiqin Sun, Zhen Sun","doi":"10.1109/ICCAIS.2018.8570447","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570447","url":null,"abstract":"The estimate of cell morphological parameter provides a fundamental basis for the diagnosis of diseases. Contour, as a key element of morphology, encapsulates a large number of details during cell growth, which assists biologist in judging the pathological state of cells. With this application in mind, we propose a novel multi-cell tracking algorithm fully based on the prediction and update of contour pheromone field. To accelerate the formation of pheromone field at the current frame, the pheromone field in the previous frame is predicted and obtained by a general linear model in the current frame. During the update, to ensure that the pheromone field keeps in consistence with the true cell contour, a gray-scale variance based decision model is developed and a gray gradient based model of pheromone propagation are designed as well. Experiment results show that the proposed approach can accurately and automatically estimate cell contours, and shows the superiority compared with other methods.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127520987","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：