Pub Date : 2016-01-01DOI: 10.1109/ICCSCE.2016.7893632
M. N. Hashim, M. K. Osman, M. N. Ibrahim, A. F. Abidin, Mat Nizam Mahmud
Transmission lines are subjected to many kind of fault. Therefore fault location scheme is needed to determine the exact location of fault. This paper proposed a method for estimating transmission line fault location system using traveling wave method and artificial neural network (ANN). The method starts by decomposing the current signal from the faulted phase using DWT technique. Then, time fault measurement is extracted from the decomposed signal. Finally, a type of ANN called multilayer perceptron network (MLP) is used to locate the fault location. The proposed method is benchmark against the existing method and evaluated by using 5 measurement indexes; Coefficient of Determination (R2) as well as four error measures-Percentage Prediction Error (PPE), Mean Square Error (MSE), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). The results shows that integration of traveling wave and ANN absolutely could improve the performance especially for fault occurs in short distance.
{"title":"Single-ended fault location for transmission lines using traveling wave and multilayer perceptron network","authors":"M. N. Hashim, M. K. Osman, M. N. Ibrahim, A. F. Abidin, Mat Nizam Mahmud","doi":"10.1109/ICCSCE.2016.7893632","DOIUrl":"https://doi.org/10.1109/ICCSCE.2016.7893632","url":null,"abstract":"Transmission lines are subjected to many kind of fault. Therefore fault location scheme is needed to determine the exact location of fault. This paper proposed a method for estimating transmission line fault location system using traveling wave method and artificial neural network (ANN). The method starts by decomposing the current signal from the faulted phase using DWT technique. Then, time fault measurement is extracted from the decomposed signal. Finally, a type of ANN called multilayer perceptron network (MLP) is used to locate the fault location. The proposed method is benchmark against the existing method and evaluated by using 5 measurement indexes; Coefficient of Determination (R2) as well as four error measures-Percentage Prediction Error (PPE), Mean Square Error (MSE), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). The results shows that integration of traveling wave and ANN absolutely could improve the performance especially for fault occurs in short distance.","PeriodicalId":6540,"journal":{"name":"2016 6th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"10 1","pages":"522-527"},"PeriodicalIF":0.0,"publicationDate":"2016-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90084726","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 : 2016-01-01DOI: 10.1109/ICCSCE.2016.7893620
M. Sejera, Glenn O. Avendaño, Jose Norman J. Grecia, Laiza Paulene G. Neri, Justine H. Sanz, Paul Julien V. Sison, M. V. Caya
This paper presents the use of visible light as a means of data communication, utilizing a Light Emitting Diode (LED) for data transmission, specifically the super bright LED and utilizing a Laser diode (LD) module which has a more focused beam and further range. The study implemented a wireless visible light communication (VLC) system that can transmit and receive data with a range of more than 3 cm; through varying modulation techniques, namely Phase Shift Keying (PSK), Frequency Shift Keying (FSK) and, Amplitude Shift Keying (ASK). The process includes using two Arduino modules, one for signal transmission and another for signal reception. The transmitter module is connected to a computer with the Arduino software where data will be inputted for transmission. The receiver consists of a photodiode which sends the intelligence to the Arduino and projects data to the screen. In all of the said techniques, it is observed that the presence of Bit Error Rate (BER) increased as the distance between the transmitter and receiver becomes greater. The farthest distance that PSK can achieve for LED is 9.8 cm and 22.2 cm for laser. In FSK the limit is up until 9.4 cm for LED and 21.4 cm for laser. While in ASK, the BER is unacceptable for all the distances in LED but in using the laser, it can reach as long as 19.4 cm. In general, the researchers were able to extend the transmission distance far greater than 3 cm. minimum distance between the devices.
{"title":"Extension of a 3-cm range of transmission and reception of a visible light communication system through varying modulation technique","authors":"M. Sejera, Glenn O. Avendaño, Jose Norman J. Grecia, Laiza Paulene G. Neri, Justine H. Sanz, Paul Julien V. Sison, M. V. Caya","doi":"10.1109/ICCSCE.2016.7893620","DOIUrl":"https://doi.org/10.1109/ICCSCE.2016.7893620","url":null,"abstract":"This paper presents the use of visible light as a means of data communication, utilizing a Light Emitting Diode (LED) for data transmission, specifically the super bright LED and utilizing a Laser diode (LD) module which has a more focused beam and further range. The study implemented a wireless visible light communication (VLC) system that can transmit and receive data with a range of more than 3 cm; through varying modulation techniques, namely Phase Shift Keying (PSK), Frequency Shift Keying (FSK) and, Amplitude Shift Keying (ASK). The process includes using two Arduino modules, one for signal transmission and another for signal reception. The transmitter module is connected to a computer with the Arduino software where data will be inputted for transmission. The receiver consists of a photodiode which sends the intelligence to the Arduino and projects data to the screen. In all of the said techniques, it is observed that the presence of Bit Error Rate (BER) increased as the distance between the transmitter and receiver becomes greater. The farthest distance that PSK can achieve for LED is 9.8 cm and 22.2 cm for laser. In FSK the limit is up until 9.4 cm for LED and 21.4 cm for laser. While in ASK, the BER is unacceptable for all the distances in LED but in using the laser, it can reach as long as 19.4 cm. In general, the researchers were able to extend the transmission distance far greater than 3 cm. minimum distance between the devices.","PeriodicalId":6540,"journal":{"name":"2016 6th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"89 1","pages":"468-471"},"PeriodicalIF":0.0,"publicationDate":"2016-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84381398","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 : 2016-01-01DOI: 10.1109/ICCSCE.2016.7893544
N. Ya'acob, Akmarulnizam Zainuddin, Izzat Bin Zainal Abidin, A. L. Yusof, A. Idris
In this rapidly modernizing era, haze or air pollution is one of the many serious global problems for the entire population in the world. Air pollutant index (API) reading increases as haze gets worse, affecting school and aircraft schedule on top of causing respiratory problem. However, there have been occasions in Malaysia where API level published by Department of Environment (DoE) does not change despite worsening haze condition. Currently, DoE uses particulate matter PM10 to measure haze. This method is considered inaccurate because there are particle matters which are less than 10 µm3 present in the air, and they can be detected using PM2.5. This paper presents a portable device which monitor the presence of dust of size 2.5 µm3 and above. The proposed portable device consist of a dust sensor and GPS, connected to beagle bone black microcontroller which function to obtain PM2.5 API reading and coordinate and send the data to a database using sierra wireless. Users will be able to access API reading of their location using the internet web browser and therefore manage their outdoor activities. The API reading obtained is more accurate in terms of particle since the proposed system can detect small particle matter and it is real time.
{"title":"Web-based real time haze monitoring system","authors":"N. Ya'acob, Akmarulnizam Zainuddin, Izzat Bin Zainal Abidin, A. L. Yusof, A. Idris","doi":"10.1109/ICCSCE.2016.7893544","DOIUrl":"https://doi.org/10.1109/ICCSCE.2016.7893544","url":null,"abstract":"In this rapidly modernizing era, haze or air pollution is one of the many serious global problems for the entire population in the world. Air pollutant index (API) reading increases as haze gets worse, affecting school and aircraft schedule on top of causing respiratory problem. However, there have been occasions in Malaysia where API level published by Department of Environment (DoE) does not change despite worsening haze condition. Currently, DoE uses particulate matter PM10 to measure haze. This method is considered inaccurate because there are particle matters which are less than 10 µm3 present in the air, and they can be detected using PM2.5. This paper presents a portable device which monitor the presence of dust of size 2.5 µm3 and above. The proposed portable device consist of a dust sensor and GPS, connected to beagle bone black microcontroller which function to obtain PM2.5 API reading and coordinate and send the data to a database using sierra wireless. Users will be able to access API reading of their location using the internet web browser and therefore manage their outdoor activities. The API reading obtained is more accurate in terms of particle since the proposed system can detect small particle matter and it is real time.","PeriodicalId":6540,"journal":{"name":"2016 6th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"44 1","pages":"51-55"},"PeriodicalIF":0.0,"publicationDate":"2016-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86004153","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 : 2016-01-01DOI: 10.1109/ICCSCE.2016.7893588
F. M. Joseph, S. Gupta, Chetanya Rastogi, Rahul Ratan Mirdha, Ankita Puwar, Utkarsh Maheshwari, Aman Pahariya, A. De, Vishrut Kumar Mishra
The primary aim of the piece of work is to classify the extension and flexion positions of thumb, index finger and middle finger by the use of EEG Signal. The EEG Signal of a human subject is recorded and used for offline training of a feedforward neural network which is used to learn the relation between EEG and finger motion. Six features have been extracted per sample of EEG signal over 10 channels, that is, signal from 10 different regions of the brain. Analysis of the data from these 10 channels revealed a certain few important channels which have been then selected for feature extraction and training of neural network. Observations show that flexion and extension positions of these three fingers are classified successfully. This idea can be developed further to combine these classified positions to perform tasks such as object translation and rotation using a finger exoskeleton.
{"title":"Classification of extension and flexion positions of thumb, index and middle fingers using EEG Signal","authors":"F. M. Joseph, S. Gupta, Chetanya Rastogi, Rahul Ratan Mirdha, Ankita Puwar, Utkarsh Maheshwari, Aman Pahariya, A. De, Vishrut Kumar Mishra","doi":"10.1109/ICCSCE.2016.7893588","DOIUrl":"https://doi.org/10.1109/ICCSCE.2016.7893588","url":null,"abstract":"The primary aim of the piece of work is to classify the extension and flexion positions of thumb, index finger and middle finger by the use of EEG Signal. The EEG Signal of a human subject is recorded and used for offline training of a feedforward neural network which is used to learn the relation between EEG and finger motion. Six features have been extracted per sample of EEG signal over 10 channels, that is, signal from 10 different regions of the brain. Analysis of the data from these 10 channels revealed a certain few important channels which have been then selected for feature extraction and training of neural network. Observations show that flexion and extension positions of these three fingers are classified successfully. This idea can be developed further to combine these classified positions to perform tasks such as object translation and rotation using a finger exoskeleton.","PeriodicalId":6540,"journal":{"name":"2016 6th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"8 1","pages":"298-303"},"PeriodicalIF":0.0,"publicationDate":"2016-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74405133","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 : 2016-01-01DOI: 10.1109/ICCSCE.2016.7893603
A. Yumang, A. Paglinawan, Glenn O. Avendaño, C. Paglinawan, Marianne M. Sejera, Nicole Joyce J. Aquino, Alelil Joy C. Garvida, Reuvin Jireh L. Datu
In traditional teaching and learning, most students tend to laidback because of the unseen progress of their work. Introduction of this gamified outcomes-based teaching and learning assessment tool can lead into a more transparent and enthusiastic experience, providing a new perspective in the academe. The study aimed to analyze the effectiveness of the tool through the time each experiment is done and the final grades of the students.i This includes the website and the training kit for Logic Circuits and Switching Theory Laboratory (COE117L). The website comprises the gamification elements for both students and professor, while the training kit will be the source of the input data. There was a controlled group who will use the assessment tool, and an uncontrolled group that was subject to the traditional teaching and learning experience. Data showed the degree of negative linear correlation, implying that when the time of completing the experiment drops off, the grade for that experiment will increase, and vice versa. Hence, the website and the training kit were able to give instructions present in its content as well as its delivery because of the gamification process.
{"title":"Gamified outcomes-based teaching and learning assessment tool for Mapúa Institute of Technology","authors":"A. Yumang, A. Paglinawan, Glenn O. Avendaño, C. Paglinawan, Marianne M. Sejera, Nicole Joyce J. Aquino, Alelil Joy C. Garvida, Reuvin Jireh L. Datu","doi":"10.1109/ICCSCE.2016.7893603","DOIUrl":"https://doi.org/10.1109/ICCSCE.2016.7893603","url":null,"abstract":"In traditional teaching and learning, most students tend to laidback because of the unseen progress of their work. Introduction of this gamified outcomes-based teaching and learning assessment tool can lead into a more transparent and enthusiastic experience, providing a new perspective in the academe. The study aimed to analyze the effectiveness of the tool through the time each experiment is done and the final grades of the students.i This includes the website and the training kit for Logic Circuits and Switching Theory Laboratory (COE117L). The website comprises the gamification elements for both students and professor, while the training kit will be the source of the input data. There was a controlled group who will use the assessment tool, and an uncontrolled group that was subject to the traditional teaching and learning experience. Data showed the degree of negative linear correlation, implying that when the time of completing the experiment drops off, the grade for that experiment will increase, and vice versa. Hence, the website and the training kit were able to give instructions present in its content as well as its delivery because of the gamification process.","PeriodicalId":6540,"journal":{"name":"2016 6th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"11 1","pages":"380-385"},"PeriodicalIF":0.0,"publicationDate":"2016-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73076875","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 : 2016-01-01DOI: 10.1109/ICCSCE.2016.7893538
S. Muji, R. Amirulah, R. Ambar, R. A. Rahim, M. Rahiman
This paper presents the development of image reconstruction for optical tomography using Field Programmable Gate Array (FPGA) board, DE0 Nano. This design eliminated the need of computer in image reconstruction stage. Therefore, this will simplify the overall design, where the image will be displayed on an Liquid Crystal Display (LCD) only and this could make the system more portable compare to the existing design of an optical tomography system. Experimental result shows that the developed system can process image in real time as the FPGA is a type of parallel computation controller.
{"title":"Development of image reconstruction using FPGA","authors":"S. Muji, R. Amirulah, R. Ambar, R. A. Rahim, M. Rahiman","doi":"10.1109/ICCSCE.2016.7893538","DOIUrl":"https://doi.org/10.1109/ICCSCE.2016.7893538","url":null,"abstract":"This paper presents the development of image reconstruction for optical tomography using Field Programmable Gate Array (FPGA) board, DE0 Nano. This design eliminated the need of computer in image reconstruction stage. Therefore, this will simplify the overall design, where the image will be displayed on an Liquid Crystal Display (LCD) only and this could make the system more portable compare to the existing design of an optical tomography system. Experimental result shows that the developed system can process image in real time as the FPGA is a type of parallel computation controller.","PeriodicalId":6540,"journal":{"name":"2016 6th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"90 1","pages":"16-21"},"PeriodicalIF":0.0,"publicationDate":"2016-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78446573","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 : 2016-01-01DOI: 10.1109/ICCSCE.2016.7893556
L. Pohl, Ludek Buchta
In this paper the nonsmooth optimization technique is proposed for parameter tuning of a set of PI controllers. PI controllers connected in a cascade structure are controlling the stator currents and the rotor speed of PMSM (permanent magnet synchronous motor). Performance criteria are specified with weighting functions for each PI controller. Important aspects of weight design and its impact on cascade control of PMSM are presented. Nonlinear nature of PMSM is resolved by sampling LPV (linear parameter varying) model at key values of the rotor speed and creating set of design points. Tuning of cascaded PI controllers is performed as a two step procedure. In the first step the inner current loop is tuned for all the design points. As a second step to the procedure, the inner loop PI controller parameters are locked and outer speed PI controller is tuned around the q-axis current loop.
{"title":"ℋ∞ tuning technique for PMSM cascade PI control structure","authors":"L. Pohl, Ludek Buchta","doi":"10.1109/ICCSCE.2016.7893556","DOIUrl":"https://doi.org/10.1109/ICCSCE.2016.7893556","url":null,"abstract":"In this paper the nonsmooth optimization technique is proposed for parameter tuning of a set of PI controllers. PI controllers connected in a cascade structure are controlling the stator currents and the rotor speed of PMSM (permanent magnet synchronous motor). Performance criteria are specified with weighting functions for each PI controller. Important aspects of weight design and its impact on cascade control of PMSM are presented. Nonlinear nature of PMSM is resolved by sampling LPV (linear parameter varying) model at key values of the rotor speed and creating set of design points. Tuning of cascaded PI controllers is performed as a two step procedure. In the first step the inner current loop is tuned for all the design points. As a second step to the procedure, the inner loop PI controller parameters are locked and outer speed PI controller is tuned around the q-axis current loop.","PeriodicalId":6540,"journal":{"name":"2016 6th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"1 1","pages":"119-124"},"PeriodicalIF":0.0,"publicationDate":"2016-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75021382","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 : 2016-01-01DOI: 10.1109/ICCSCE.2016.7893546
Nur Adilah Abd Rahman, M. Jamil
Electroporation (EP) is a method of controlling cell function by using pulses of electrical fields to create a pore through a cell membrane and causes other substance around it to be absorbed into the cell. Where this method had been led to a variety of medical applications. In this study, we will use voltage of electroporation is 2000V/cm with pulse electric field of 30μs and single pulse to the HeLa Cell (Human Cervical cancer cell) that used as a primary cell in this study. Other than that, we also study the effect of protein surface with parameter of pulsed electric field mention above. Which are the comparison effect of HeLa cell with protein surface and an empty surface of substrate In certain cases, it is important for the cell to be in the specific location. Which also we studies on microcontact printing (μCP) method, it is a quite useful technique for patterning extracellular matrix as an adhesion molecule for cells that works for controlling the cell growth. By this two method which is EP and μCP method, we will combine this with the method in an experiment in order to see the effect of EP technique on cell properties cultured on micropatterned surface.
{"title":"Investigation of pulsed electric field on cancer cell cultured on patterned surface","authors":"Nur Adilah Abd Rahman, M. Jamil","doi":"10.1109/ICCSCE.2016.7893546","DOIUrl":"https://doi.org/10.1109/ICCSCE.2016.7893546","url":null,"abstract":"Electroporation (EP) is a method of controlling cell function by using pulses of electrical fields to create a pore through a cell membrane and causes other substance around it to be absorbed into the cell. Where this method had been led to a variety of medical applications. In this study, we will use voltage of electroporation is 2000V/cm with pulse electric field of 30μs and single pulse to the HeLa Cell (Human Cervical cancer cell) that used as a primary cell in this study. Other than that, we also study the effect of protein surface with parameter of pulsed electric field mention above. Which are the comparison effect of HeLa cell with protein surface and an empty surface of substrate In certain cases, it is important for the cell to be in the specific location. Which also we studies on microcontact printing (μCP) method, it is a quite useful technique for patterning extracellular matrix as an adhesion molecule for cells that works for controlling the cell growth. By this two method which is EP and μCP method, we will combine this with the method in an experiment in order to see the effect of EP technique on cell properties cultured on micropatterned surface.","PeriodicalId":6540,"journal":{"name":"2016 6th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"30 1","pages":"62-66"},"PeriodicalIF":0.0,"publicationDate":"2016-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74532886","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 : 2016-01-01DOI: 10.1109/ICCSCE.2016.7893584
Lawrence Charlemagne G. David, A. Ballado
The use of unmanned aerial vehicles (UAV) propelled the growing interest of small to medium farmers in precision agriculture applications. In this study, a methodology was developed to automatically map the land use in a vegetable farm with a very high resolution aerial image (5cm/pixel) taken at an altitude of 100 m. Using color index of vegetation extraction and Otsu's thresholding method, the soil was delineated from vegetation by object-based technique, and subsequently segmented the vegetation using multi-resolution algorithm. The Support Vector Machine classification on various vegetation indices produced agreeable results, where eggplant, corn, string beans and grass/weeds were classified. The classification was further improved by including Gray Level Co-Occurrence Measures or textural features, as indicated by the increase in overall accuracy and kappa index of agreement. The output map can serve as guide for farmers and other management agencies to know the correct farm interventions such as weed control. The output map can also be used in the periodic updating of the initial land cover map produced from high resolution LiDAR data.
{"title":"Vegetation indices and textures in object-based weed detection from UAV imagery","authors":"Lawrence Charlemagne G. David, A. Ballado","doi":"10.1109/ICCSCE.2016.7893584","DOIUrl":"https://doi.org/10.1109/ICCSCE.2016.7893584","url":null,"abstract":"The use of unmanned aerial vehicles (UAV) propelled the growing interest of small to medium farmers in precision agriculture applications. In this study, a methodology was developed to automatically map the land use in a vegetable farm with a very high resolution aerial image (5cm/pixel) taken at an altitude of 100 m. Using color index of vegetation extraction and Otsu's thresholding method, the soil was delineated from vegetation by object-based technique, and subsequently segmented the vegetation using multi-resolution algorithm. The Support Vector Machine classification on various vegetation indices produced agreeable results, where eggplant, corn, string beans and grass/weeds were classified. The classification was further improved by including Gray Level Co-Occurrence Measures or textural features, as indicated by the increase in overall accuracy and kappa index of agreement. The output map can serve as guide for farmers and other management agencies to know the correct farm interventions such as weed control. The output map can also be used in the periodic updating of the initial land cover map produced from high resolution LiDAR data.","PeriodicalId":6540,"journal":{"name":"2016 6th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"6 11-12 1","pages":"273-278"},"PeriodicalIF":0.0,"publicationDate":"2016-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78127108","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 : 2016-01-01DOI: 10.1109/ICCSCE.2016.7893615
Jonathan David Estilo, M. Ramos
In this work, a modularized obstacle detection system using binocular stereopsis and motion field was implemented for automated vehicles. The module used a Hardkernel Odroid XU4 Single Board Computer and two Leopard Imaging oCam OV5640 USB 3.0 Cameras. The binocular stereopsis algorithm uses Stereo Block Matching Algorithm in order to compute for disparities from spatially adjacent images. The motion field algorithm uses FAST Corner Detector and ORB Key point Descriptors in order to compute for velocity vectors from temporally adjacent images. Results show that the module was able to detect feature-rich obstacles such as vehicles and pedestrians, but it failed when it tried to detect featureless obstacles.
本文研究了一种基于双目立体视觉和运动场的模块化自动驾驶车辆障碍物检测系统。该模块采用一台硬内核Odroid XU4单板计算机和两台Leopard Imaging oCam OV5640 USB 3.0摄像头。双目立体视觉算法采用立体块匹配算法来计算空间相邻图像之间的差异。运动场算法使用FAST角点检测器和ORB关键点描述符来计算时间相邻图像的速度向量。结果表明，该模块能够检测到特征丰富的障碍物，如车辆和行人，但在检测无特征障碍物时失败。
{"title":"Obstacle detection and localization in an automated vehicle using binocular stereopsis and motion field","authors":"Jonathan David Estilo, M. Ramos","doi":"10.1109/ICCSCE.2016.7893615","DOIUrl":"https://doi.org/10.1109/ICCSCE.2016.7893615","url":null,"abstract":"In this work, a modularized obstacle detection system using binocular stereopsis and motion field was implemented for automated vehicles. The module used a Hardkernel Odroid XU4 Single Board Computer and two Leopard Imaging oCam OV5640 USB 3.0 Cameras. The binocular stereopsis algorithm uses Stereo Block Matching Algorithm in order to compute for disparities from spatially adjacent images. The motion field algorithm uses FAST Corner Detector and ORB Key point Descriptors in order to compute for velocity vectors from temporally adjacent images. Results show that the module was able to detect feature-rich obstacles such as vehicles and pedestrians, but it failed when it tried to detect featureless obstacles.","PeriodicalId":6540,"journal":{"name":"2016 6th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"32 1","pages":"446-451"},"PeriodicalIF":0.0,"publicationDate":"2016-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76090026","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：