It is well known that the robustness of many computer vision algorithms can be improved by employing large field of view cameras, such as omnidirectional cameras. To avoid obstructions in the field of view, such camer...
详细信息
ISBN:
(纸本)9781479936397
It is well known that the robustness of many computer vision algorithms can be improved by employing large field of view cameras, such as omnidirectional cameras. To avoid obstructions in the field of view, such cameras need to be mounted in an exposed position. Alternatively, a multi-camera setup can be used. However, this requires the extrinsic calibration to be known. In the present work, we propose a method to calibrate a fisheye multi-camera rig, mounted on a mobile platform. The method only relies on feature correspondences from pairwise overlapping fields of view of adjacent cameras. In contrast to existing approaches, motion estimation or specific motion patterns are not required. To compensate for the large extent of multi-camera setups and corresponding viewpoint variations, as well as geometrical distortions caused by fisheye lenses, captured images are mapped into virtual camera views such that corresponding image regions coincide. To this end, the scene geometry is approximated by the ground plane in close proximity and by infinitely far away objects elsewhere. As a result, low complexity feature detectors and matchers can be employed. The approach is evaluated using a setup of four rigidly coupled and synchronized wide angle fisheye cameras that were attached to four sides of a mobile platform. The cameras have pairwise overlapping fields of view and baselines between 2.25 and 3 meters.
Vehicle occupants that are out-of-position can be deadly injured by the deployment of the air bag in a crash situation. In recent years many different sensors and systems have been proposed to detect the type of occup...
详细信息
Vehicle occupants that are out-of-position can be deadly injured by the deployment of the air bag in a crash situation. In recent years many different sensors and systems have been proposed to detect the type of occupant and the position of the occupant's head. This work presents a method for classification and occupant's head detection based on passive stereo vision. The proposed system uses depth surface analysis and scene statistics together with support vector machines for classification and selection of head candidates. Evaluation of the method shows 99% correct for classification and 98% correct for head detection, using large sets of image data, and image sequences recorded in a driving vehicle.
A new class of quintic minimal surfaces with two shape parameters was proposed. We proved that the minimal surfaces were isothermal parameter surfaces and harmonic surfaces. The symmetry and the self-intersection prop...
详细信息
A new class of quintic minimal surfaces with two shape parameters was proposed. We proved that the minimal surfaces were isothermal parameter surfaces and harmonic surfaces. The symmetry and the self-intersection properties of the minimal surfaces were studied. We investigated the distributions of Gaussian curvature and hyperbolic points of these minimal surfaces, and analysised the effects of the two shape parameters through graphic examples. The control mesh representations of the minimal surfaces are given by tensor product Bézier surface and triangular Bézier surface. Finally, we presented their application in modeling of tensioned membrane structure. The result not only enriched the theory of minimal surface in differential geometry, but also enhanced the application of minimal surfaces in CAD systems.
Automatic image annotation has been an active research topic in the last decade due to its potentially large impact on image retrieval, object recognition and image understanding. Many approaches have been proposed fo...
详细信息
We developed an augmented reality tool for vision-based hand gesture recognition in a camera-projector system. Our recognition method uses modified Fourier descriptors for the classification of static hand gestures. H...
详细信息
We developed an augmented reality tool for vision-based hand gesture recognition in a camera-projector system. Our recognition method uses modified Fourier descriptors for the classification of static hand gestures. Hand segmentation is based on a background subtraction method, which is improved to handle background changes. Most of the recognition methods are trained and tested by the same service-person, and training phase occurs only preceding the interaction. However, there are numerous situations when several untrained users would like to use gestures for the interaction. In our new practical approach the correction of faulty detected gestures is done during the recognition itself. Our main result is the quick on-line adaptation to the gestures of a new user to achieve user-independent gesture recognition.
Various channels of the neuromorphic, multi-layer retina has been successfully modeled by CNN. Our primary aim was to build up a real-time test environment with camera input and display output in order to mimic the be...
详细信息
Various channels of the neuromorphic, multi-layer retina has been successfully modeled by CNN. Our primary aim was to build up a real-time test environment with camera input and display output in order to mimic the behavior of retina model implementation on emulated digital CNN by using a low-cost, moderate sized field-programmable gate array (FPGA) architecture.
Prediction of the amino acids that have a catalytic effect on the enzymes is a major stage in appointing the activity of the enzymes and classification. The biological activity of a protein usually depends on the exis...
详细信息
Prediction of the amino acids that have a catalytic effect on the enzymes is a major stage in appointing the activity of the enzymes and classification. The biological activity of a protein usually depends on the existence of a small number of amino acids. Recently, many algorithms have been proposed in the literature for finding these amino acids which are complex and time consuming. In this paper, we will introduce a new method for predicting the active sites that will use the spatial coordinates and the type of amino acids that contain the active sites. In order to increase the speed we use an approximate graph isomorphism algorithm. Furthermore, this algorithm allows us to find several active sites for a protein and order them according to a RMSD (Root Mean Square Deviation) number which has several applications in biology.
To simulate mobile-to-mobile (M2M) Rayleigh fading channels under more realistic scenario of non-isotropic scattering, we propose one deterministic and one stochastic sumof- sinusoids (SoS) based simulation models. Th...
详细信息
ISBN:
(纸本)9781605585697
To simulate mobile-to-mobile (M2M) Rayleigh fading channels under more realistic scenario of non-isotropic scattering, we propose one deterministic and one stochastic sumof- sinusoids (SoS) based simulation models. The proposed models extensively consider the distributions of the angle of arrival (AoA) and the angle of departure (AoD), and thus show a good approximation to the desired statistical properties of the reference model. Copyright 2009 ACM.
Rock fractures junctions are important objects for detection of rock fracture. Traditionally, junction detectors are devoted to the step-edge corners. Such corners are usually located using a Laplascian operator (zero...
详细信息
Rock fractures junctions are important objects for detection of rock fracture. Traditionally, junction detectors are devoted to the step-edge corners. Such corners are usually located using a Laplascian operator (zero-crossings or extrema) or a curvature measure based on the gradient direction. However, the gradient direction of a line does not exist, and a line junction does not correspond to a zero-crossing of the Laplacian. Consequently, step-edge corner detectors are not suitable for line junctions. Their response to a single line junction is not unique. There are other methods to detect the junction. Most of them find L-shaped corners, but create multiple or no responses for more complex junctions. This paper proposes a robust detection method for gray-level line junction which is called the neighborhood pixel-track algorithm. Examples are provided based on experiments with synthetic and real images. The achieved results demonstrate that such junction detection algorithm can successfully identify T-and Y-junctions, and of degree four X-junctions or more complex intercross of rock fractures.
In this paper we discuss landmark based absolute localization of tiny autonomous mobile robots in a known environment. Landmark features are naturally occurring as it is not allowed to modify the environment with spec...
详细信息
In this paper we discuss landmark based absolute localization of tiny autonomous mobile robots in a known environment. Landmark features are naturally occurring as it is not allowed to modify the environment with special navigational aids. These features are sparse in our application domain and are frequently occluded by other robots. This makes simultaneous acquisition of two or more landmarks difficult. Therefore, we propose a system that requires a single landmark feature. The algorithm is based on range measurement of a single landmark from two arbitrary points whose displacement can be measured using dead-reckoning sensors. Range estimation is done with a stereo vision system. Simulation results show that the robot can localize itself if it can estimates range of the same landmark from two different position and if the displacement between the two position is known.
暂无评论