Pub Date : 2018-12-01DOI: 10.1109/SPC.2018.8704126
A. Lee, S. Yong
The ultimate goal of computer vision research is to understand a scene semantically from an image or a video. Real-time object detection received significant attention over the past few years. Many challenges remain, especially in the focus of extraction of localized object information for scene representation. In order to have an accurate, intelligent and fast real-time object detection, the implementation of accurate localized information in the machine is inevitable. This research will focus on developing the object localization extractor that can extract the localized object information from the scene for further scene prediction and inference. In particular, (i) our localized extractor can encode significantly high-level features information; (ii) this rich localized information will be used for scene representation and understanding.
{"title":"Localized Object Information from Detected Objects Based on Deep Learning in Video Scene","authors":"A. Lee, S. Yong","doi":"10.1109/SPC.2018.8704126","DOIUrl":"https://doi.org/10.1109/SPC.2018.8704126","url":null,"abstract":"The ultimate goal of computer vision research is to understand a scene semantically from an image or a video. Real-time object detection received significant attention over the past few years. Many challenges remain, especially in the focus of extraction of localized object information for scene representation. In order to have an accurate, intelligent and fast real-time object detection, the implementation of accurate localized information in the machine is inevitable. This research will focus on developing the object localization extractor that can extract the localized object information from the scene for further scene prediction and inference. In particular, (i) our localized extractor can encode significantly high-level features information; (ii) this rich localized information will be used for scene representation and understanding.","PeriodicalId":432464,"journal":{"name":"2018 IEEE Conference on Systems, Process and Control (ICSPC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129763226","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 : 2018-12-01DOI: 10.1109/SPC.2018.8704143
Musab A. M. Ali, N. Md. Tahir, A. Ali
In this research, infants and newborns mortality can decrease significantly to 50% by monitoring vital signs and early intervention. Real time care is indeed vital for sick baby in ensuring the appropriate treatment is given and thus more attentions are required to detect any symptoms or signs of infants' diseases. Hence, a system is proposed that integrates several functions in one single device and analyze the data from sensors along with the interaction of the device that will inform the conditions which will be determined by standard based clinical studies. The proposed system could be able to reduce the burden on hospitals and parents, with less direct intervention for unserious conditions and allow early intervention for serious conditions. The integrate system will offers technology to assist for existing medical practices and also for real-time monitoring system for newborn, special treatment and assistance for newborns.
{"title":"Monitoring Healthcare System for Infants: A Review","authors":"Musab A. M. Ali, N. Md. Tahir, A. Ali","doi":"10.1109/SPC.2018.8704143","DOIUrl":"https://doi.org/10.1109/SPC.2018.8704143","url":null,"abstract":"In this research, infants and newborns mortality can decrease significantly to 50% by monitoring vital signs and early intervention. Real time care is indeed vital for sick baby in ensuring the appropriate treatment is given and thus more attentions are required to detect any symptoms or signs of infants' diseases. Hence, a system is proposed that integrates several functions in one single device and analyze the data from sensors along with the interaction of the device that will inform the conditions which will be determined by standard based clinical studies. The proposed system could be able to reduce the burden on hospitals and parents, with less direct intervention for unserious conditions and allow early intervention for serious conditions. The integrate system will offers technology to assist for existing medical practices and also for real-time monitoring system for newborn, special treatment and assistance for newborns.","PeriodicalId":432464,"journal":{"name":"2018 IEEE Conference on Systems, Process and Control (ICSPC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130645278","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 : 2018-12-01DOI: 10.1109/SPC.2018.8704136
S. M. Mohd Isa, S. A. Abdul Shukor, N. A. Rahim, I. Maarof, Z. R. Yahya, A. Zakaria, A. Abdullah, R. Wong
3D digital documentation for buildings has become a necessary tool in preserving them. Heritage buildings are exposed from various kind of threats such as human negligence, natural disaster and weather changes. The fundamental in 3D digital documentation which is the 3D point cloud data has captures great attention and has widely used in many fields due to the availability of laser scanners. The use of laser scanning in engineering surveys is gaining attention due to its advantage of producing high accuracy data. In most situations, it also able to scan the entire required site, thus offers a good potential technique for large-scale applications like for heritage buildings preservation. The data, which consists of high density of points, can be delivered in a short time. However, this causes a massive amount of data generated and hence, it becomes very difficult to be managed. Due to this issue, there are critical needs to have a good method in managing 3D point cloud data to maintain features and visualization of buildings, specially the old and aged ones. This paper will review developed methods in handling these data, concentrating on two specific processes, which are data structure and data filtering. The 3D point cloud data is having a unique representation, thus researchers are no longer concentrating on the usual concepts of data registration, meshing and reconstruction to handle it, but data structure and data filtering are preferred. In data structure, mathematical methods incorporating geometric and topological techniques can be used for studying finite set of points. As most of the data captured contains noises and outliers, filtering is also important and can be treated as one of the processes that can be adapted in handling 3D point cloud data. The implementation of various solutions within these areas are presented in this paper and will be analyzed by emphasizing their contributions. Then, results will be studied to explain the effectiveness of the methods used in handling big point data. Finally, some future work for 3D point cloud handling will be highlighted to conclude this critical review focusing in building data for its preservation.
{"title":"A Review of Data Structure and Filtering in Handling 3D Big Point Cloud Data for Building Preservation","authors":"S. M. Mohd Isa, S. A. Abdul Shukor, N. A. Rahim, I. Maarof, Z. R. Yahya, A. Zakaria, A. Abdullah, R. Wong","doi":"10.1109/SPC.2018.8704136","DOIUrl":"https://doi.org/10.1109/SPC.2018.8704136","url":null,"abstract":"3D digital documentation for buildings has become a necessary tool in preserving them. Heritage buildings are exposed from various kind of threats such as human negligence, natural disaster and weather changes. The fundamental in 3D digital documentation which is the 3D point cloud data has captures great attention and has widely used in many fields due to the availability of laser scanners. The use of laser scanning in engineering surveys is gaining attention due to its advantage of producing high accuracy data. In most situations, it also able to scan the entire required site, thus offers a good potential technique for large-scale applications like for heritage buildings preservation. The data, which consists of high density of points, can be delivered in a short time. However, this causes a massive amount of data generated and hence, it becomes very difficult to be managed. Due to this issue, there are critical needs to have a good method in managing 3D point cloud data to maintain features and visualization of buildings, specially the old and aged ones. This paper will review developed methods in handling these data, concentrating on two specific processes, which are data structure and data filtering. The 3D point cloud data is having a unique representation, thus researchers are no longer concentrating on the usual concepts of data registration, meshing and reconstruction to handle it, but data structure and data filtering are preferred. In data structure, mathematical methods incorporating geometric and topological techniques can be used for studying finite set of points. As most of the data captured contains noises and outliers, filtering is also important and can be treated as one of the processes that can be adapted in handling 3D point cloud data. The implementation of various solutions within these areas are presented in this paper and will be analyzed by emphasizing their contributions. Then, results will be studied to explain the effectiveness of the methods used in handling big point data. Finally, some future work for 3D point cloud handling will be highlighted to conclude this critical review focusing in building data for its preservation.","PeriodicalId":432464,"journal":{"name":"2018 IEEE Conference on Systems, Process and Control (ICSPC)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130669956","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 : 2018-12-01DOI: 10.1109/SPC.2018.8704161
M. R. Ghazali, Mohd Ashraf Ahmad, R. Ismail
This research paper presents a data-driven PID control for a DC/DC Buck-Boost converter-inverter-DC motor system based on safe experimentation dynamics (SED). The data-driven is a control scheme refers to a controller that is designed using the information of input-output data obtained from an actual plant. Then, the data-driven scheme required an optimization as a tool for finding the optimal parameter controller design with the help of the running data. Hence, the SED is an optimization method provides high accuracy solution by keeping the best controller parameter values based on the input-output data measurement. Moreover, the SED method is a single agent-based optimization that provides an accurate and fast solution in order to find an optimal solution, especially in the high dimensional problem. Apart from that, a PID controller structure is chosen due to its simple structure, easy to implement, provides a robust performance, effective control performances and widely applied in industries. The performance of the SED based method is evaluated by an extensive numerical example based on tracking performance and computational time. The simulation results show that the propose data-driven PID control based on the SED is capable to track the trajectory task given and obtain a good control accuracy without requiring any theoretical assumptions about the plant dynamics.
{"title":"Data-Driven PID Control for DC/DC Buck-Boost Converter-Inverter-DC Motor based on Safe Experimentation Dynamics","authors":"M. R. Ghazali, Mohd Ashraf Ahmad, R. Ismail","doi":"10.1109/SPC.2018.8704161","DOIUrl":"https://doi.org/10.1109/SPC.2018.8704161","url":null,"abstract":"This research paper presents a data-driven PID control for a DC/DC Buck-Boost converter-inverter-DC motor system based on safe experimentation dynamics (SED). The data-driven is a control scheme refers to a controller that is designed using the information of input-output data obtained from an actual plant. Then, the data-driven scheme required an optimization as a tool for finding the optimal parameter controller design with the help of the running data. Hence, the SED is an optimization method provides high accuracy solution by keeping the best controller parameter values based on the input-output data measurement. Moreover, the SED method is a single agent-based optimization that provides an accurate and fast solution in order to find an optimal solution, especially in the high dimensional problem. Apart from that, a PID controller structure is chosen due to its simple structure, easy to implement, provides a robust performance, effective control performances and widely applied in industries. The performance of the SED based method is evaluated by an extensive numerical example based on tracking performance and computational time. The simulation results show that the propose data-driven PID control based on the SED is capable to track the trajectory task given and obtain a good control accuracy without requiring any theoretical assumptions about the plant dynamics.","PeriodicalId":432464,"journal":{"name":"2018 IEEE Conference on Systems, Process and Control (ICSPC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126229924","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 : 2018-12-01DOI: 10.1109/SPC.2018.8704127
M. N. Mohammed, Vidya Shini Nadarajah, Nor Fazlina Mohd Lazim, Nur Shazwany Zamani, Omar Ismael Al-Sanjary, Musab A. M. Ali, Shahad Al-Youif
Robots are devised in such way to dispose of human intervention from labour extensive and hazardous work environment. At times they are also used to travel to unreachable workplaces that are typically not possible to access by human. Pipe inspections fall in the same category due to the fact that they carry toxic chemicals and fluids. Furthermore, most of the pipeline segments have tiny internal diameter or bends which end up unreachable to human. The complex inner geometry and hazard content constraints of pipes call for robots for inspection of such pipes so as to test corrosion, cracks and restoration of usable parts from pipe interior, sampling of sludge and scale formation on pipe inner surface. This research aims to design and develop a pipeline inspection robot using an autonomous mobile robot with ultrasound sensors and connected via GSM and GPS. In addition, IP camera was also used for visual inspection, integration of wireless capability for easy viewing of acquired data and images. The improvements achieved by the new-fangled design bring the ultrasonic inspection of pipeline even more competitive. Furthermore, the system has the ability to record and display the view of the atmospheres on the employees monitor display screen for effective observation, detection, quick analysis, diagnosis and reliably in confined, darkish environments.
{"title":"Design and Development of Pipeline Inspection Robot for Crack and Corrosion Detection","authors":"M. N. Mohammed, Vidya Shini Nadarajah, Nor Fazlina Mohd Lazim, Nur Shazwany Zamani, Omar Ismael Al-Sanjary, Musab A. M. Ali, Shahad Al-Youif","doi":"10.1109/SPC.2018.8704127","DOIUrl":"https://doi.org/10.1109/SPC.2018.8704127","url":null,"abstract":"Robots are devised in such way to dispose of human intervention from labour extensive and hazardous work environment. At times they are also used to travel to unreachable workplaces that are typically not possible to access by human. Pipe inspections fall in the same category due to the fact that they carry toxic chemicals and fluids. Furthermore, most of the pipeline segments have tiny internal diameter or bends which end up unreachable to human. The complex inner geometry and hazard content constraints of pipes call for robots for inspection of such pipes so as to test corrosion, cracks and restoration of usable parts from pipe interior, sampling of sludge and scale formation on pipe inner surface. This research aims to design and develop a pipeline inspection robot using an autonomous mobile robot with ultrasound sensors and connected via GSM and GPS. In addition, IP camera was also used for visual inspection, integration of wireless capability for easy viewing of acquired data and images. The improvements achieved by the new-fangled design bring the ultrasonic inspection of pipeline even more competitive. Furthermore, the system has the ability to record and display the view of the atmospheres on the employees monitor display screen for effective observation, detection, quick analysis, diagnosis and reliably in confined, darkish environments.","PeriodicalId":432464,"journal":{"name":"2018 IEEE Conference on Systems, Process and Control (ICSPC)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115882336","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 : 2018-12-01DOI: 10.1109/SPC.2018.8704129
S. El-Ferik, Mohamed A. Hassan, Mustafa Al-Naser
Control valve stiction is one of the common issues in industrial plant leading to poor control loops performance. Knocker based methods is one of common stiction compensation approaches. In this paper, a detailed comparison is held among three knocker based methods. Ideal compensator criteria proposed by Srinivasan and Rengaswamy is used to perform the comparison between three methods using MATLAB simulation and experimental setup.
{"title":"A Comparative Study of Valve Stiction Compensation: Knocker Based Methods","authors":"S. El-Ferik, Mohamed A. Hassan, Mustafa Al-Naser","doi":"10.1109/SPC.2018.8704129","DOIUrl":"https://doi.org/10.1109/SPC.2018.8704129","url":null,"abstract":"Control valve stiction is one of the common issues in industrial plant leading to poor control loops performance. Knocker based methods is one of common stiction compensation approaches. In this paper, a detailed comparison is held among three knocker based methods. Ideal compensator criteria proposed by Srinivasan and Rengaswamy is used to perform the comparison between three methods using MATLAB simulation and experimental setup.","PeriodicalId":432464,"journal":{"name":"2018 IEEE Conference on Systems, Process and Control (ICSPC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114653654","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 : 2018-12-01DOI: 10.1109/SPC.2018.8704163
W. Wong, Sindhu Rajindran, C. Lee
In today’s fast-paced world, customers’ demands are constantly evolving at next expectation level. Adopting, implementing and maintaining a QIM within an organization can be quite a challenge directive for the management team. Most importantly, QIM for an organization is about gathering the right information, method, person and time under an umbrella; focusing on putting quality management system (QMS) into practice. It is important to pinpoint the factors that may affect the decision of a small enterprise. The decision to QIM adoption and implementation is useful for SMEs/SMIs which are attempting to bring the organization to another level by shaping an efficient quality strategy. This paper aims to provide multi-dimensions criteria in single roadmap to QIM selection for IT and non-IT related projects. Thus, this roadmap provide a clearer, qualitative and quantitative measures to a suitable and applicable methodology that fits an organization’s objectives and culture, prior weighing organization’s own ability to undertake a successful QIM adoption and implementation.
{"title":"A Roadmap to Quality Improvement Methodology (QIM) for IT and Non-IT Related Project: Factors Affecting the Adoption and Implementation of QIM","authors":"W. Wong, Sindhu Rajindran, C. Lee","doi":"10.1109/SPC.2018.8704163","DOIUrl":"https://doi.org/10.1109/SPC.2018.8704163","url":null,"abstract":"In today’s fast-paced world, customers’ demands are constantly evolving at next expectation level. Adopting, implementing and maintaining a QIM within an organization can be quite a challenge directive for the management team. Most importantly, QIM for an organization is about gathering the right information, method, person and time under an umbrella; focusing on putting quality management system (QMS) into practice. It is important to pinpoint the factors that may affect the decision of a small enterprise. The decision to QIM adoption and implementation is useful for SMEs/SMIs which are attempting to bring the organization to another level by shaping an efficient quality strategy. This paper aims to provide multi-dimensions criteria in single roadmap to QIM selection for IT and non-IT related projects. Thus, this roadmap provide a clearer, qualitative and quantitative measures to a suitable and applicable methodology that fits an organization’s objectives and culture, prior weighing organization’s own ability to undertake a successful QIM adoption and implementation.","PeriodicalId":432464,"journal":{"name":"2018 IEEE Conference on Systems, Process and Control (ICSPC)","volume":"228 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124635699","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 : 2018-12-01DOI: 10.1109/SPC.2018.8704134
Nirbhay Mathur, V. Asirvadam, A. Abd Aziz, R. Ibrahim
An industrial plant assembled with many components, standby systems, sensors, controlling components to make smooth operation of plants. Losses produced by unplanned downtime may leads to major problems. Although, control valves which are used to control the rate of flow for pressure or liquid is an essential part of the plants operation. Since to reduce the losses or downtime damage, high reliability and standby availability is required to monitor. Hence, it requires some prediction which can express the likelihood of the events in the terms of quantitative methods. This research performs the prediction for reliability on the control instruments and its availability that is visualized for an quantitative prospective. By using Weibull distribution and calculating pdf and cdf for shape and size parameters for prediction and estimation of the consequences of these failure depends on the control valve assembled in process plant. Validating with estimation maximization(EM) technique and fitting it in curve to achieve 95% prediction accuracy. This research will give practical assessments of reliability of control valve for better actions and higher reliable redundancy.
{"title":"Visualizing and Predicting Reliability of Control Valves based on Simulation","authors":"Nirbhay Mathur, V. Asirvadam, A. Abd Aziz, R. Ibrahim","doi":"10.1109/SPC.2018.8704134","DOIUrl":"https://doi.org/10.1109/SPC.2018.8704134","url":null,"abstract":"An industrial plant assembled with many components, standby systems, sensors, controlling components to make smooth operation of plants. Losses produced by unplanned downtime may leads to major problems. Although, control valves which are used to control the rate of flow for pressure or liquid is an essential part of the plants operation. Since to reduce the losses or downtime damage, high reliability and standby availability is required to monitor. Hence, it requires some prediction which can express the likelihood of the events in the terms of quantitative methods. This research performs the prediction for reliability on the control instruments and its availability that is visualized for an quantitative prospective. By using Weibull distribution and calculating pdf and cdf for shape and size parameters for prediction and estimation of the consequences of these failure depends on the control valve assembled in process plant. Validating with estimation maximization(EM) technique and fitting it in curve to achieve 95% prediction accuracy. This research will give practical assessments of reliability of control valve for better actions and higher reliable redundancy.","PeriodicalId":432464,"journal":{"name":"2018 IEEE Conference on Systems, Process and Control (ICSPC)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115166681","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 : 2018-12-01DOI: 10.1109/SPC.2018.8703976
Nur Alyani Nadhiya, F. Yakub, Hatta Ariff, A. Azizan, Zainuddin A. Rasit, Sheikh Ahmad Zaki, Abdul Yasser Abd Fattah, Y. Mori
This paper extends the analysis of Yakub et. al [1], by suggesting an integrated control which includes an active aerodynamic control and differential braking control to enhance high speed vehicle dynamics stability. Two aerodynamic surfaces are attached to the roof of the vehicle and servo controlled separately in real time. A hierarchical control structure which is composed of an upper and a lower controller. In the upper controller, the additional yaw moment required for stability control is determined by sliding mode control with the consideration of driver inputs, vehicle dynamic and the limitation of road adhesion. In the lower controller, a control strategy is designed to coordinate differential brake and active aerodynamic control, and an optimal control allocation algorithm is adopted to distribute the brake pressure of each wheel. Two double lane change tests on dry and wet road performed to study the effectiveness of the control algorithm in Simulink simulation. The results show, the proposed control strategy can effectively improve the vehicle dynamics stability and tire workload usage.
{"title":"Vehicle High Speed Stability Analysis throughIntegrated Control","authors":"Nur Alyani Nadhiya, F. Yakub, Hatta Ariff, A. Azizan, Zainuddin A. Rasit, Sheikh Ahmad Zaki, Abdul Yasser Abd Fattah, Y. Mori","doi":"10.1109/SPC.2018.8703976","DOIUrl":"https://doi.org/10.1109/SPC.2018.8703976","url":null,"abstract":"This paper extends the analysis of Yakub et. al [1], by suggesting an integrated control which includes an active aerodynamic control and differential braking control to enhance high speed vehicle dynamics stability. Two aerodynamic surfaces are attached to the roof of the vehicle and servo controlled separately in real time. A hierarchical control structure which is composed of an upper and a lower controller. In the upper controller, the additional yaw moment required for stability control is determined by sliding mode control with the consideration of driver inputs, vehicle dynamic and the limitation of road adhesion. In the lower controller, a control strategy is designed to coordinate differential brake and active aerodynamic control, and an optimal control allocation algorithm is adopted to distribute the brake pressure of each wheel. Two double lane change tests on dry and wet road performed to study the effectiveness of the control algorithm in Simulink simulation. The results show, the proposed control strategy can effectively improve the vehicle dynamics stability and tire workload usage.","PeriodicalId":432464,"journal":{"name":"2018 IEEE Conference on Systems, Process and Control (ICSPC)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131927380","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 : 2018-12-01DOI: 10.1109/SPC.2018.8704131
Y. Gan, R. Hamzah, Ns. Nik Anwar
This paper proposed a new algorithm framework for stereo vision system. A four stage taxonomy is applied to obtain disparity map or depth map. The initial stage started with matching cost computation based on pixel difference adjustment strategies. In this stage, the proposed algorithm uses combination of Absolute Difference (AD) and Gradient Matching (GM) that focus on simple computation and radiometric distortion reduction. Next, the second stage continues with cost aggregation that apply image segmentation technique. Minimum spanning tree method is applied for object boundary preservation. During the third stage; disparity optimization takes a local approach by using Winner-Takes-All (WTA) strategy. This strategy normalizes the disparity values of each pixel of the image. Finally, the disparity refinement stage, noise smothering and reduction is applied on the final disparity with the aid of weighted median (WM) filter.
{"title":"Local Stereo Matching Algorithm Based on Pixel Difference Adjustment, Minimum Spanning Tree and Weighted Median Filter","authors":"Y. Gan, R. Hamzah, Ns. Nik Anwar","doi":"10.1109/SPC.2018.8704131","DOIUrl":"https://doi.org/10.1109/SPC.2018.8704131","url":null,"abstract":"This paper proposed a new algorithm framework for stereo vision system. A four stage taxonomy is applied to obtain disparity map or depth map. The initial stage started with matching cost computation based on pixel difference adjustment strategies. In this stage, the proposed algorithm uses combination of Absolute Difference (AD) and Gradient Matching (GM) that focus on simple computation and radiometric distortion reduction. Next, the second stage continues with cost aggregation that apply image segmentation technique. Minimum spanning tree method is applied for object boundary preservation. During the third stage; disparity optimization takes a local approach by using Winner-Takes-All (WTA) strategy. This strategy normalizes the disparity values of each pixel of the image. Finally, the disparity refinement stage, noise smothering and reduction is applied on the final disparity with the aid of weighted median (WM) filter.","PeriodicalId":432464,"journal":{"name":"2018 IEEE Conference on Systems, Process and Control (ICSPC)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128536604","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：