A hierarchical stereo system is described that uses structural descriptions up to the surface level. Surface descriptions are computed from monocular images, by using a perceptual grouping technique. Occlusion can be ...
详细信息
A hierarchical stereo system is described that uses structural descriptions up to the surface level. Surface descriptions are computed from monocular images, by using a perceptual grouping technique. Occlusion can be a major problem in stereo analysis and is often not treated explicitly. An analysis is presented of occlusion effects in stereo, and it is shown how structural descriptions can be used to deal with them. Experimental results are given for scenes with curved objects and significant occlusions.< >
Dynamic segmentation is a method for improving the performance of cooperating tasks executed on loosely coupled multiprocessors. Four different data transfer techniques that can be used for intersegment data transfers...
详细信息
Dynamic segmentation is a method for improving the performance of cooperating tasks executed on loosely coupled multiprocessors. Four different data transfer techniques that can be used for intersegment data transfers in dynamically segmented buses are analyzed. Preemptive data transfers are considered for uniform message latencies and results are provided for message latency comparisons using various locality factors. These results indicate dynamic segmentation improves performance considerably, at a fraction of the cost of more complex interconnection networks such as multiple buses.< >
An early-processing algorithm to extract motion information from closely sampled image sequences is presented. This method outputs dense displacement field, based on the extraction of strips in slices taken from the i...
详细信息
An early-processing algorithm to extract motion information from closely sampled image sequences is presented. This method outputs dense displacement field, based on the extraction of strips in slices taken from the image volume along the temporal dimension. The extracted strips provide estimates of the velocity component along the slice orientation. Because of the high sampling rate, the motion is assumed to be piecewisely translational. A voting scheme to estimate the position of FOE while extracting strips is proposed. The true velocity can then be calculated. Results on several real image sequences and a promising speedup from the parallel implementation on the Connection Machine are presented.< >
The reduction of the state space of generalized stochastic Petri net (GSPN) models is discussed. For a certain class of GSPNs it is possible to analyze subnets in isolation by keeping the number of tokens in the net c...
详细信息
The reduction of the state space of generalized stochastic Petri net (GSPN) models is discussed. For a certain class of GSPNs it is possible to analyze subnets in isolation by keeping the number of tokens in the net constant. The authors construct a flow equivalent net (FEN), which has the same temporal and input/output properties of the original net, but with a strongly reduced state space. The FEN is substituted back into the complement of the original net.< >
A new approach to solving the collision detection problem for mobile robots in the presence of moving obstacles is proposed. Both the robot and obstacles in the two-dimensional space are assumed to be polygonal and ar...
详细信息
A new approach to solving the collision detection problem for mobile robots in the presence of moving obstacles is proposed. Both the robot and obstacles in the two-dimensional space are assumed to be polygonal and are composed of a set of convex polygons. The half-plane representation uses an algebraic method to describe the object motion including translation and rotation through time. Compared with previous methods, the proposed representation is more general in that obstacles are now allowed to move at nonconstant velocities. To detect collision between polygonal objects, a traversability vector method was developed. Traversability vectors are a simple mechanism used to analyze geometric constraints imposed by polygons. Using these vectors, a simple algorithm for predicting collision is derived. computer simulations were conducted to show the feasibility of the proposed method.< >
An Extended Object Model (XOM) is p resented for the design and development of knowledge based systems. A set of operations is defined on the object model. The model is used in designing the conceptual schema of an ex...
详细信息
We present a multiscale stereo algorithm whose design makes it easily implemented on a fine grain parallel architecture. The matching at a given scale is performed in accordance with the algorithm proposed by Drumhell...
详细信息
An intelligent externally powered orthotic system (exoskeleton) for the treatment of motor dysfunctions of the upper extremities of stroke patients is described. IROS is an interactive and cooperative human-machine sy...
详细信息
An intelligent externally powered orthotic system (exoskeleton) for the treatment of motor dysfunctions of the upper extremities of stroke patients is described. IROS is an interactive and cooperative human-machine system, with both controlling the human arm. Initially, the machine is the main controller of the arm. As the patient improves, the human control of the arm increases, and the machine control of the arm decreases. The system combines the skills of professional therapists with a sensor-integrated orthosis and a real-time graphics system to ensure proper interaction and cooperation with the patient in order to achieve the goals of therapy. It uses the expertise of the therapists, which is incorporated into its knowledge system, while monitoring the sensory information from the patient, including the force, motion, and electromyogram (EMG) signals. The treatment-related tasks are displayed on the real-time graphic system to increase the interest and enhance the motivation of the patient. Such a system can be used to improve the rehabilitation process for stroke patients.< >
A three fingered, multijointed robot gripper for experimental use is presented. The mechanics as well as the control architecture are designed for this special purpose. The gripper system provides the basic means in t...
详细信息
Usually, shape description systems assume that a scene has been segmented into objects and that object boundaries are given. This, however, is not realistic when working with intensity images; the resulting boundaries...
详细信息
Usually, shape description systems assume that a scene has been segmented into objects and that object boundaries are given. This, however, is not realistic when working with intensity images; the resulting boundaries are fragmented and contain surface markings, and shadow and noise boundaries. A system is described which works with such input and computes shape descriptions of complex objects. Scene segmentation takes place through shape description. Generalized cones or, more precisely, their 2D analogs of ribbons are used as the basic shape representation scheme. Results for synthetic and real examples are shown. The output of the system is useful for object recognition, learning, further inference of 3D shape, grasping, and navigation.< >
暂无评论