Pub Date : 2013-03-25DOI: 10.1109/ICE-CCN.2013.6528549
R. Simon, A. Geetha
This paper presents the fuzzy and ANFIS control system for Induction motor drives for better performance. The design and simulation of fuzzy logic controller and ANFIS for Induction motor are carried out based on fuzzy set theory and Back propagation. Fuzzy Controller will produce the output based on the rules provided and that are based on human experience. Whereas ANFIS is a best tradeoff between neural and fuzzy system which provide smoothness, due to the fuzzy controller (FC) interpolation and adaptability due to the neural network (NN) Back propagation. Simulated result for Fuzzy and ANFIS controlled Induction motor shows that latter exhibit better results.
{"title":"Comparison on the performance of Induction motor control using fuzzy and ANFIS controllers","authors":"R. Simon, A. Geetha","doi":"10.1109/ICE-CCN.2013.6528549","DOIUrl":"https://doi.org/10.1109/ICE-CCN.2013.6528549","url":null,"abstract":"This paper presents the fuzzy and ANFIS control system for Induction motor drives for better performance. The design and simulation of fuzzy logic controller and ANFIS for Induction motor are carried out based on fuzzy set theory and Back propagation. Fuzzy Controller will produce the output based on the rules provided and that are based on human experience. Whereas ANFIS is a best tradeoff between neural and fuzzy system which provide smoothness, due to the fuzzy controller (FC) interpolation and adaptability due to the neural network (NN) Back propagation. Simulated result for Fuzzy and ANFIS controlled Induction motor shows that latter exhibit better results.","PeriodicalId":286830,"journal":{"name":"2013 IEEE International Conference ON Emerging Trends in Computing, Communication and Nanotechnology (ICECCN)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115381733","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 : 2013-03-25DOI: 10.1109/ICE-CCN.2013.6528535
V. Venus, K. Ramani
Multilevel inverter is as one of the most recent and popular type of advances in power electronics. It synthesizes desired output voltage waveform from several dc sources used as input for the multilevel inverter. This paper describes a diode-clamped five-level inverter-based battery/super capacitor direct integration scheme for photovoltaic energy systems. The study is carried out for three cases. In the first case, one of the two dc-link capacitors of the inverter is replaced by a battery bank and the other by a super capacitor bank. In the second case, dc-link capacitors are replaced by two battery banks. In the third case, ordinary dc-link capacitors are replaced by two super capacitor banks. The first system is supposed to mitigate both long-term and short-term power fluctuations while the last two systems are intended for smoothening long-term and short-term power fluctuations, respectively. These topologies eliminate the need for interfacing dc-dc converters and thus considerably improve the overall system efficiency. The major issue in aforementioned systems is the unavoidable imbalance in dc-link voltages. An analysis on the effects of unbalance and a space vector modulation method, which can produce undistorted current even in the presence of such unbalances, are presented in this paper. Simulation work is done using the MATLAB software which validates the proposed method and finally THD comparison is presented for analysis.
{"title":"Implementation of SVPWM technique based diode clamped five-level inverter direct integration scheme for photovoltaic systems","authors":"V. Venus, K. Ramani","doi":"10.1109/ICE-CCN.2013.6528535","DOIUrl":"https://doi.org/10.1109/ICE-CCN.2013.6528535","url":null,"abstract":"Multilevel inverter is as one of the most recent and popular type of advances in power electronics. It synthesizes desired output voltage waveform from several dc sources used as input for the multilevel inverter. This paper describes a diode-clamped five-level inverter-based battery/super capacitor direct integration scheme for photovoltaic energy systems. The study is carried out for three cases. In the first case, one of the two dc-link capacitors of the inverter is replaced by a battery bank and the other by a super capacitor bank. In the second case, dc-link capacitors are replaced by two battery banks. In the third case, ordinary dc-link capacitors are replaced by two super capacitor banks. The first system is supposed to mitigate both long-term and short-term power fluctuations while the last two systems are intended for smoothening long-term and short-term power fluctuations, respectively. These topologies eliminate the need for interfacing dc-dc converters and thus considerably improve the overall system efficiency. The major issue in aforementioned systems is the unavoidable imbalance in dc-link voltages. An analysis on the effects of unbalance and a space vector modulation method, which can produce undistorted current even in the presence of such unbalances, are presented in this paper. Simulation work is done using the MATLAB software which validates the proposed method and finally THD comparison is presented for analysis.","PeriodicalId":286830,"journal":{"name":"2013 IEEE International Conference ON Emerging Trends in Computing, Communication and Nanotechnology (ICECCN)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124198991","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 : 2013-03-25DOI: 10.1109/ICE-CCN.2013.6528586
E. F. I. Raj, V. Kamaraj
Switched Reluctance Motors (SRMs) have evolved to represent interesting solutions for variable speed drive applications, due to their low cost and high dynamic performance capabilities. On the other hand, a number of less positive characteristics, such as their nonlinear behavior, and the existence of a significant torque ripple in the output also accompanied by audible noise, make the control problem associated with their operation a challenging task. These things limited their deployment in practical applications. The motivation of the present work is to simplify the control of SRM using Neural Network based control, to cut down the complexity and cost so that it can be accepted as a viable variable speed drive in general and a preferred drive for industrial and domestic applications This paper deals with the neural network based control for 8/6 pole Switched Reluctance Motor. Here, the neural network based controller, which is used to obtain the optimum turn on and turn off angles to minimize the torque ripple and speed ripple. The machine is modeled and simulated using Matlab / Simulink environment. The output response shows good dynamic behavior of the system.
{"title":"Neural network based control for Switched Reluctance Motor drive","authors":"E. F. I. Raj, V. Kamaraj","doi":"10.1109/ICE-CCN.2013.6528586","DOIUrl":"https://doi.org/10.1109/ICE-CCN.2013.6528586","url":null,"abstract":"Switched Reluctance Motors (SRMs) have evolved to represent interesting solutions for variable speed drive applications, due to their low cost and high dynamic performance capabilities. On the other hand, a number of less positive characteristics, such as their nonlinear behavior, and the existence of a significant torque ripple in the output also accompanied by audible noise, make the control problem associated with their operation a challenging task. These things limited their deployment in practical applications. The motivation of the present work is to simplify the control of SRM using Neural Network based control, to cut down the complexity and cost so that it can be accepted as a viable variable speed drive in general and a preferred drive for industrial and domestic applications This paper deals with the neural network based control for 8/6 pole Switched Reluctance Motor. Here, the neural network based controller, which is used to obtain the optimum turn on and turn off angles to minimize the torque ripple and speed ripple. The machine is modeled and simulated using Matlab / Simulink environment. The output response shows good dynamic behavior of the system.","PeriodicalId":286830,"journal":{"name":"2013 IEEE International Conference ON Emerging Trends in Computing, Communication and Nanotechnology (ICECCN)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124380401","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 : 2013-03-25DOI: 10.1109/ICE-CCN.2013.6528471
Gurinder Pal Singh, B. Raj
In this paper theoretical concepts based on analytical models for Single Electron Transistor (SET) are presented. It has been observed that the fabrication technology has reached on its limits for the MOS feature size, beyond which further scaling of the channel is not achievable. Due to which SET is considered as the future of the complex IC fabrication by replacing MOS technology, having small quantum dot or island, instead of channel. Working of the SET is based on the Coulomb blockade principle which is the heart of the technology. Quantum mechanics is the physics used for explaining the tunnelling of single electron of SET, which says that the energy levels are quantized not continuous. Main reason behind the advancement in SET is the market requirement of the low power, high density and fast switching devices. These are possible by SET; no doubt speed is an issue for the memories designed with SET, with its low gain and high input impedance. In the review, mathematical model including tunnelling effect in junction, coulomb blockade, current equation, free energy equation based on Shcrodinger's wave equation are presented.
{"title":"Single Electron Transistor theory: A review","authors":"Gurinder Pal Singh, B. Raj","doi":"10.1109/ICE-CCN.2013.6528471","DOIUrl":"https://doi.org/10.1109/ICE-CCN.2013.6528471","url":null,"abstract":"In this paper theoretical concepts based on analytical models for Single Electron Transistor (SET) are presented. It has been observed that the fabrication technology has reached on its limits for the MOS feature size, beyond which further scaling of the channel is not achievable. Due to which SET is considered as the future of the complex IC fabrication by replacing MOS technology, having small quantum dot or island, instead of channel. Working of the SET is based on the Coulomb blockade principle which is the heart of the technology. Quantum mechanics is the physics used for explaining the tunnelling of single electron of SET, which says that the energy levels are quantized not continuous. Main reason behind the advancement in SET is the market requirement of the low power, high density and fast switching devices. These are possible by SET; no doubt speed is an issue for the memories designed with SET, with its low gain and high input impedance. In the review, mathematical model including tunnelling effect in junction, coulomb blockade, current equation, free energy equation based on Shcrodinger's wave equation are presented.","PeriodicalId":286830,"journal":{"name":"2013 IEEE International Conference ON Emerging Trends in Computing, Communication and Nanotechnology (ICECCN)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114839574","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 : 2013-03-25DOI: 10.1109/ICE-CCN.2013.6528583
R. K. Mishra, T. K. Dan
The prime objective of any industrial process is to perform efficiently with variable cost reduction. Internal Model Control (IMC) is a commonly used technique that provides a transparent mode for the designing and tuning of various types of control architecture. In this paper, we have designed the internal model control for binary distillation column for SISO process. The transfer function has been taken from Wood and Berry model. The internal model control has been designed considering three strategies namely, process perfect, process mismatch with disturbances and process model with disturbance only. It has also been tried to reduce the disturbance created in the system by varying tuning parameter (λ).
{"title":"Design of an Internal Model Control for SISO binary distillation column","authors":"R. K. Mishra, T. K. Dan","doi":"10.1109/ICE-CCN.2013.6528583","DOIUrl":"https://doi.org/10.1109/ICE-CCN.2013.6528583","url":null,"abstract":"The prime objective of any industrial process is to perform efficiently with variable cost reduction. Internal Model Control (IMC) is a commonly used technique that provides a transparent mode for the designing and tuning of various types of control architecture. In this paper, we have designed the internal model control for binary distillation column for SISO process. The transfer function has been taken from Wood and Berry model. The internal model control has been designed considering three strategies namely, process perfect, process mismatch with disturbances and process model with disturbance only. It has also been tried to reduce the disturbance created in the system by varying tuning parameter (λ).","PeriodicalId":286830,"journal":{"name":"2013 IEEE International Conference ON Emerging Trends in Computing, Communication and Nanotechnology (ICECCN)","volume":"465 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116167102","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 : 2013-03-25DOI: 10.1109/ICE-CCN.2013.6528585
P. Eswaran, A. Manikandan, S. Godha
This work proposes to develop and implement a prototype model of an efficient unmanned car parking system using microcontroller. Model developed for underground car parking with multiple floors, prevents the usage of the parking space at ground level. Entire process was automated so that it reduces the time wasted by a person to park a car. This model uses two circular floors, with six car-parking slots in each floor. This mechanism has centre primary shaft holding a lift to transport the vehicle to its appropriate parking slot. Various sensors, motors and software were used to detect and transport the car to its allocated parking slot. Hence, this system provides a closed loop control, making it an efficient, accurate, secure and a convenient method proposed for parking cars in both commercial and residential areas.
{"title":"Prototype of an underground multi-storied automated car parking system","authors":"P. Eswaran, A. Manikandan, S. Godha","doi":"10.1109/ICE-CCN.2013.6528585","DOIUrl":"https://doi.org/10.1109/ICE-CCN.2013.6528585","url":null,"abstract":"This work proposes to develop and implement a prototype model of an efficient unmanned car parking system using microcontroller. Model developed for underground car parking with multiple floors, prevents the usage of the parking space at ground level. Entire process was automated so that it reduces the time wasted by a person to park a car. This model uses two circular floors, with six car-parking slots in each floor. This mechanism has centre primary shaft holding a lift to transport the vehicle to its appropriate parking slot. Various sensors, motors and software were used to detect and transport the car to its allocated parking slot. Hence, this system provides a closed loop control, making it an efficient, accurate, secure and a convenient method proposed for parking cars in both commercial and residential areas.","PeriodicalId":286830,"journal":{"name":"2013 IEEE International Conference ON Emerging Trends in Computing, Communication and Nanotechnology (ICECCN)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129910215","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 : 2013-03-25DOI: 10.1109/ICE-CCN.2013.6528571
G. Viswanathan, A. Murugesan, K. Nallaperumal
The thinning algorithm proposed in this paper, is an improved parallel thinning algorithm that aims in both, medial axis based thinning and contour extraction in a same process. In the process of thinning to obtain the medial axis of the character the points are deleted from outer boundary first and then proceeded inside till a single pixel wide skeleton is produced. In this process the outermost boundary line alone is preserved which is then produced as the contour of the image. So within one algorithm we get the two major categories of skeletonization, Medial axis Transform and contour extraction. Experiments are done on printed English characters and the results show that this algorithm is very effective.
{"title":"A parallel thinning algorithm for contour extraction and medial axis transform","authors":"G. Viswanathan, A. Murugesan, K. Nallaperumal","doi":"10.1109/ICE-CCN.2013.6528571","DOIUrl":"https://doi.org/10.1109/ICE-CCN.2013.6528571","url":null,"abstract":"The thinning algorithm proposed in this paper, is an improved parallel thinning algorithm that aims in both, medial axis based thinning and contour extraction in a same process. In the process of thinning to obtain the medial axis of the character the points are deleted from outer boundary first and then proceeded inside till a single pixel wide skeleton is produced. In this process the outermost boundary line alone is preserved which is then produced as the contour of the image. So within one algorithm we get the two major categories of skeletonization, Medial axis Transform and contour extraction. Experiments are done on printed English characters and the results show that this algorithm is very effective.","PeriodicalId":286830,"journal":{"name":"2013 IEEE International Conference ON Emerging Trends in Computing, Communication and Nanotechnology (ICECCN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129367873","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 : 2013-03-25DOI: 10.1109/ICE-CCN.2013.6528475
D. J. Harmah, D. Kathirvelu
Miniaturization of devices has brought a lot of improvements in the healthcare delivery as a result of advancenments in Integrated circuit technologies. As a result, proper and effective way of analyzing various body conditions and diseases can be achieved. When the heart muscles repolarize and depolarize, it generates electrical impulses which could help the doctor or the health professional to diagnose various heart abnormalities. The aim of this project is to design and develop a miniaturized ECG system displayed on both PC and Tablet for preliminary diagnoses of the heart. This system utilizes a programmable single-chip microcontroller for analysing the biosignals to indicate the condition of the heart. The system is incomporated with alarm systems which prompt the doctor if there is any abnormality from a patient's heart. These abnormalities could be bradycardia or tachycardia. This system is built with a provision of enabling wireless transmission of ECG signals to a PC or TABLET through BLUETOOTH and ANDROID PLATFORM. The android application can be installed and tested on any smart phone or tablet and screen resolution can be adjusted later as per requirement. This helps the doctor to have visual description of the patient ECG without the need of mounted monitors. The experimental results show that device is clinically useful, compact, cost effective and user friendly.
{"title":"An ubiquitous miniaturized android based ECG monitoring system","authors":"D. J. Harmah, D. Kathirvelu","doi":"10.1109/ICE-CCN.2013.6528475","DOIUrl":"https://doi.org/10.1109/ICE-CCN.2013.6528475","url":null,"abstract":"Miniaturization of devices has brought a lot of improvements in the healthcare delivery as a result of advancenments in Integrated circuit technologies. As a result, proper and effective way of analyzing various body conditions and diseases can be achieved. When the heart muscles repolarize and depolarize, it generates electrical impulses which could help the doctor or the health professional to diagnose various heart abnormalities. The aim of this project is to design and develop a miniaturized ECG system displayed on both PC and Tablet for preliminary diagnoses of the heart. This system utilizes a programmable single-chip microcontroller for analysing the biosignals to indicate the condition of the heart. The system is incomporated with alarm systems which prompt the doctor if there is any abnormality from a patient's heart. These abnormalities could be bradycardia or tachycardia. This system is built with a provision of enabling wireless transmission of ECG signals to a PC or TABLET through BLUETOOTH and ANDROID PLATFORM. The android application can be installed and tested on any smart phone or tablet and screen resolution can be adjusted later as per requirement. This helps the doctor to have visual description of the patient ECG without the need of mounted monitors. The experimental results show that device is clinically useful, compact, cost effective and user friendly.","PeriodicalId":286830,"journal":{"name":"2013 IEEE International Conference ON Emerging Trends in Computing, Communication and Nanotechnology (ICECCN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129560510","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 : 2013-03-25DOI: 10.1109/ICE-CCN.2013.6528507
A. Rajeswari, C. Deisy, J. Preethi
Most of the data mining algorithms perform analysis on quantitative data only after performing discretization. Nowadays, there is a great interest in finding the health impacts of climate change. One of the factors that cause changes in the climate is the ozone layer. Adverse levels of ozone may cause several diseases like asthma, chronic disorders and other respiratory symptoms. Hereby we present an evolutionary approach based association technique to find the relationship between several multidimensional climatological variables that are involved in determining an ozone day. The relationships between variables are discovered by generating quantitative association rules that exhibit a temporal pattern. When association rules are generated from high dimensional quantitative databases, the rules suffer from loss of information due to discretization. To overcome this problem, the proposed approach involves genetic algorithm to discover all possible dependencies between variables with optimal intervals. Our method generates quantitative association rules on temporal database, with more realistic interval rather than crisp boundary.
{"title":"Generation of temporal class association rules from quantitative data using evolutionary approach","authors":"A. Rajeswari, C. Deisy, J. Preethi","doi":"10.1109/ICE-CCN.2013.6528507","DOIUrl":"https://doi.org/10.1109/ICE-CCN.2013.6528507","url":null,"abstract":"Most of the data mining algorithms perform analysis on quantitative data only after performing discretization. Nowadays, there is a great interest in finding the health impacts of climate change. One of the factors that cause changes in the climate is the ozone layer. Adverse levels of ozone may cause several diseases like asthma, chronic disorders and other respiratory symptoms. Hereby we present an evolutionary approach based association technique to find the relationship between several multidimensional climatological variables that are involved in determining an ozone day. The relationships between variables are discovered by generating quantitative association rules that exhibit a temporal pattern. When association rules are generated from high dimensional quantitative databases, the rules suffer from loss of information due to discretization. To overcome this problem, the proposed approach involves genetic algorithm to discover all possible dependencies between variables with optimal intervals. Our method generates quantitative association rules on temporal database, with more realistic interval rather than crisp boundary.","PeriodicalId":286830,"journal":{"name":"2013 IEEE International Conference ON Emerging Trends in Computing, Communication and Nanotechnology (ICECCN)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132165521","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 : 2013-03-25DOI: 10.1109/ICE-CCN.2013.6528484
K. Devi, N. Malmurugan, H. Ambika
In this paper, we introduce new method to segment the moving regions from compressed video by incorporating more features from different previous segmentation methods. Briefly, our method proceeds as follows. First we classify the macroblocks of the compressed video frames into different classes and we perform Global Motion Estimation and Global motion Compensation techniques to remove the influence of camera motion on the Motion Vector field from the compressed video. Then Motion vector quantization (VQ) based on similarity of local motion is used to find the likely number of moving regions. The inferred statistics are used to initialize prior probabilities for subsequent Markov Random field (MRF) classification, which produces coarse segmentation map. Finally, coarse to fine strategy is utilized to refine region boundaries. This proposed approach produces accuracy in segmentation. While each of these components has been employed in previous segmentation approaches, we believe that complete solution incorporating all of the listed components is novel and represents the main contribution of this work.
{"title":"Moving region segmentation from compressed video using Global Motion Estimation by macroblock classification and Markov Random field model","authors":"K. Devi, N. Malmurugan, H. Ambika","doi":"10.1109/ICE-CCN.2013.6528484","DOIUrl":"https://doi.org/10.1109/ICE-CCN.2013.6528484","url":null,"abstract":"In this paper, we introduce new method to segment the moving regions from compressed video by incorporating more features from different previous segmentation methods. Briefly, our method proceeds as follows. First we classify the macroblocks of the compressed video frames into different classes and we perform Global Motion Estimation and Global motion Compensation techniques to remove the influence of camera motion on the Motion Vector field from the compressed video. Then Motion vector quantization (VQ) based on similarity of local motion is used to find the likely number of moving regions. The inferred statistics are used to initialize prior probabilities for subsequent Markov Random field (MRF) classification, which produces coarse segmentation map. Finally, coarse to fine strategy is utilized to refine region boundaries. This proposed approach produces accuracy in segmentation. While each of these components has been employed in previous segmentation approaches, we believe that complete solution incorporating all of the listed components is novel and represents the main contribution of this work.","PeriodicalId":286830,"journal":{"name":"2013 IEEE International Conference ON Emerging Trends in Computing, Communication and Nanotechnology (ICECCN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130919717","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：