Pub Date : 2013-05-30DOI: 10.1109/WORV.2013.6521923
Jianhao Du, W. Sheng
Human sensing is always an important topic for robotic applications. In this paper, we proposed an active view planning approach for human observation on a mobile robot platform with sensor data processing. The sensor adopted in our research is an inexpensive RGB-D camera. A new measure based on distance and orientation information is introduced to evaluate the quality of the viewpoint when the robot detects the human subject. The result shows that the robot can move to the best viewpoint based on the proposed approach.
{"title":"Active view planing for human observation through a RGB-D camera","authors":"Jianhao Du, W. Sheng","doi":"10.1109/WORV.2013.6521923","DOIUrl":"https://doi.org/10.1109/WORV.2013.6521923","url":null,"abstract":"Human sensing is always an important topic for robotic applications. In this paper, we proposed an active view planning approach for human observation on a mobile robot platform with sensor data processing. The sensor adopted in our research is an inexpensive RGB-D camera. A new measure based on distance and orientation information is introduced to evaluate the quality of the viewpoint when the robot detects the human subject. The result shows that the robot can move to the best viewpoint based on the proposed approach.","PeriodicalId":130461,"journal":{"name":"2013 IEEE Workshop on Robot Vision (WORV)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122569733","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 : 2013-05-30DOI: 10.1109/WORV.2013.6521919
B. Grelsson, M. Felsberg, Folke Isaksson
A method for online global pose estimation of aerial images by alignment with a georeferenced 3D model is presented. Motion stereo is used to reconstruct a dense local height patch from an image pair. The global pose is inferred from the 3D transform between the local height patch and the model. For efficiency, the sought 3D similarity transform is found by least-squares minimizations of three 2D subproblems. The method does not require any landmarks or reference points in the 3D model, but an approximate initialization of the global pose, in our case provided by onboard navigation sensors, is assumed. Real aerial images from helicopter and aircraft flights are used to evaluate the method. The results show that the accuracy of the position and orientation estimates is significantly improved compared to the initialization and our method is more robust than competing methods on similar datasets. The proposed matching error computed between the transformed patch and the map clearly indicates whether a reliable pose estimate has been obtained.
{"title":"Efficient 7D aerial pose estimation","authors":"B. Grelsson, M. Felsberg, Folke Isaksson","doi":"10.1109/WORV.2013.6521919","DOIUrl":"https://doi.org/10.1109/WORV.2013.6521919","url":null,"abstract":"A method for online global pose estimation of aerial images by alignment with a georeferenced 3D model is presented. Motion stereo is used to reconstruct a dense local height patch from an image pair. The global pose is inferred from the 3D transform between the local height patch and the model. For efficiency, the sought 3D similarity transform is found by least-squares minimizations of three 2D subproblems. The method does not require any landmarks or reference points in the 3D model, but an approximate initialization of the global pose, in our case provided by onboard navigation sensors, is assumed. Real aerial images from helicopter and aircraft flights are used to evaluate the method. The results show that the accuracy of the position and orientation estimates is significantly improved compared to the initialization and our method is more robust than competing methods on similar datasets. The proposed matching error computed between the transformed patch and the map clearly indicates whether a reliable pose estimate has been obtained.","PeriodicalId":130461,"journal":{"name":"2013 IEEE Workshop on Robot Vision (WORV)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122370063","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 : 2013-05-30DOI: 10.1109/WORV.2013.6521937
Romain Marie, O. Labbani-Igbida, Pauline Merveilleux, E. Mouaddib
This paper addresses the issues of autonomous exploration and topological mapping using monocular catadioptric vision in fully unknown environments. We propose an incremental process that allows the robot to extract and combine multiple spatial representations built upon its visual information only: free space detection, local space topology extraction, place signatures construction and topological mapping. The efficiency of the proposed system is evaluated in real world experiments. It opens new perspectives for vision-based autonomous exploration, which is still an open problem in robotics.
{"title":"Autonomous robot exploration and cognitive map building in unknown environments using omnidirectional visual information only","authors":"Romain Marie, O. Labbani-Igbida, Pauline Merveilleux, E. Mouaddib","doi":"10.1109/WORV.2013.6521937","DOIUrl":"https://doi.org/10.1109/WORV.2013.6521937","url":null,"abstract":"This paper addresses the issues of autonomous exploration and topological mapping using monocular catadioptric vision in fully unknown environments. We propose an incremental process that allows the robot to extract and combine multiple spatial representations built upon its visual information only: free space detection, local space topology extraction, place signatures construction and topological mapping. The efficiency of the proposed system is evaluated in real world experiments. It opens new perspectives for vision-based autonomous exploration, which is still an open problem in robotics.","PeriodicalId":130461,"journal":{"name":"2013 IEEE Workshop on Robot Vision (WORV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128986850","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 : 2013-05-30DOI: 10.1109/WORV.2013.6521915
J. Hedborg, M. Felsberg
Robust estimation of the relative pose between two cameras is a fundamental part of Structure and Motion methods. For calibrated cameras, the five point method together with a robust estimator such as RANSAC gives the best result in most cases. The current state-of-the-art method for solving the relative pose problem from five points is due to Nistér [9], because it is faster than other methods and in the RANSAC scheme one can improve precision by increasing the number of iterations. In this paper, we propose a new iterative method, which is based on Powell's Dog Leg algorithm. The new method has the same precision and is approximately twice as fast as Nister's algorithm. The proposed method is easily extended to more than five points while retaining a efficient error metrics. This makes it also very suitable as an refinement step. The proposed algorithm is systematically evaluated on three types of datasets with known ground truth.
两个相机之间的相对姿态的鲁棒估计是结构和运动方法的基本组成部分。对于校准过的相机，五点方法与稳健的估计器(如RANSAC)在大多数情况下给出了最好的结果。目前最先进的从五个点求解相对位姿问题的方法是由于nist[9]，因为它比其他方法更快，并且在RANSAC方案中可以通过增加迭代次数来提高精度。本文提出了一种新的基于Powell's Dog Leg算法的迭代方法。新方法具有相同的精度，并且速度大约是Nister算法的两倍。该方法易于扩展到5个点以上，同时保留了有效的误差度量。这使得它也非常适合作为一个细化步骤。该算法在三种已知地面真值的数据集上进行了系统的评估。
{"title":"Fast iterative five point relative pose estimation","authors":"J. Hedborg, M. Felsberg","doi":"10.1109/WORV.2013.6521915","DOIUrl":"https://doi.org/10.1109/WORV.2013.6521915","url":null,"abstract":"Robust estimation of the relative pose between two cameras is a fundamental part of Structure and Motion methods. For calibrated cameras, the five point method together with a robust estimator such as RANSAC gives the best result in most cases. The current state-of-the-art method for solving the relative pose problem from five points is due to Nistér [9], because it is faster than other methods and in the RANSAC scheme one can improve precision by increasing the number of iterations. In this paper, we propose a new iterative method, which is based on Powell's Dog Leg algorithm. The new method has the same precision and is approximately twice as fast as Nister's algorithm. The proposed method is easily extended to more than five points while retaining a efficient error metrics. This makes it also very suitable as an refinement step. The proposed algorithm is systematically evaluated on three types of datasets with known ground truth.","PeriodicalId":130461,"journal":{"name":"2013 IEEE Workshop on Robot Vision (WORV)","volume":"354 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115925799","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 : 2013-05-30DOI: 10.1109/WORV.2013.6521909
A. Sekmen, A. Aldroubi
Subspace segmentation and clustering of high dimensional data drawn from a union of subspaces are important with practical robot vision applications, such as smart airborne video surveillance. This paper presents a clustering algorithm for high dimensional data that comes from a union of lower dimensional subspaces of equal and known dimensions. Rigid motion segmentation is a special case of this more general subspace segmentation problem. The algorithm matches a local subspace for each trajectory vector and estimates the relationships between trajectories. It is reliable in the presence of noise, and it has been experimentally verified by the Hopkins 155 Dataset.
{"title":"Subspace and motion segmentation via local subspace estimation","authors":"A. Sekmen, A. Aldroubi","doi":"10.1109/WORV.2013.6521909","DOIUrl":"https://doi.org/10.1109/WORV.2013.6521909","url":null,"abstract":"Subspace segmentation and clustering of high dimensional data drawn from a union of subspaces are important with practical robot vision applications, such as smart airborne video surveillance. This paper presents a clustering algorithm for high dimensional data that comes from a union of lower dimensional subspaces of equal and known dimensions. Rigid motion segmentation is a special case of this more general subspace segmentation problem. The algorithm matches a local subspace for each trajectory vector and estimates the relationships between trajectories. It is reliable in the presence of noise, and it has been experimentally verified by the Hopkins 155 Dataset.","PeriodicalId":130461,"journal":{"name":"2013 IEEE Workshop on Robot Vision (WORV)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132373638","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 : 2013-05-30DOI: 10.1109/WORV.2013.6521944
Mu Fang, R. Chung
One important motivation of integrating stereo vision and visual motion into the so-called stereo-motion cue is to make the two original vision cues complementary, in the sense that (i) the ease of establishing motion correspondences and (ii) the accuracy of 3D reconstruction under stereo vision can be put together for bypassing or overcoming (i) the generally difficult stereo correspondence problem and (ii) the limited reconstruction accuracy of the motion cue. The objective is to allow a relatively short stereo pair of videos to be adequate for recovering accurate 3D information. A previous work has addressed the issue, which lets the easily acquirable motion correspondences be used to infer the stereo correspondences. Yet the inference mechanism requires to assume the affine projection model of the cameras. This work further extends from the affine camera assumption to quasi-perspective projection models of cameras. A novel stereo-motion model under quasi-perspective projection is proposed, and a simple and fast 3D reconstruction algorithm is given. Only a small number of stereo correspondences are required for reconstruction. Experimental results on real image data are shown to demonstrate the effectiveness of the mechanism.
{"title":"Quasi-perspective stereo-motion for 3D reconstruction","authors":"Mu Fang, R. Chung","doi":"10.1109/WORV.2013.6521944","DOIUrl":"https://doi.org/10.1109/WORV.2013.6521944","url":null,"abstract":"One important motivation of integrating stereo vision and visual motion into the so-called stereo-motion cue is to make the two original vision cues complementary, in the sense that (i) the ease of establishing motion correspondences and (ii) the accuracy of 3D reconstruction under stereo vision can be put together for bypassing or overcoming (i) the generally difficult stereo correspondence problem and (ii) the limited reconstruction accuracy of the motion cue. The objective is to allow a relatively short stereo pair of videos to be adequate for recovering accurate 3D information. A previous work has addressed the issue, which lets the easily acquirable motion correspondences be used to infer the stereo correspondences. Yet the inference mechanism requires to assume the affine projection model of the cameras. This work further extends from the affine camera assumption to quasi-perspective projection models of cameras. A novel stereo-motion model under quasi-perspective projection is proposed, and a simple and fast 3D reconstruction algorithm is given. Only a small number of stereo correspondences are required for reconstruction. Experimental results on real image data are shown to demonstrate the effectiveness of the mechanism.","PeriodicalId":130461,"journal":{"name":"2013 IEEE Workshop on Robot Vision (WORV)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126135947","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 : 2013-05-30DOI: 10.1109/WORV.2013.6521940
J. Piepmeier, S. Firebaugh
Microrobots have a number of potential applications for micromanipulation and assembly, but also offer challenges in power and control. This paper describes the control system for magnetically actuated microrobots operating at the interface between two immiscible fluids. The microrobots are 20 μm thick and approximately 100-200 μm in lateral dimension. Several different robot shapes are investigated. The robots and fluid are in a 20 × 20 mm vial placed at the center of four electromagnets Pulse width modulation of the electromagnet currents is used to control robot speed and direction, and a linear relationship between robot speed and duty cycle was observed, although the slope of that dependence varied with robot type and magnet. A proportional controller has been implemented and characterized. The steady-state error with this controller ranged from 6.4 to 12.8 pixels, or 90-180 μm.
{"title":"Visual servo control of electromagnetic actuation for a family of microrobot devices","authors":"J. Piepmeier, S. Firebaugh","doi":"10.1109/WORV.2013.6521940","DOIUrl":"https://doi.org/10.1109/WORV.2013.6521940","url":null,"abstract":"Microrobots have a number of potential applications for micromanipulation and assembly, but also offer challenges in power and control. This paper describes the control system for magnetically actuated microrobots operating at the interface between two immiscible fluids. The microrobots are 20 μm thick and approximately 100-200 μm in lateral dimension. Several different robot shapes are investigated. The robots and fluid are in a 20 × 20 mm vial placed at the center of four electromagnets Pulse width modulation of the electromagnet currents is used to control robot speed and direction, and a linear relationship between robot speed and duty cycle was observed, although the slope of that dependence varied with robot type and magnet. A proportional controller has been implemented and characterized. The steady-state error with this controller ranged from 6.4 to 12.8 pixels, or 90-180 μm.","PeriodicalId":130461,"journal":{"name":"2013 IEEE Workshop on Robot Vision (WORV)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133476006","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 : 2013-05-30DOI: 10.1109/WORV.2013.6521934
O. de Silva, G. Mann, R. Gosine
In this paper we detail a numerical optimization method for automated tuning of a nonlinear filter used in Attitude Heading Reference Systems (AHRS). First, the Levenberg Marquardt method is used for nonlinear parameter estimation of the observer model. Two approaches are described; Extended Kalman Filter (EKF) based supervised implementation and unsupervised error minimization based implementation. The quaternion formulation is used in the development in order to have a global minimum parametrization in the rotation group. These two methods are then compared using both simulated and experimental data taken from a commercial Inertial Measurement Unit (IMU) used in an autopilot system of an unmanned aerial vehicle. The results reveal that the proposed EKF based supervised implementation is faster and also has a better robustness against different initial conditions.
{"title":"Automated tuning of the nonlinear complementary filter for an Attitude Heading Reference observer","authors":"O. de Silva, G. Mann, R. Gosine","doi":"10.1109/WORV.2013.6521934","DOIUrl":"https://doi.org/10.1109/WORV.2013.6521934","url":null,"abstract":"In this paper we detail a numerical optimization method for automated tuning of a nonlinear filter used in Attitude Heading Reference Systems (AHRS). First, the Levenberg Marquardt method is used for nonlinear parameter estimation of the observer model. Two approaches are described; Extended Kalman Filter (EKF) based supervised implementation and unsupervised error minimization based implementation. The quaternion formulation is used in the development in order to have a global minimum parametrization in the rotation group. These two methods are then compared using both simulated and experimental data taken from a commercial Inertial Measurement Unit (IMU) used in an autopilot system of an unmanned aerial vehicle. The results reveal that the proposed EKF based supervised implementation is faster and also has a better robustness against different initial conditions.","PeriodicalId":130461,"journal":{"name":"2013 IEEE Workshop on Robot Vision (WORV)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115304906","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 : 2013-05-30DOI: 10.1109/WORV.2013.6521932
Kristoffer Öfjäll, M. Felsberg
An online method for rapidly learning the inverse kinematics of a redundant robotic arm is presented addressing the special requirements of active vision for visual inspection tasks. The system is initialized with a model covering a small area around the starting position, which is then incrementally extended by exploration. The number of motions during this process is minimized by only exploring configurations required for successful completion of the task at hand. The explored area is automatically extended online and on demand. To achieve this, state of the art methods for learning and numerical optimization are combined in a tight implementation where parts of the learned model, the Jacobians, are used during optimization, resulting in significant synergy effects. In a series of standard experiments, we show that the integrated method performs better than using both methods sequentially.
{"title":"Rapid explorative direct inverse kinematics learning of relevant locations for active vision","authors":"Kristoffer Öfjäll, M. Felsberg","doi":"10.1109/WORV.2013.6521932","DOIUrl":"https://doi.org/10.1109/WORV.2013.6521932","url":null,"abstract":"An online method for rapidly learning the inverse kinematics of a redundant robotic arm is presented addressing the special requirements of active vision for visual inspection tasks. The system is initialized with a model covering a small area around the starting position, which is then incrementally extended by exploration. The number of motions during this process is minimized by only exploring configurations required for successful completion of the task at hand. The explored area is automatically extended online and on demand. To achieve this, state of the art methods for learning and numerical optimization are combined in a tight implementation where parts of the learned model, the Jacobians, are used during optimization, resulting in significant synergy effects. In a series of standard experiments, we show that the integrated method performs better than using both methods sequentially.","PeriodicalId":130461,"journal":{"name":"2013 IEEE Workshop on Robot Vision (WORV)","volume":"19 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120914627","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 : 2013-05-30DOI: 10.1109/WORV.2013.6521925
M. Levihn, M. Dutton, A. J. Trevor, M. Silman
This paper presents a novel algorithm: Verfied Partial Object Detector (VPOD) for accurate detection of partially occluded objects such as furniture in 3D point clouds. VPOD is implemented and validated on real sensor data obtained by our robot. It extends Viewpoint Feature Histograms (VFH), which classify unoccluded objects, to also classify partially occluded objects such as furniture that might be seen in typical office environments. To achieve this result, VPOD employs two strategies. First, object models are segmented and the object database is extended to include partial models. Second, once a matching partial object is detected, the complete object model is aligned back into the scene and verified for consistency with the point cloud data. Overall, our approach increases the number of objects found and substantially reduces false positives due to the verification process.
{"title":"Detecting partially occluded objects via segmentation and validation","authors":"M. Levihn, M. Dutton, A. J. Trevor, M. Silman","doi":"10.1109/WORV.2013.6521925","DOIUrl":"https://doi.org/10.1109/WORV.2013.6521925","url":null,"abstract":"This paper presents a novel algorithm: Verfied Partial Object Detector (VPOD) for accurate detection of partially occluded objects such as furniture in 3D point clouds. VPOD is implemented and validated on real sensor data obtained by our robot. It extends Viewpoint Feature Histograms (VFH), which classify unoccluded objects, to also classify partially occluded objects such as furniture that might be seen in typical office environments. To achieve this result, VPOD employs two strategies. First, object models are segmented and the object database is extended to include partial models. Second, once a matching partial object is detected, the complete object model is aligned back into the scene and verified for consistency with the point cloud data. Overall, our approach increases the number of objects found and substantially reduces false positives due to the verification process.","PeriodicalId":130461,"journal":{"name":"2013 IEEE Workshop on Robot Vision (WORV)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127687352","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：