Pub Date : 2020-08-30DOI: 10.1109/CCECE47787.2020.9255750
Abdeslem Kadri, F. Mohammadi
Demand charges (DC) is one of the major utility charges especially in the case of large electricity customers. The Energy Storage System (ESS) can be optimized to minimize these charges. For instance, a large consumer can minimize his DC by incorporating an ESS that charges during his low-consuming hours and discharges during his high-consuming hours. In other words, the ESS can shave the high peak powers of the customer's load profile to ensure lower DC. In this way, the large electricity customer will be able to save a big portion of his/her energy bill of which the DC is a part. This paper presents an optimization formulation for the sizing and scheduling of the ESS to minimize the energy monthly bill through the minimization of DC. Based on the market regulations of Ontario (Canada), this study investigates the potential of using the ESS for DC minimization based on real data for a large class-A Canadian electricity customer in Ontario. The results demonstrate the effectiveness of the proposed ESS deployment algorithm in minimizing the overall energy bills of the class-A customer.
{"title":"Demand Charges Minimization for Ontario Class-A Customers Based on the Optimization of Energy Storage System","authors":"Abdeslem Kadri, F. Mohammadi","doi":"10.1109/CCECE47787.2020.9255750","DOIUrl":"https://doi.org/10.1109/CCECE47787.2020.9255750","url":null,"abstract":"Demand charges (DC) is one of the major utility charges especially in the case of large electricity customers. The Energy Storage System (ESS) can be optimized to minimize these charges. For instance, a large consumer can minimize his DC by incorporating an ESS that charges during his low-consuming hours and discharges during his high-consuming hours. In other words, the ESS can shave the high peak powers of the customer's load profile to ensure lower DC. In this way, the large electricity customer will be able to save a big portion of his/her energy bill of which the DC is a part. This paper presents an optimization formulation for the sizing and scheduling of the ESS to minimize the energy monthly bill through the minimization of DC. Based on the market regulations of Ontario (Canada), this study investigates the potential of using the ESS for DC minimization based on real data for a large class-A Canadian electricity customer in Ontario. The results demonstrate the effectiveness of the proposed ESS deployment algorithm in minimizing the overall energy bills of the class-A customer.","PeriodicalId":296506,"journal":{"name":"2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128024811","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 : 2020-08-30DOI: 10.1109/CCECE47787.2020.9255816
L. Taha, E. Abdel-Raheem
The aim of this paper is to apply blind source separation (BSS) to extract fetal electrocardiogram (FECG) signal with ectopic beat. We use a novel deterministic BSS algorithm type null space transformation matrix (NSITM). The ECG signals are used to compute the ITM. Then, the FECG signal and maternal ECG (MECG) signals are extracted from the null space of the ITM. Results from Physionet synthesized ECG data show considerable improvement in extraction performance (quality signal-to-noise ratio qSNR and correlation $r$) over other algorithms used in this work, when the fetal-to-maternal signal-to-noise ratio (fmSNR) increases from −30 dB to 0 dB. Using the NSITM algorithm, the maximum values of qSNR and $r$ are 5.95 dB and 0.871, respectively, when fmSNR is equal to 0 dB. The minimum values of qSNR and $r$ are 2.27 dB and 0.726, respectively, when fmSNR is equal to −30 dB. The study demonstrates that the BSS type NSITM is a feasible algorithm for extracting FECG signals for subjects with ectopic beats.
{"title":"Extraction of Fetal ECG Signal with Ectopic Beats using Blind Source Separation Based Null Space Approach","authors":"L. Taha, E. Abdel-Raheem","doi":"10.1109/CCECE47787.2020.9255816","DOIUrl":"https://doi.org/10.1109/CCECE47787.2020.9255816","url":null,"abstract":"The aim of this paper is to apply blind source separation (BSS) to extract fetal electrocardiogram (FECG) signal with ectopic beat. We use a novel deterministic BSS algorithm type null space transformation matrix (NSITM). The ECG signals are used to compute the ITM. Then, the FECG signal and maternal ECG (MECG) signals are extracted from the null space of the ITM. Results from Physionet synthesized ECG data show considerable improvement in extraction performance (quality signal-to-noise ratio qSNR and correlation $r$) over other algorithms used in this work, when the fetal-to-maternal signal-to-noise ratio (fmSNR) increases from −30 dB to 0 dB. Using the NSITM algorithm, the maximum values of qSNR and $r$ are 5.95 dB and 0.871, respectively, when fmSNR is equal to 0 dB. The minimum values of qSNR and $r$ are 2.27 dB and 0.726, respectively, when fmSNR is equal to −30 dB. The study demonstrates that the BSS type NSITM is a feasible algorithm for extracting FECG signals for subjects with ectopic beats.","PeriodicalId":296506,"journal":{"name":"2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124384519","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 : 2020-08-30DOI: 10.1109/CCECE47787.2020.9255680
B. Venkatesh
About 60% of the energy consumed by homes in North America is for air conditioning. With about 78% of electric energy is generated by from fossil fuels in the US, this energy use contributes to greenhouse gas emissions and global warming. Residential solar energy is now becoming cost effective and is as cost effective electric energy from the electric grid. However, solar energy availability and energy required for air conditioning are mismatched with respect to time. This mismatch in availability and need necessitates the use of energy storage. In previous works, storage of energy in thermal air mass of homes has been proposed. However, the thermostat required for such application is very complex. In this work, an artificial-neural-network-based thermostat is proposed. A method to train the model for an average home is demonstrated with an example, and the method is shown to be effective.
{"title":"Automation of Thermal Energy Storage in Homes Using Artificial Neural Networks","authors":"B. Venkatesh","doi":"10.1109/CCECE47787.2020.9255680","DOIUrl":"https://doi.org/10.1109/CCECE47787.2020.9255680","url":null,"abstract":"About 60% of the energy consumed by homes in North America is for air conditioning. With about 78% of electric energy is generated by from fossil fuels in the US, this energy use contributes to greenhouse gas emissions and global warming. Residential solar energy is now becoming cost effective and is as cost effective electric energy from the electric grid. However, solar energy availability and energy required for air conditioning are mismatched with respect to time. This mismatch in availability and need necessitates the use of energy storage. In previous works, storage of energy in thermal air mass of homes has been proposed. However, the thermostat required for such application is very complex. In this work, an artificial-neural-network-based thermostat is proposed. A method to train the model for an average home is demonstrated with an example, and the method is shown to be effective.","PeriodicalId":296506,"journal":{"name":"2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121558875","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 : 2020-08-30DOI: 10.1109/CCECE47787.2020.9255800
A. Alnoman
In this paper, a supervised machine learning approach, namely, the decision tree is used to classify IoT applications based on their delay requirements. The decision-tree is trained and tested using simulated datasets to classify tasks into delay-sensitive and delay-insensitive based on the application features such as type and location. Delay-sensitive tasks are generally related to applications such as medical, manufacturing, and connected vehicles that require high service quality and short response time. Once delay-sensitive tasks are recognized, a prioritized scheduling mechanism is implemented to reduce the queueing delay at edge devices. Here, a two-class priority queueing system is used to model the scheduling mechanism at the edge device. Results show the effectiveness of machine learning in identifying delay-sensitive tasks that will experience shorter queueing delay at the edge device to enable high quality edge computing services.
{"title":"Supporting Delay-Sensitive IoT Applications: A Machine Learning Approach","authors":"A. Alnoman","doi":"10.1109/CCECE47787.2020.9255800","DOIUrl":"https://doi.org/10.1109/CCECE47787.2020.9255800","url":null,"abstract":"In this paper, a supervised machine learning approach, namely, the decision tree is used to classify IoT applications based on their delay requirements. The decision-tree is trained and tested using simulated datasets to classify tasks into delay-sensitive and delay-insensitive based on the application features such as type and location. Delay-sensitive tasks are generally related to applications such as medical, manufacturing, and connected vehicles that require high service quality and short response time. Once delay-sensitive tasks are recognized, a prioritized scheduling mechanism is implemented to reduce the queueing delay at edge devices. Here, a two-class priority queueing system is used to model the scheduling mechanism at the edge device. Results show the effectiveness of machine learning in identifying delay-sensitive tasks that will experience shorter queueing delay at the edge device to enable high quality edge computing services.","PeriodicalId":296506,"journal":{"name":"2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122437045","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 : 2020-08-30DOI: 10.1109/CCECE47787.2020.9255775
Khoa Nguyen, A. Dinh, F. Bui
The use of infrared (IR) light for noninvasive glucose monitoring is a potential solution to reduce infection-related mortality rate for diabetic patients. However, IR spans a wide band and the relevant wavelengths need to be chosen. This paper presents an automated and computationally efficient model, capable of examining a large number of wavelengths, to determine the suitable ones for monitoring, based on feature selection and other machine learning techniques. The study examined wavelengths from 1300-2600nm which cover the majority of short-wave infrared (SWIR) band. For reliable ground truth, two datasets, D1 and D2, were used with 100 observations and 1000 observations respectively. In term of optimal performance with limited time and computational resources, Sequential Forward Floating Selection (SFFS) technique was chosen as a core feature selection algorithm due to its high accuracy and reasonable speed. Classifiers based on Support Vector Machine (SVM) were used to evaluate the performance of selected wavelengths. Principal Component Analysis (PCA) was used to enhance the accuracy. Pipeline and nested cross-validation techniques were adopted to prevent information leakage and biased results. The proposed approach managed to reduce the number of wavelengths by 65% for D1 and 58% for D2 while achieving accuracy and f1 score above 90%, which are 10% higher compared to other work in the literature. The feature selection results also suggest that suitable wavelengths fall in the range 1600–2600 nm.
{"title":"Determination of SWIR Features for Noninvasive Glucose Monitoring Using Machine Learning","authors":"Khoa Nguyen, A. Dinh, F. Bui","doi":"10.1109/CCECE47787.2020.9255775","DOIUrl":"https://doi.org/10.1109/CCECE47787.2020.9255775","url":null,"abstract":"The use of infrared (IR) light for noninvasive glucose monitoring is a potential solution to reduce infection-related mortality rate for diabetic patients. However, IR spans a wide band and the relevant wavelengths need to be chosen. This paper presents an automated and computationally efficient model, capable of examining a large number of wavelengths, to determine the suitable ones for monitoring, based on feature selection and other machine learning techniques. The study examined wavelengths from 1300-2600nm which cover the majority of short-wave infrared (SWIR) band. For reliable ground truth, two datasets, D1 and D2, were used with 100 observations and 1000 observations respectively. In term of optimal performance with limited time and computational resources, Sequential Forward Floating Selection (SFFS) technique was chosen as a core feature selection algorithm due to its high accuracy and reasonable speed. Classifiers based on Support Vector Machine (SVM) were used to evaluate the performance of selected wavelengths. Principal Component Analysis (PCA) was used to enhance the accuracy. Pipeline and nested cross-validation techniques were adopted to prevent information leakage and biased results. The proposed approach managed to reduce the number of wavelengths by 65% for D1 and 58% for D2 while achieving accuracy and f1 score above 90%, which are 10% higher compared to other work in the literature. The feature selection results also suggest that suitable wavelengths fall in the range 1600–2600 nm.","PeriodicalId":296506,"journal":{"name":"2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123930459","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 : 2020-08-30DOI: 10.1109/CCECE47787.2020.9255786
Jie Wang, Chenglei Peng, Ming Li, Xudong Chen, S. Du, Yang Li
In this paper, we focused on accelerating the stereo matching by using multi-baseline trinocular camera model. To optimize matching cost calculation and cost aggregation steps, we designed a special scheme called the trinocular dynamic disparity range (T-DDR) by narrowing disparity searching range. Based on that, we proposed the T-DDR-SGM for trinocular stereo matching. Evaluation results showed that T-DDR-SGM could significantly reduce the computational complexity with slightly improving the accuracy. We proved that the proposed optimization methods for the trinocular stereo matching are effective and the trinocular stereo matching is useful for reducing computational complexity.
{"title":"Stereo Matching Optimization with Multi-baseline Trinocular Camera Model","authors":"Jie Wang, Chenglei Peng, Ming Li, Xudong Chen, S. Du, Yang Li","doi":"10.1109/CCECE47787.2020.9255786","DOIUrl":"https://doi.org/10.1109/CCECE47787.2020.9255786","url":null,"abstract":"In this paper, we focused on accelerating the stereo matching by using multi-baseline trinocular camera model. To optimize matching cost calculation and cost aggregation steps, we designed a special scheme called the trinocular dynamic disparity range (T-DDR) by narrowing disparity searching range. Based on that, we proposed the T-DDR-SGM for trinocular stereo matching. Evaluation results showed that T-DDR-SGM could significantly reduce the computational complexity with slightly improving the accuracy. We proved that the proposed optimization methods for the trinocular stereo matching are effective and the trinocular stereo matching is useful for reducing computational complexity.","PeriodicalId":296506,"journal":{"name":"2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126791544","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 : 2020-08-30DOI: 10.1109/CCECE47787.2020.9255696
Abdallah S. Abdallah, L. Elliott, Daniel Donley
A significant portion of the internet of things (IoT) devices will become reliable products in our daily life if and only if they are equipped with strong human computer interaction (HCI) technologies, specifically visual interaction with users through affective computing. One of the major challenges faced in affective computing is recognizing facial expressions and the true emotions behind them. Despite numerous studies performed, current detection systems are ineffective at correctly identifying facial expressions with reliable accuracy, especially in case of negative expressions. Several research projects attempted to extract the recognition process that humans follow to identify facial expressions in order to replicate in smart machines without a significant success. This paper describes our interdisciplinary project whose goal is to extract and define the recognition process that humans follow when identifying the facial expressions of others. We monitor this process by identifying and analyzing the regions of interest participants look at when they are shown static emotions samples under a specific experimental setup. This paper reports the current status of data collection, experimental setup, and initial data visualization.
{"title":"Toward Smart Internet of Things (IoT) Devices: Exploring the Regions of Interest for Recognition of Facial Expressions using Eye-gaze Tracking","authors":"Abdallah S. Abdallah, L. Elliott, Daniel Donley","doi":"10.1109/CCECE47787.2020.9255696","DOIUrl":"https://doi.org/10.1109/CCECE47787.2020.9255696","url":null,"abstract":"A significant portion of the internet of things (IoT) devices will become reliable products in our daily life if and only if they are equipped with strong human computer interaction (HCI) technologies, specifically visual interaction with users through affective computing. One of the major challenges faced in affective computing is recognizing facial expressions and the true emotions behind them. Despite numerous studies performed, current detection systems are ineffective at correctly identifying facial expressions with reliable accuracy, especially in case of negative expressions. Several research projects attempted to extract the recognition process that humans follow to identify facial expressions in order to replicate in smart machines without a significant success. This paper describes our interdisciplinary project whose goal is to extract and define the recognition process that humans follow when identifying the facial expressions of others. We monitor this process by identifying and analyzing the regions of interest participants look at when they are shown static emotions samples under a specific experimental setup. This paper reports the current status of data collection, experimental setup, and initial data visualization.","PeriodicalId":296506,"journal":{"name":"2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114684897","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 : 2020-08-30DOI: 10.1109/CCECE47787.2020.9255797
S. Sudhagar, B. Surgenor, K. Hashtrudi-Zaad
This paper addresses the question as to whether a serial robot could be used to sand a wooden bowl, in order to free a human operator from what is considered a hazardous task. The process of sanding wood is similar to the polishing of metal, There are robot-based commercial systems available for the polishing of metal. However, unlike aluminum, wood is a non-homogeneous material. In the case of wooden bowls, each has a unique geometry, and to a degree, unique material properties. A hybrid force/position impedance controller was implemented and four different force control configurations were tested. The best performance was obtained with a FO filter for force control and PD action for position control.
{"title":"Robotic Sanding of Wooden Bowls with Hybrid Force/Position Impedance Control","authors":"S. Sudhagar, B. Surgenor, K. Hashtrudi-Zaad","doi":"10.1109/CCECE47787.2020.9255797","DOIUrl":"https://doi.org/10.1109/CCECE47787.2020.9255797","url":null,"abstract":"This paper addresses the question as to whether a serial robot could be used to sand a wooden bowl, in order to free a human operator from what is considered a hazardous task. The process of sanding wood is similar to the polishing of metal, There are robot-based commercial systems available for the polishing of metal. However, unlike aluminum, wood is a non-homogeneous material. In the case of wooden bowls, each has a unique geometry, and to a degree, unique material properties. A hybrid force/position impedance controller was implemented and four different force control configurations were tested. The best performance was obtained with a FO filter for force control and PD action for position control.","PeriodicalId":296506,"journal":{"name":"2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114476019","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 : 2020-08-30DOI: 10.1109/CCECE47787.2020.9255726
Yubing Liang, S. Liao
In this paper, we have discussed the computational aspects regarding to Jacobi-Fourier moments. A $k$ × $k$ numerical scheme has been applied to improve the computing accuracy of Jacobi-Fourier moments. To verify our proposed method, image reconstructions of the higher orders of Jacobi-Fourier moments have been carried out. The experimental results of reconstructing a testing image sized at 512 × 512 are highly satisfying. We have also conducted a study on image reconstructions from uneven order pairs of Jacobi-Fourier moments, {n, m}, and concluded that the order $n$ and repetition $m$ preserve the circular and radial pattern information of image, respectively.
{"title":"A Study of Jacobi-Fourier Moments via Image Reconstruction","authors":"Yubing Liang, S. Liao","doi":"10.1109/CCECE47787.2020.9255726","DOIUrl":"https://doi.org/10.1109/CCECE47787.2020.9255726","url":null,"abstract":"In this paper, we have discussed the computational aspects regarding to Jacobi-Fourier moments. A $k$ × $k$ numerical scheme has been applied to improve the computing accuracy of Jacobi-Fourier moments. To verify our proposed method, image reconstructions of the higher orders of Jacobi-Fourier moments have been carried out. The experimental results of reconstructing a testing image sized at 512 × 512 are highly satisfying. We have also conducted a study on image reconstructions from uneven order pairs of Jacobi-Fourier moments, {n, m}, and concluded that the order $n$ and repetition $m$ preserve the circular and radial pattern information of image, respectively.","PeriodicalId":296506,"journal":{"name":"2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114875263","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 : 2020-08-30DOI: 10.1109/CCECE47787.2020.9255691
Andy Couturier, M. Akhloufi
Unmanned aerial vehicles (UAV) are now used for a large number of applications in everyday life. These applications require autonomous navigation which is enabled by the self-localization solution integrated to the UAV. To perform self-localization, most UAVs are relying on a series of sensors combined with a global navigation satellite system (GNSS) in a sensor fusion framework. However, GNSS are using radio signals which are subjected to a large range of outages and interferences. This paper presents a relative visual localization (RVL) approach for GPS-denied environments using a down-facing 2D monocular camera and an inertial measurement unit (IMU). The solution is embedded in an adapted particle filter and use feature points to match images and estimate the localization of the UAV. A new conditional RVL measure is developed in order to leverage spare computation resources available during the data collection when the UAV is still receiving a GNSS signal. An evaluation of six feature point extraction methods is performed using real-world data while varying the number of feature points extracted. The results are promising and the approach has shown to be more efficient and to have fewer limitations than similar approaches in the literature.
{"title":"Conditional Probabilistic Relative Visual Localization for Unmanned Aerial Vehicles","authors":"Andy Couturier, M. Akhloufi","doi":"10.1109/CCECE47787.2020.9255691","DOIUrl":"https://doi.org/10.1109/CCECE47787.2020.9255691","url":null,"abstract":"Unmanned aerial vehicles (UAV) are now used for a large number of applications in everyday life. These applications require autonomous navigation which is enabled by the self-localization solution integrated to the UAV. To perform self-localization, most UAVs are relying on a series of sensors combined with a global navigation satellite system (GNSS) in a sensor fusion framework. However, GNSS are using radio signals which are subjected to a large range of outages and interferences. This paper presents a relative visual localization (RVL) approach for GPS-denied environments using a down-facing 2D monocular camera and an inertial measurement unit (IMU). The solution is embedded in an adapted particle filter and use feature points to match images and estimate the localization of the UAV. A new conditional RVL measure is developed in order to leverage spare computation resources available during the data collection when the UAV is still receiving a GNSS signal. An evaluation of six feature point extraction methods is performed using real-world data while varying the number of feature points extracted. The results are promising and the approach has shown to be more efficient and to have fewer limitations than similar approaches in the literature.","PeriodicalId":296506,"journal":{"name":"2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114997184","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：