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.
Nowadays Unmanned Underwater Vehicles (UlNs) are used in a growing number of underwater missions, mostly inspections of different types of installations such as: telecommunication cables, pipes or oil extraction insta...
详细信息
作者：
Puente, S.T.Torres, F.Aracil, R.Automatics
Robotics and Computer Vision Group Dept. of Physics Systems Engineering and Signal Theory University of Alicante Spain DISAM
Polytechnic University of Madrid Spain
Product disassembly for reusing or recycling can be done in a destructive or not-destructive way. Furthermore, to achieve an automatic disassembly, a robot arm has to be considered for doing the desired task. This pap...
详细信息
This paper presents and evaluates a pixel-based texture classifier that integrates multiple texture feature extraction methods through a new scheme based on the Kullback J-divergence. Experimental results show that th...
详细信息
A wide variety of texture feature extraction methods have been proposed for texture based image classification and segmentation. These methods are typically evaluated over windows of the same size, the latter being us...
详细信息
This paper describes the improvements achieved in our mosaicking system to assist unmanned underwater vehicle navigation. A major advance has been attained in the processing of images of the ocean floor when light abs...
详细信息
This paper describes the improvements achieved in our mosaicking system to assist unmanned underwater vehicle navigation. A major advance has been attained in the processing of images of the ocean floor when light absorption effects are evident. Due to the absorption of natural light, underwater vehicles often require artificial light sources attached to them to provide the adequate illumination for processing underwater images. Unfortunately, these flashlights tend to illuminate the scene in a nonuniform fashion. In this paper a technique to correct non-uniform lighting is proposed. The acquired frames are compensated through a point-by-point division of the image by an estimation of the illumination field. Then, the gray-levels of the obtained image remapped to enhance image contrast. Experiments with real images are presented.
Catadioptric sensors are combinations of mirrors and lenses made in order to obtain a wide field of view. In this paper we propose a new sensor that has omnidirectional viewing ability and it also provides depth infor...
详细信息
Catadioptric sensors are combinations of mirrors and lenses made in order to obtain a wide field of view. In this paper we propose a new sensor that has omnidirectional viewing ability and it also provides depth information about the nearby surrounding. The sensor is based on a conventional camera coupled with a laser emitter and two hyperbolic mirrors. Mathematical formulation and precise specifications of the intrinsic and extrinsic parameters of the sensor are discussed. Our approach overcomes limitations of the existing omni-directional sensors and eventually leads to reduced costs of production.
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 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 idea is to generate a 3D model of a person's face and animate different emotions on the face at a remote observer's end, thus eliminating the need to send raw video. This research is part of a larger project, which deals with development of novel sensory systems and interfaces to enhance safety of a driver. The proposed algorithm uses a stereo pair of images of a driver's face and creates a 3D mesh model by deforming and texture mapping a predefined 3D mesh.
暂无评论