It is proposed a new method to compute, from the current unstructured view, a reference (desired) image for visual servoing. The approach, which is based on Cartesian specifications, is made without moving the robot t...
详细信息
It is proposed a new method to compute, from the current unstructured view, a reference (desired) image for visual servoing. The approach, which is based on Cartesian specifications, is made without moving the robot to the target location as in the teach-by-showing paradigm. In addition, although it is assumed a piecewise planar target, no metric information between the object features is required. Several results demonstrate its validity and usefulness, for example in reconnaissance and surveillance tasks.
This paper presents an actuator fault detection and diagnosis system for autonomous helicopters. The system has been tested with the MARVIN autonomous helicopter. Fault detection is accomplished by evaluating any sign...
详细信息
This paper presents an actuator fault detection and diagnosis system for autonomous helicopters. The system has been tested with the MARVIN autonomous helicopter. Fault detection is accomplished by evaluating any significant change in the behaviour of the vehicle with respect to the fault-free behaviour, which is estimated by using an observer. The effectiveness of the proposed approach is demonstrated by means of MARVIN experimental results and simulations.
Several key segmentation techniques integrating region information and boundary information were reviewed. A classification of cooperative segmentation techniques was proposed, and described several algorithms with th...
详细信息
ISBN:
(纸本)0120147629
Several key segmentation techniques integrating region information and boundary information were reviewed. A classification of cooperative segmentation techniques was proposed, and described several algorithms with the aim of pointing out their strengths and weaknesses. The intention of integrating complementary information from the image may follow, it seems that a considerable improvement in segmentation could result from the fusion of color, texture, and boundary information. A hybrid strategy between embedded and postprocessing may be a solution for some of the previously mentioned typical weak points. An embedded algorithm permits the adequate placement of the seeds in an optimal position, and a result with regions free of holes may be obtained. A posteriori fusion with boundary information could refine the segmentation, improving the resulting boundaries.
The general objective of EXOCET/D is to develop, implement and test specific instruments aimed at exploring, describing, quantifying and monitoring biodiversity in deep-sea fragmented habitats as well as at identifyin...
详细信息
A mobile platform mounted with Omni-Directional vision Sensor (ODVS) can be used to monitor large areas and detect interesting events such as independently moving persons and vehicles. To avoid false alarms due to ext...
详细信息
ISBN:
(纸本)158113780X
A mobile platform mounted with Omni-Directional vision Sensor (ODVS) can be used to monitor large areas and detect interesting events such as independently moving persons and vehicles. To avoid false alarms due to extraneous features, the image motion induced by the moving platform should be compensated. This paper describes a formulation of parametric ego-motion compensation for an ODVS. Omni images give 360 degrees view of surroundings but undergo considerable image distortion. To account for these distortions, the parametric planar motion model is integrated with the transformations into omni image space. Prior knowledge of approximate camera calibration and vehicle speed are integrated with the estimation process using Bayesian approach. Iterative, coarse to fine, gradient based estimation is used to correct the motion parameters for vibrations and other inaccuracies in prior knowledge. Experiments with camera mounted on a mobile platform demonstrate successful detection of moving persons and vehicles. Copyright 2003 ACM.
In this paper, we present a fast algorithm for automatically generating a 3D model of a human face and synthesizing affects on it. This work is a step towards low bandwidth virtual tele-presence using avatars. The ide...
详细信息
In earlier work, we developed a fast method for 2-D shape retrieval based on point correspondences of silhouette contours. That method did not assume that the database shapes had class labels. If class label informati...
详细信息
In earlier work, we developed a fast method for 2-D shape retrieval based on point correspondences of silhouette contours. That method did not assume that the database shapes had class labels. If class label information is added, then the shape retrieval system can be used for 2-D shape classification. This paper explores this application, by extending our prior shape retrieval method to make use of class labels, and then evaluating its classification accuracy on a large test database containing 70 object classes. The results show that the method is both highly accurate (96.5-99.6%) and fast (< 1 second).
In recent work, we presented a correspondence-based approach for real-time retrieval from databases of 2-D shapes. The system performs with high speed and accuracy relative to other published systems as measured on a ...
详细信息
In recent work, we presented a correspondence-based approach for real-time retrieval from databases of 2-D shapes. The system performs with high speed and accuracy relative to other published systems as measured on a widely used benchmark dataset. In this paper, we test the generalization accuracy of the approach;i.e., its ability to correctly retrieve shapes from a shape database when the query shapes are not contained in the database. The experimental results show that the system's accuracy on novel inputs is nearly as high as its accuracy on shapes that are already contained in the database, demonstrating that the approach has good generalization accuracy. This result provides additional support for the use of the proposed approach for shape retrieval and object recognition applications.
Real-world objects exhibit rich physical interaction behaviours on contact. Such behaviours depend on how heavy and hard it is when held, how its surf ace feels when touched, how it deforms on contact, etc. Recently, ...
详细信息
Real-world objects exhibit rich physical interaction behaviours on contact. Such behaviours depend on how heavy and hard it is when held, how its surf ace feels when touched, how it deforms on contact, etc. Recently, there are thus growing needs for haptic exploration to estimate and extract such physical object properties ax mass, friction, elasticity, relational constraints etc.. In this paper, we propose a novel paradigm, we call haptic *** is a vision-based haptic exploration approach toward an automatic construction of reality-based virtual space simulator, by augmenting active vision with active touch. We apply this technique to mass, elational constraints estimation and elasticity, and use these results to construct virtual object manipulation simulator. Experimental results show that feasibility and validity of the proposed approach.
The particulars of facial gestures are frequently used to qualitatively define and characterize faces. It is not merely the skin motion induced by such gestures, but the appearance of the skin changes that provides th...
详细信息
ISBN:
(纸本)1581137796
The particulars of facial gestures are frequently used to qualitatively define and characterize faces. It is not merely the skin motion induced by such gestures, but the appearance of the skin changes that provides this information. For gestures and their appearance to be utilized as a biometric, it is critical that a robust model be established. For this purpose we are exploring gesture manifolds. This paper describes work underway toward evaluation of the manifold representation of facial gestures both as a biometric, and as a means to extract biometric information. Details of the current acquisition system are discussed with the motivating principles behind the device. Preliminary observations are presented to motivate manifold analysis followed by an exposition of the experiments underway that will be used to validate the model. Copyright 2003 ACM.
暂无评论