We propose a new technique, based on self-organization, for localizing salient contours in an image, with applications to, for instance, object and character recognition, stereopsis and motion tracking. A neuronal net...
详细信息
We propose a new technique, based on self-organization, for localizing salient contours in an image, with applications to, for instance, object and character recognition, stereopsis and motion tracking. A neuronal network which is isomorphic to the template/initial contour is created. This network acts as an active contour, which, using self-organization, undergoes deformation in an attempt to cling on to the nearest salient contour in the test image. The application areas of the model proposed are similar to "snake", but distinct from it both in the underlying mathematics and implementation. The new technique is illustrated with some examples.
Probabilistic occupancy grids have proved to be very useful for workspace modeling in 2D environments. Due to the expansion of computational load, this approach was not tractable for mapping a 3D environment in real a...
详细信息
Probabilistic occupancy grids have proved to be very useful for workspace modeling in 2D environments. Due to the expansion of computational load, this approach was not tractable for mapping a 3D environment in real applications. In this paper, the original occupancy grid scheme is revisited and a generic closed-form function is introduced to avoid numerical computation of probabilities for a range sensor with Gaussian error distribution. Occupancy probabilities are computed and stored in a multiresolution octree for improved performance and compactness. Occupancy models are built in local reference frames and linked to a global reference frame through uncertain spatial relationships that can be updated dynamically. This scheme is used for building a 3D map in a telerobotic maintenance application of electric power lines where perturbations may cause motion of object assembly.
In this paper the control problem of telemanipulators is considered under the condition that they are subject to modeling and other uncertainties of considerable levels. The design is based on the S. Lee and H. S. Lee...
详细信息
ISBN:
(纸本)0780341236
In this paper the control problem of telemanipulators is considered under the condition that they are subject to modeling and other uncertainties of considerable levels. The design is based on the S. Lee and H. S. Lee teleoperator control scheme, which is modified so as to be able to compensate the uncertainties, and is implemented using a partitioned multilayer perceptron neural network. Several subnetworks are used each one identifying a term of the manipulator's dynamic model. A new learning algorithm is proposed which distributes the learning error to each subnetwork and enables online training Several simulation results are provided which show the robustness ability by the partitioned neurocontroller, and compare it with the results obtained through sliding mode control.
This paper investigates a novel hybrid fuzzy neural system, fuzzy cognitive map (FCM), and its implementation in distributed systems and control problems. The description and the methodology of this system will be exa...
详细信息
This paper investigates a novel hybrid fuzzy neural system, fuzzy cognitive map (FCM), and its implementation in distributed systems and control problems. The description and the methodology of this system will be examined and then it will be shown the application of FCM in a process control problem, which will reveal the characteristics and qualities of FCM. There is an oncoming need for more autonomous and intelligent systems, which could be satisfied with the application of FCM in the field of systems and control.
In this paper we focus on using local 3D structure for segmentation. A tensor descriptor is estimated for each neighbourhood, i.e. for each voxel in the data set. The tensors are created from a combination of the outp...
详细信息
In this paper we focus on using local 3D structure for segmentation. A tensor descriptor is estimated for each neighbourhood, i.e. for each voxel in the data set. The tensors are created from a combination of the outputs form a set of 3D quadrature filters. The shape of the tensors describe locally the structure of the neighbourhood in terms of how much it is like a plane, a line, and a sphere. We apply this to segmentation of bone from computer Tomography data (CT). Traditional methods are based purely on gray-level value discrimination and have difficulties in recovering thin bone structures due to so called partial voluming, a problem which is present in all such sampled data. We illuminate the partial voluming problem by showing that thresholding creates complicated artifacts even if the signal is densely enough sampled and can be perfectly reconstructed. The unwanted effects of thresholding can be reduced by a change of the signal basis. We show that by using additional local structure information can significantly reduce the degree of sampling artifacts. Evaluation of the method on a clinical case is presented, the segmentation of a human skull from a CT volume. The method shows that many of the thin bone structures which disappear in a pure thresholding can be recovered.
Distributed manipulation experiments were performed using a massively-parallel, microfabricated actuator array. An organic ciliary array of thin-film polyimide bimorph microactuators exploiting combined thermal and el...
详细信息
Distributed manipulation experiments were performed using a massively-parallel, microfabricated actuator array. An organic ciliary array of thin-film polyimide bimorph microactuators exploiting combined thermal and electrostatic control was employed to implement task-level, sensorless manipulation strategies for macroscopic objects. The tasks of parts-translation, -rotation, -orientation, and -centering were demonstrated using small integrated circuit (IC) dice. Strategies were programmed in a fine-grained SIMD (single instruction, multiple data) fashion by specifying planar force vector fields. When a part is placed on the array, the programmed vector field induces a force and moment upon it. The part's equilibrium states may be predicted and cascaded (using a sequence of fields) to bring the part to a desired final state. Vector fields with and without potential were tested in experiments, and the behavior of parts in the fields was compared with the theory of programmable vector fields. These fields were implemented by actuating the organic cilia in a cyclic, gait-like fashion. Motion in non-principal (e.g. diagonal) directions was effected by a pairwise coupling of the cilia to implement virtual cilia. These experiments suggest that MEMS actuator arrays are useful for parts-orientation, -posing, -transfer, -singulation, and -sorting.
A rigorous framework is presented for the design of nonlinear digital and analog filters. The approach followed is based on a Generalized Fock (GF) space framework developed by the Principal Investigator and T.A.W. Dw...
详细信息
A rigorous framework is presented for the design of nonlinear digital and analog filters. The approach followed is based on a Generalized Fock (GF) space framework developed by the Principal Investigator and T.A.W. Dwyer, III. A GF space is a reproducing kernel Hilbert space of discrete or continuous Volterra series with a problem-dependent weighted inner product. The optimal nonlinear filter structure is obtained by an orthogonal projection of the desired filter into the subspace spanned by the representers of interpolating, smoothing, and other design constraint functionals in the appropriate GF space. One of the attractive features of this approach is that the solutions to the filter design problem appear naturally as feedforward (FIR) or recurrent (IIR) artificial neural networks. These results are derived for a GF space F(E/sup N/) on a finite-dimensional Euclidian space E/sup N/. Generalization to functional FIR and IIR nonlinear filters follows immediately from replacing F(E/sup N/) by F(L/sub 2/(I)), where L/sub 2/(I) is the space of square integrable functions on an interval I of the real line.
This paper presents a function discovery system FFS that has two core parts: FFS-0-CORE and FFS-1-CORE. Both cores are with polynomial time complexity in discovering functions of either a•f(x)+b form or a 1 f 1 (x)+…...
详细信息
This paper presents a function discovery system FFS that has two core parts: FFS-0-CORE and FFS-1-CORE. Both cores are with polynomial time complexity in discovering functions of either a•f(x)+b form or a 1 f 1 (x)+…+a n f n (x)+b form. FFS-0-CORE allows users to define their own models. FFS-1-CORE uses novel principles to increase information which helps the function discovery procedures. Three computational examples are included.
A custom CMOS imager with integrated motion computation is described. The architecture is based on correlating in time moving edges. Edges are located in time by a custom sensor; and correlated in a coprocessing modul...
详细信息
A custom CMOS imager with integrated motion computation is described. The architecture is based on correlating in time moving edges. Edges are located in time by a custom sensor; and correlated in a coprocessing module. The sensor architecture is centered around a compact pixel with analog signal processing and digital self-signaling capabilities. The sensor pixels detect moving edges in the image and communicate their position using an address-event protocol associated to temporal stamps. The coprocessing module correlates the edges and computes the velocity vector map. The motion sensor could be used in applications such as self-guided vehicles, mobile robotics and smart surveillance systems. The article details the motion sensor architecture, the simulated performance, the VLSI implementation and some preliminary results on fabricated prototypes.
暂无评论