Pub Date : 2012-11-12DOI: 10.1109/MFI.2012.6343059
R. Luo, Yen-Chang Wu
With advances in technology, robots play an important role in our lives. Nowadays, we have more chance to see robots service in our society such as intelligent robot for rescue and for service. Therefore, Human-Robot interaction becomes an essential issue for research. In this paper we introduce a combining method for hand sign recognition. Hand sign recognition is an essential way for Human-Robot Interaction (HRI). Sign language is the most intuitive and direct way to communication for impaired or disabled people. Through the hand or body gestures, the disabled can easily let caregiver or robot know what message they want to convey. In this paper, we propose a combining hands gesture recognition algorithm which combines two distinct recognizers. These two recognizers collectively determine the hand's sign via a process called CAR equation. These two recognizers are aimed to complement the ability of discrimination. To achieve this goal, one recognizer recognizes hand gesture by hand skeleton recognizer (HSR), and the other recognizer is based on support vector machines (SVM). In addition, the corresponding classifiers of SVM are trained using different features like local binary pattern (LBP) and raw data. Furthermore, the trained images are using Bosphorus Hand Database and in addition to taking by us. A set of rules including recognizer switching and combinatorial approach recognizer CAR equation is devised to synthesize the distinctive methods. We have successfully demonstrated gesture recognition experimentally with successful proof of concept.
{"title":"Hand gesture recognition for Human-Robot Interaction for service robot","authors":"R. Luo, Yen-Chang Wu","doi":"10.1109/MFI.2012.6343059","DOIUrl":"https://doi.org/10.1109/MFI.2012.6343059","url":null,"abstract":"With advances in technology, robots play an important role in our lives. Nowadays, we have more chance to see robots service in our society such as intelligent robot for rescue and for service. Therefore, Human-Robot interaction becomes an essential issue for research. In this paper we introduce a combining method for hand sign recognition. Hand sign recognition is an essential way for Human-Robot Interaction (HRI). Sign language is the most intuitive and direct way to communication for impaired or disabled people. Through the hand or body gestures, the disabled can easily let caregiver or robot know what message they want to convey. In this paper, we propose a combining hands gesture recognition algorithm which combines two distinct recognizers. These two recognizers collectively determine the hand's sign via a process called CAR equation. These two recognizers are aimed to complement the ability of discrimination. To achieve this goal, one recognizer recognizes hand gesture by hand skeleton recognizer (HSR), and the other recognizer is based on support vector machines (SVM). In addition, the corresponding classifiers of SVM are trained using different features like local binary pattern (LBP) and raw data. Furthermore, the trained images are using Bosphorus Hand Database and in addition to taking by us. A set of rules including recognizer switching and combinatorial approach recognizer CAR equation is devised to synthesize the distinctive methods. We have successfully demonstrated gesture recognition experimentally with successful proof of concept.","PeriodicalId":103145,"journal":{"name":"2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127102631","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 : 2012-11-12DOI: 10.1109/MFI.2012.6342999
Yuanyuan Hu, Zhangjun Song, Jun‐Hua Zhu
Pipeline network is one of the city's critical infrastructures, such as lots of gas pipes and water pipes exist in public utilities, factories and so on. Regular inspection is required to ensure the static integrity of the pipes and to insure against the problems associated with failure of the pipes. We have developed a pipeline inspection robot equipped with a camera which can walk in the pipes and stream back live video to the base station. In this paper we propose a new method for estimating the posture of the robot in round pipes with a 2D Laser Rang Finder (LRF) and a dual tilt-sensor by using the geometrical characteristic of the round pipes constructed with the point cloud data. Transformation matrix from the robot coordinate system to the global system is deduced. The positions and sizes of pipe defects can be calculated easily relying on the range data and images. Experiments by the inspection robot in dry smooth HDPE pipes are carried out and the results show that the proposed method is useful and valid.
{"title":"Estimating the posture of pipeline inspection robot with a 2D Laser Rang Finder","authors":"Yuanyuan Hu, Zhangjun Song, Jun‐Hua Zhu","doi":"10.1109/MFI.2012.6342999","DOIUrl":"https://doi.org/10.1109/MFI.2012.6342999","url":null,"abstract":"Pipeline network is one of the city's critical infrastructures, such as lots of gas pipes and water pipes exist in public utilities, factories and so on. Regular inspection is required to ensure the static integrity of the pipes and to insure against the problems associated with failure of the pipes. We have developed a pipeline inspection robot equipped with a camera which can walk in the pipes and stream back live video to the base station. In this paper we propose a new method for estimating the posture of the robot in round pipes with a 2D Laser Rang Finder (LRF) and a dual tilt-sensor by using the geometrical characteristic of the round pipes constructed with the point cloud data. Transformation matrix from the robot coordinate system to the global system is deduced. The positions and sizes of pipe defects can be calculated easily relying on the range data and images. Experiments by the inspection robot in dry smooth HDPE pipes are carried out and the results show that the proposed method is useful and valid.","PeriodicalId":103145,"journal":{"name":"2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123696977","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 : 2012-11-12DOI: 10.1109/MFI.2012.6343039
Xiaodong Li, N. Aouf, A. Nemra
This paper presents an in-depth evaluation of filter algorithms utilized in the estimation of 3D position and attitude for UAV using stereo vision based Visual SLAM integrated with feature detection and matching techniques i.e., SIFT and SURF. The evaluation's aim was to investigate the accuracy and robustness of the filters' estimation for vision based navigation problems. The investigation covered several filter methods and both feature extraction algorithms behave in VSLAM applied to UAV. Statistical analyses were carried out in terms of error rates. The Robustness and relative merits of the approaches are discussed to conclude along with evidence of the filters' performances.
{"title":"Estimation analysis in VSLAM for UAV application","authors":"Xiaodong Li, N. Aouf, A. Nemra","doi":"10.1109/MFI.2012.6343039","DOIUrl":"https://doi.org/10.1109/MFI.2012.6343039","url":null,"abstract":"This paper presents an in-depth evaluation of filter algorithms utilized in the estimation of 3D position and attitude for UAV using stereo vision based Visual SLAM integrated with feature detection and matching techniques i.e., SIFT and SURF. The evaluation's aim was to investigate the accuracy and robustness of the filters' estimation for vision based navigation problems. The investigation covered several filter methods and both feature extraction algorithms behave in VSLAM applied to UAV. Statistical analyses were carried out in terms of error rates. The Robustness and relative merits of the approaches are discussed to conclude along with evidence of the filters' performances.","PeriodicalId":103145,"journal":{"name":"2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121544329","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 : 2012-11-12DOI: 10.1109/MFI.2012.6343051
Zhe Liu, Weidong Chen, Yong Wang, Jingchuan Wang
A novel approach to estimate localizability for mobile robots is presented based on probabilistic grid map (PGM). Firstly, a static localizability matrix is proposed for off-line estimation over the priori PGM. Then a dynamic localizability matrix is proposed to deal with unexpected dynamic changes. These matrices describe both localizability index and localizability direction quantitatively. The validity of the proposed method is demonstrated by experiments in different typical environments. Furthermore, two typical localization-related applications, including active global localization and pose tracking, are presented for illustrating the effectiveness of the proposed localizability estimation method.
{"title":"Localizability estimation for mobile robots based on probabilistic grid map and its applications to localization","authors":"Zhe Liu, Weidong Chen, Yong Wang, Jingchuan Wang","doi":"10.1109/MFI.2012.6343051","DOIUrl":"https://doi.org/10.1109/MFI.2012.6343051","url":null,"abstract":"A novel approach to estimate localizability for mobile robots is presented based on probabilistic grid map (PGM). Firstly, a static localizability matrix is proposed for off-line estimation over the priori PGM. Then a dynamic localizability matrix is proposed to deal with unexpected dynamic changes. These matrices describe both localizability index and localizability direction quantitatively. The validity of the proposed method is demonstrated by experiments in different typical environments. Furthermore, two typical localization-related applications, including active global localization and pose tracking, are presented for illustrating the effectiveness of the proposed localizability estimation method.","PeriodicalId":103145,"journal":{"name":"2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129490586","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 : 2012-11-12DOI: 10.1109/MFI.2012.6343030
B. Adler, Junhao Xiao
This work documents our progress on building an unmanned aerial vehicle capable of autonomously mapping urban environments. This includes localization and tracking of the vehicle's pose, fusion of sensor-data from onboard GNSS receivers, IMUs, laserscanners and cameras as well as realtime path-planning and collision-avoidance. Currently, we focus on a physics-based approach to computing waypoints, which are subsequently used to steer the platform in three-dimensional space. Generation of efficient sensor trajectories for maximized information gain operates directly on unorganized point clouds, creating a perfect fit for environment mapping with commonly used LIDAR sensors and time-of-flight cameras. We present the algorithm's application to real sensor-data and analyze its performance in a virtual outdoor scenario.
{"title":"Towards autonomous airborne mapping of urban environments","authors":"B. Adler, Junhao Xiao","doi":"10.1109/MFI.2012.6343030","DOIUrl":"https://doi.org/10.1109/MFI.2012.6343030","url":null,"abstract":"This work documents our progress on building an unmanned aerial vehicle capable of autonomously mapping urban environments. This includes localization and tracking of the vehicle's pose, fusion of sensor-data from onboard GNSS receivers, IMUs, laserscanners and cameras as well as realtime path-planning and collision-avoidance. Currently, we focus on a physics-based approach to computing waypoints, which are subsequently used to steer the platform in three-dimensional space. Generation of efficient sensor trajectories for maximized information gain operates directly on unorganized point clouds, creating a perfect fit for environment mapping with commonly used LIDAR sensors and time-of-flight cameras. We present the algorithm's application to real sensor-data and analyze its performance in a virtual outdoor scenario.","PeriodicalId":103145,"journal":{"name":"2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130780503","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 : 2012-11-12DOI: 10.1109/MFI.2012.6343057
Christian Herdtweck, Cristóbal Curio
Estimating heading information reliably from visual cues only is an important goal in human navigation research as well as in application areas ranging from robotics to automotive safety. The focus of expansion (FoE) is deemed to be important for this task. Yet, dynamic and unstructured environments like urban areas still pose an algorithmic challenge. We extend a robust learning framework that operates on optical flow and has at center stage a continuous Latent Variable Model (LVM) [1]. It accounts for missing measurements, erroneous correspondences and independent outlier motion in the visual field of view. The approach bypasses classical camera calibration through learning stages, that only require monocular video footage and corresponding platform motion information. To estimate the FoE we present both a numerical method acting on inferred optical flow fields and regression mapping, e.g. Gaussian-Process regression. We also present results for mapping to velocity, yaw, and even pitch and roll. Performance is demonstrated for car data recorded in non-stationary, urban environments.
{"title":"Monocular heading estimation in non-stationary urban environment","authors":"Christian Herdtweck, Cristóbal Curio","doi":"10.1109/MFI.2012.6343057","DOIUrl":"https://doi.org/10.1109/MFI.2012.6343057","url":null,"abstract":"Estimating heading information reliably from visual cues only is an important goal in human navigation research as well as in application areas ranging from robotics to automotive safety. The focus of expansion (FoE) is deemed to be important for this task. Yet, dynamic and unstructured environments like urban areas still pose an algorithmic challenge. We extend a robust learning framework that operates on optical flow and has at center stage a continuous Latent Variable Model (LVM) [1]. It accounts for missing measurements, erroneous correspondences and independent outlier motion in the visual field of view. The approach bypasses classical camera calibration through learning stages, that only require monocular video footage and corresponding platform motion information. To estimate the FoE we present both a numerical method acting on inferred optical flow fields and regression mapping, e.g. Gaussian-Process regression. We also present results for mapping to velocity, yaw, and even pitch and roll. Performance is demonstrated for car data recorded in non-stationary, urban environments.","PeriodicalId":103145,"journal":{"name":"2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134368416","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 : 2012-11-12DOI: 10.1109/MFI.2012.6343003
M. Baum, F. Faion, U. Hanebeck
This paper is about an experimental set-up for tracking a ground moving mobile object from a bird's eye view. In this experiment, an RGB and depth camera is used for detecting moving points. The detected points serve as input for a probabilistic extended object tracking algorithm that simultaneously estimates the kinematic parameters and the shape parameters of the object. By this means, it is easy to discriminate moving objects from the background and the probabilistic tracking algorithm ensures a robust and smooth shape estimate. We provide an experimental evaluation of a recent Bayesian extended object tracking algorithm based on a so-called Random Hypersurface Model and give a comparison with active contour models.
{"title":"Tracking ground moving extended objects using RGBD data","authors":"M. Baum, F. Faion, U. Hanebeck","doi":"10.1109/MFI.2012.6343003","DOIUrl":"https://doi.org/10.1109/MFI.2012.6343003","url":null,"abstract":"This paper is about an experimental set-up for tracking a ground moving mobile object from a bird's eye view. In this experiment, an RGB and depth camera is used for detecting moving points. The detected points serve as input for a probabilistic extended object tracking algorithm that simultaneously estimates the kinematic parameters and the shape parameters of the object. By this means, it is easy to discriminate moving objects from the background and the probabilistic tracking algorithm ensures a robust and smooth shape estimate. We provide an experimental evaluation of a recent Bayesian extended object tracking algorithm based on a so-called Random Hypersurface Model and give a comparison with active contour models.","PeriodicalId":103145,"journal":{"name":"2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132020829","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 : 2012-11-12DOI: 10.1109/MFI.2012.6343009
Feihu Zhang, H. Stahle, Guang Chen, Chao-Wei Chen, Carsten Simon, C. Buckl, A. Knoll
This paper describes a robust approach which improves the precision of vehicle localization in complex urban environments by fusing data from GPS, gyroscope and velocity sensors. In this method, we apply Kalman filter to estimate the position of the vehicle. Compared with other fusion based localization approaches, we process the data in a public coordinate system, called Earth Centred Earth Fixed (ECEF) coordinates and eliminate the cumulative error by its statistics characteristics. The contribution is that it not only provides a sensor fusion framework to estimate the position of the vehicle, but also gives a mathematical solution to eliminate the cumulative error stems from the relative pose measurements (provided by the gyroscope and velocity sensors). The experiments exhibit the reliability and the feasibility of our approach in large scale environment.
{"title":"A sensor fusion approach for localization with cumulative error elimination","authors":"Feihu Zhang, H. Stahle, Guang Chen, Chao-Wei Chen, Carsten Simon, C. Buckl, A. Knoll","doi":"10.1109/MFI.2012.6343009","DOIUrl":"https://doi.org/10.1109/MFI.2012.6343009","url":null,"abstract":"This paper describes a robust approach which improves the precision of vehicle localization in complex urban environments by fusing data from GPS, gyroscope and velocity sensors. In this method, we apply Kalman filter to estimate the position of the vehicle. Compared with other fusion based localization approaches, we process the data in a public coordinate system, called Earth Centred Earth Fixed (ECEF) coordinates and eliminate the cumulative error by its statistics characteristics. The contribution is that it not only provides a sensor fusion framework to estimate the position of the vehicle, but also gives a mathematical solution to eliminate the cumulative error stems from the relative pose measurements (provided by the gyroscope and velocity sensors). The experiments exhibit the reliability and the feasibility of our approach in large scale environment.","PeriodicalId":103145,"journal":{"name":"2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114757731","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 : 2012-11-12DOI: 10.1109/MFI.2012.6343013
J. Trapnauskas, M. Romanovas, L. Klingbeil, A. Al-Jawad, M. Trächtler, Y. Manoli
The work demonstrates how the methods of Active Sensing (AS), based on the theory of optimal experimental design, can be applied for a location estimation scenario. The simulated problem consists of several mobile and fixed nodes where each mobile unit is equipped with a gyroscope and an incremental path encoder and is capable to make a selective range measurement to one of several fixed anchors as well as to other moving tags. All available measurements are combined within a fusion filter, while the range measurements are selected with one of the AS methods in order to minimize the position uncertainty under the constraints of a maximum available measurement rate. Different AS strategies are incorporated into a recursive Bayesian estimation framework in the form of Extended Kalman and Particle Filters. The performance of the fusion algorithms augmented with the active sensing techniques is discussed for several scenarios with different measurement rates and a number of fixed or moving tags.
{"title":"On Active Sensing methods for localization scenarios with range-based measurements","authors":"J. Trapnauskas, M. Romanovas, L. Klingbeil, A. Al-Jawad, M. Trächtler, Y. Manoli","doi":"10.1109/MFI.2012.6343013","DOIUrl":"https://doi.org/10.1109/MFI.2012.6343013","url":null,"abstract":"The work demonstrates how the methods of Active Sensing (AS), based on the theory of optimal experimental design, can be applied for a location estimation scenario. The simulated problem consists of several mobile and fixed nodes where each mobile unit is equipped with a gyroscope and an incremental path encoder and is capable to make a selective range measurement to one of several fixed anchors as well as to other moving tags. All available measurements are combined within a fusion filter, while the range measurements are selected with one of the AS methods in order to minimize the position uncertainty under the constraints of a maximum available measurement rate. Different AS strategies are incorporated into a recursive Bayesian estimation framework in the form of Extended Kalman and Particle Filters. The performance of the fusion algorithms augmented with the active sensing techniques is discussed for several scenarios with different measurement rates and a number of fixed or moving tags.","PeriodicalId":103145,"journal":{"name":"2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114787873","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 : 2012-11-12DOI: 10.1109/MFI.2012.6343000
Y. Xu, J. Y. Wang, B. Cao, J. Yang
This paper presents an ultrasonic sensing based human face identification approach. As a biometric identification method, ultrasonic sensing could detect the geometric structure of faces without being affected by the illumination of the environment. Multi ultrasonic sensors are used for data collection. Continuous Transmitted Frequency Modulated (CTFM) signal is chosen as the detection signal. High Resolution Range Profile (HRRP) is extracted from the echo signal as the feature and a K nearest neighbor (KNN) classifier is used for the face classification. Data fusion is applied to improve the performance for identifying faces with multi facial expressions. Experimental results show a success rate of more than 96.9% when the test database includes 62 persons and 5 facial expressions for each person. The results prove that multi sensors ultrasonic sensing could be a potential competent face identification solution for many applications.
{"title":"Multi sensors based ultrasonic human face identification: Experiment and analysis","authors":"Y. Xu, J. Y. Wang, B. Cao, J. Yang","doi":"10.1109/MFI.2012.6343000","DOIUrl":"https://doi.org/10.1109/MFI.2012.6343000","url":null,"abstract":"This paper presents an ultrasonic sensing based human face identification approach. As a biometric identification method, ultrasonic sensing could detect the geometric structure of faces without being affected by the illumination of the environment. Multi ultrasonic sensors are used for data collection. Continuous Transmitted Frequency Modulated (CTFM) signal is chosen as the detection signal. High Resolution Range Profile (HRRP) is extracted from the echo signal as the feature and a K nearest neighbor (KNN) classifier is used for the face classification. Data fusion is applied to improve the performance for identifying faces with multi facial expressions. Experimental results show a success rate of more than 96.9% when the test database includes 62 persons and 5 facial expressions for each person. The results prove that multi sensors ultrasonic sensing could be a potential competent face identification solution for many applications.","PeriodicalId":103145,"journal":{"name":"2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)","volume":"308 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123481817","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：