Pub Date : 2016-10-01DOI: 10.1109/ICCAIS.2016.7822429
Weifeng Liu, Shujun Zhu, Chenglin Wen
This paper considers multiple resolvable group target estimation under clutter environment. We first build the structure for the resolvable group targets using graph theory. Then, the group estimation involves two stages of the target state estimation and group state (group size, shape, etc) estimation. In the first stage, based on the given group dynamic models, we derive the target estimated state set and the number of targets by using the multi-Bernoulli filter under the assumption of independence of all targets. In the second stage, we combine the graph theory with the group targets and build the adjacency matrix of the estimated state set. We thus get the number of the subgroups, the group state, the group sizes and its structures. Finally, a linear and a non-linear examples are given to verify the proposed algorithm, respectively.
{"title":"Multiple resolvable group target estimation using graph theory and the multi-Bernoulli filter","authors":"Weifeng Liu, Shujun Zhu, Chenglin Wen","doi":"10.1109/ICCAIS.2016.7822429","DOIUrl":"https://doi.org/10.1109/ICCAIS.2016.7822429","url":null,"abstract":"This paper considers multiple resolvable group target estimation under clutter environment. We first build the structure for the resolvable group targets using graph theory. Then, the group estimation involves two stages of the target state estimation and group state (group size, shape, etc) estimation. In the first stage, based on the given group dynamic models, we derive the target estimated state set and the number of targets by using the multi-Bernoulli filter under the assumption of independence of all targets. In the second stage, we combine the graph theory with the group targets and build the adjacency matrix of the estimated state set. We thus get the number of the subgroups, the group state, the group sizes and its structures. Finally, a linear and a non-linear examples are given to verify the proposed algorithm, respectively.","PeriodicalId":407031,"journal":{"name":"2016 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127346342","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 : 2016-10-01DOI: 10.1109/ICCAIS.2016.7822426
Michal Chaluš, J. Liška
This paper describes the design and development of a cognitive module for 3D robotic welding using TIG or laser technology. This area is constantly evolving with the needs to solve complex problems of welding automatization and robotization, and also thanks to the continuous advances in measurement technology and robotics. Besides the use of welding robots for serial production with dedicated tightly defined trajectories, systems for automatic welding of a previously undefined path or paths, which the operator can't manually define because of its complexity, are developed. This paper covers the general description of the cognitive module and its required functions. After that, the procedure for 3D robotic welding with a laser profile scanner is described in more detail. The task of controlling the end effector of the robot during the welding process is described. Then an algorithm for 3D model construction based on data from the profile scanner is presented. Development of the cognitive module prototype with use of a 2D profile scanner led to experimental evaluation of its function in the task of automatic cavity repair, which is discussed in the last part of the paper.
{"title":"3D robotic welding with a laser profile scanner","authors":"Michal Chaluš, J. Liška","doi":"10.1109/ICCAIS.2016.7822426","DOIUrl":"https://doi.org/10.1109/ICCAIS.2016.7822426","url":null,"abstract":"This paper describes the design and development of a cognitive module for 3D robotic welding using TIG or laser technology. This area is constantly evolving with the needs to solve complex problems of welding automatization and robotization, and also thanks to the continuous advances in measurement technology and robotics. Besides the use of welding robots for serial production with dedicated tightly defined trajectories, systems for automatic welding of a previously undefined path or paths, which the operator can't manually define because of its complexity, are developed. This paper covers the general description of the cognitive module and its required functions. After that, the procedure for 3D robotic welding with a laser profile scanner is described in more detail. The task of controlling the end effector of the robot during the welding process is described. Then an algorithm for 3D model construction based on data from the profile scanner is presented. Development of the cognitive module prototype with use of a 2D profile scanner led to experimental evaluation of its function in the task of automatic cavity repair, which is discussed in the last part of the paper.","PeriodicalId":407031,"journal":{"name":"2016 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"383 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123507567","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 : 2016-10-01DOI: 10.1109/ICCAIS.2016.7822468
Yifan Xie, H. Kim, T. Song
For splitting target tracking, the target may split into several such that estimating the states of all targets respon-sively and accurately becomes crucial. The standard formulation of the CBMeMBer filter assumes that the target birth intensity is known as a priori. In consideration of the fact that the target splitting event should be random and could happen at an arbitrary position, this assumption becomes unrealistic. In this paper we apply the adaptive birth distribution to solve the problem of tracking splitting targets. The adaptive birth method is turned out to be more suitable to the splitting target problem. The performance is evaluated by the Optimal Sub-pattern Assignment(OSPA) metric and cardinality estimate. Simulations show that the adaptive birth CBMeMBer is responsive to the changes in cardinality with small OSPA distance.
{"title":"Tracking splitting targets in clutter using the CBMeMBer filter","authors":"Yifan Xie, H. Kim, T. Song","doi":"10.1109/ICCAIS.2016.7822468","DOIUrl":"https://doi.org/10.1109/ICCAIS.2016.7822468","url":null,"abstract":"For splitting target tracking, the target may split into several such that estimating the states of all targets respon-sively and accurately becomes crucial. The standard formulation of the CBMeMBer filter assumes that the target birth intensity is known as a priori. In consideration of the fact that the target splitting event should be random and could happen at an arbitrary position, this assumption becomes unrealistic. In this paper we apply the adaptive birth distribution to solve the problem of tracking splitting targets. The adaptive birth method is turned out to be more suitable to the splitting target problem. The performance is evaluated by the Optimal Sub-pattern Assignment(OSPA) metric and cardinality estimate. Simulations show that the adaptive birth CBMeMBer is responsive to the changes in cardinality with small OSPA distance.","PeriodicalId":407031,"journal":{"name":"2016 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129795702","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 : 2016-10-01DOI: 10.1109/ICCAIS.2016.7822463
Yongsang Yoon, Jeonghwan Gwak, Jong-In Song, M. Jeon
Crowd density estimation for counting persons, or for determining interactions among persons, groups of people, or crowds has been a challenging problem since persons can be occluded by other persons in (highly) crowded situations. The successful development of such techniques has diverse purposes, such as reassigning limited resources (e.g., public transportation) properly by counting floating population or categorizing the type of events based on the identification of crowd interactions. While existing counting approaches are mostly based on regression models that directly map features to the corresponding class labels, we propose a conditional marked point process (CMPP)-based approach to count individual persons even in moderately crowded scenes. We use a mixture of Bernoulli shape, which is a stochastic model, estimated from the training set with extrinsic shape distribution that determines the size of a shape for the given location in an input image to count the proper number of persons in different types of scenes. The experiment was carried out on PETS2009 which is a well-known public dataset. It was concluded from the experimental results that the proposed approach can be an alternative to the conventional MPP-based approaches.
{"title":"Conditional marked point process-based crowd counting in sparsely and moderately crowded scenes","authors":"Yongsang Yoon, Jeonghwan Gwak, Jong-In Song, M. Jeon","doi":"10.1109/ICCAIS.2016.7822463","DOIUrl":"https://doi.org/10.1109/ICCAIS.2016.7822463","url":null,"abstract":"Crowd density estimation for counting persons, or for determining interactions among persons, groups of people, or crowds has been a challenging problem since persons can be occluded by other persons in (highly) crowded situations. The successful development of such techniques has diverse purposes, such as reassigning limited resources (e.g., public transportation) properly by counting floating population or categorizing the type of events based on the identification of crowd interactions. While existing counting approaches are mostly based on regression models that directly map features to the corresponding class labels, we propose a conditional marked point process (CMPP)-based approach to count individual persons even in moderately crowded scenes. We use a mixture of Bernoulli shape, which is a stochastic model, estimated from the training set with extrinsic shape distribution that determines the size of a shape for the given location in an input image to count the proper number of persons in different types of scenes. The experiment was carried out on PETS2009 which is a well-known public dataset. It was concluded from the experimental results that the proposed approach can be an alternative to the conventional MPP-based approaches.","PeriodicalId":407031,"journal":{"name":"2016 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115937433","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 : 2016-10-01DOI: 10.1109/ICCAIS.2016.7822460
Yongxin Chou, Benlian Xu, Ruilei Zhang, Yufeng Feng, Yi Jin
The signal to noise ratio (SNR) of dynamic pulse signal is time-varying, which influence the results of common used filtering methods. On the basis of integer-coefficients digital filter, in this study, we proposed a new approach can adjust the parameters of filter by the smooth degree of pulse signal. Moreover, the proposed method and three common used filtering methods: integer-coefficients digital filter, empirical mode decomposition) (EMD) filter and morphological filter are employed to suppress the noise and interference in the simulated and measured pulse signals. The results show that the proposed method can suppress the noise and interference of pulse signal effectively and can be used in dynamic pulse signal filtering.
{"title":"A novel filtering approach for dynamic pulse signal based on parameters self-adjusting integer-coefficients filter","authors":"Yongxin Chou, Benlian Xu, Ruilei Zhang, Yufeng Feng, Yi Jin","doi":"10.1109/ICCAIS.2016.7822460","DOIUrl":"https://doi.org/10.1109/ICCAIS.2016.7822460","url":null,"abstract":"The signal to noise ratio (SNR) of dynamic pulse signal is time-varying, which influence the results of common used filtering methods. On the basis of integer-coefficients digital filter, in this study, we proposed a new approach can adjust the parameters of filter by the smooth degree of pulse signal. Moreover, the proposed method and three common used filtering methods: integer-coefficients digital filter, empirical mode decomposition) (EMD) filter and morphological filter are employed to suppress the noise and interference in the simulated and measured pulse signals. The results show that the proposed method can suppress the noise and interference of pulse signal effectively and can be used in dynamic pulse signal filtering.","PeriodicalId":407031,"journal":{"name":"2016 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121909335","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 : 2016-10-01DOI: 10.1109/ICCAIS.2016.7822448
C. Choi, Hyeon Jun Jang, Seong Gyu Lim, Hyun Chul Lim, S. Cho, I. Gaponov
With a dramatic growth in the drone market in recent years, the amount of research efforts dedicated to drones increases correspondingly. However, short battery life severely restricts applications of the unmanned aerial vehicles and has proven to be a hard issue to tackle. Among various solutions for this problem, an automatic drone charging station can be utilized. This paper proposes a fully automatic charging station which operates wirelessly. The station also allows for imprecise landing of the UAV on the platform, which is often the case for practical systems. Application of the proposed charging station may completely eliminate the need in manual battery charging of the quadrotor UAVs.
{"title":"Automatic wireless drone charging station creating essential environment for continuous drone operation","authors":"C. Choi, Hyeon Jun Jang, Seong Gyu Lim, Hyun Chul Lim, S. Cho, I. Gaponov","doi":"10.1109/ICCAIS.2016.7822448","DOIUrl":"https://doi.org/10.1109/ICCAIS.2016.7822448","url":null,"abstract":"With a dramatic growth in the drone market in recent years, the amount of research efforts dedicated to drones increases correspondingly. However, short battery life severely restricts applications of the unmanned aerial vehicles and has proven to be a hard issue to tackle. Among various solutions for this problem, an automatic drone charging station can be utilized. This paper proposes a fully automatic charging station which operates wirelessly. The station also allows for imprecise landing of the UAV on the platform, which is often the case for practical systems. Application of the proposed charging station may completely eliminate the need in manual battery charging of the quadrotor UAVs.","PeriodicalId":407031,"journal":{"name":"2016 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116070174","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 : 2016-10-01DOI: 10.1109/ICCAIS.2016.7822442
Shoufeng Lin, B. Vo, S. Nordholm
This paper presents a measurement driven birth (MDB) model for the generalized labeled multi-Bernoulli (GLMB) filter. The MDB model adaptively generates target births based on measurement data, thereby eliminating the dependence of a priori knowledge of target birth distributions. Numerical results are provided to demonstrate the performance.
{"title":"Measurement driven birth model for the generalized labeled multi-Bernoulli filter","authors":"Shoufeng Lin, B. Vo, S. Nordholm","doi":"10.1109/ICCAIS.2016.7822442","DOIUrl":"https://doi.org/10.1109/ICCAIS.2016.7822442","url":null,"abstract":"This paper presents a measurement driven birth (MDB) model for the generalized labeled multi-Bernoulli (GLMB) filter. The MDB model adaptively generates target births based on measurement data, thereby eliminating the dependence of a priori knowledge of target birth distributions. Numerical results are provided to demonstrate the performance.","PeriodicalId":407031,"journal":{"name":"2016 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"329 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133536045","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 : 2016-10-01DOI: 10.1109/ICCAIS.2016.7822427
Wei Yang, Xiaocong Ma
In this paper, a novel spaceborne SAR imaging mode is proposed. In this mode, sensor illuminates the scene with different azimuth squint angles and obtains a series of sequential images. According to the working mechanism of the mode, the geometry model is built first. Based on the geometry model, the characteristics of signal are analyzed in detail, which reveals principle of velocity estimation. Moreover, combined with image formation processing algorithm, moving target velocity estimation method is present. Furthermore, some conclusions are drawn and discussed. Finally, simulation data and TerraSAR-X real data are used for verifying the validity of the method.
{"title":"A novel spaceborne SAR imaging mode for moving target velocity estimation","authors":"Wei Yang, Xiaocong Ma","doi":"10.1109/ICCAIS.2016.7822427","DOIUrl":"https://doi.org/10.1109/ICCAIS.2016.7822427","url":null,"abstract":"In this paper, a novel spaceborne SAR imaging mode is proposed. In this mode, sensor illuminates the scene with different azimuth squint angles and obtains a series of sequential images. According to the working mechanism of the mode, the geometry model is built first. Based on the geometry model, the characteristics of signal are analyzed in detail, which reveals principle of velocity estimation. Moreover, combined with image formation processing algorithm, moving target velocity estimation method is present. Furthermore, some conclusions are drawn and discussed. Finally, simulation data and TerraSAR-X real data are used for verifying the validity of the method.","PeriodicalId":407031,"journal":{"name":"2016 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128238336","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 : 2016-10-01DOI: 10.1109/ICCAIS.2016.7822433
D. Kim, B. Vo, B. Vo
Instead of the filtering density, we are interested in the entire posterior density that describes the random set of object trajectories. So far only Markov Chain Monte Carlo (MCMC) technique have been proposed to approximate the posterior distribution of the set of trajectories. Using labeled random finite set we show how the classical multi-object particle filter (a direct generalisation of the standard particle filter to the multi-object case) can be used to recursively compute posterior distribution of the set of trajectories. The result is a generic Bayesian multi-object tracker that does not require re-computing the posterior at every time step nor running a long Markov chain, and is much more efficient than the MCMC approximations.
{"title":"Multi-object particle filter revisited","authors":"D. Kim, B. Vo, B. Vo","doi":"10.1109/ICCAIS.2016.7822433","DOIUrl":"https://doi.org/10.1109/ICCAIS.2016.7822433","url":null,"abstract":"Instead of the filtering density, we are interested in the entire posterior density that describes the random set of object trajectories. So far only Markov Chain Monte Carlo (MCMC) technique have been proposed to approximate the posterior distribution of the set of trajectories. Using labeled random finite set we show how the classical multi-object particle filter (a direct generalisation of the standard particle filter to the multi-object case) can be used to recursively compute posterior distribution of the set of trajectories. The result is a generic Bayesian multi-object tracker that does not require re-computing the posterior at every time step nor running a long Markov chain, and is much more efficient than the MCMC approximations.","PeriodicalId":407031,"journal":{"name":"2016 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128967365","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 : 2016-10-01DOI: 10.1109/ICCAIS.2016.7822440
B. Wei, B. Nener, Weifeng Liu, Liang Ma
This paper addresses the problem of multi-sensor multi-target tracking. The main contribution is an efficient implementation of the multi-sensor δ-Generalized labeled Multi-Bernoulli (δ-GLMB) update. To truncate the weighted sums of the multi-target exponentials, the ranked assignment algorithm is used in the update to determine the most important terms without computing all the terms. Simulation experiments via linear Gaussian mixture models confirm the effectiveness of the proposed algorithm.
{"title":"Centralized multi-sensor multi-target tracking with labeled random finite sets","authors":"B. Wei, B. Nener, Weifeng Liu, Liang Ma","doi":"10.1109/ICCAIS.2016.7822440","DOIUrl":"https://doi.org/10.1109/ICCAIS.2016.7822440","url":null,"abstract":"This paper addresses the problem of multi-sensor multi-target tracking. The main contribution is an efficient implementation of the multi-sensor δ-Generalized labeled Multi-Bernoulli (δ-GLMB) update. To truncate the weighted sums of the multi-target exponentials, the ranked assignment algorithm is used in the update to determine the most important terms without computing all the terms. Simulation experiments via linear Gaussian mixture models confirm the effectiveness of the proposed algorithm.","PeriodicalId":407031,"journal":{"name":"2016 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121862411","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：