In the design and construction of mobile robotsvision has always been one of the most potentially useful sensory systems. In practice however, it has also become the most difficult to successfully implement. At the M...
详细信息
ISBN:
(纸本)0819413208
In the design and construction of mobile robotsvision has always been one of the most potentially useful sensory systems. In practice however, it has also become the most difficult to successfully implement. At the MIT Mobile Robotics (Mobot) Lab we have designed a small, light, cheap, and low power Mobot vision System that can be used to guide a mobile robot in a constrained environment. The target environment is the surface of Mars, although we believe the system should be applicable to other conditions as well. It is our belief that the constraints of the Maitian environment will allow the implementation of a system that provides vision based guidance to a small mobile rover. The purpose of this vision system is to process realtime visual input and provide as output information about the relative location of safe and unsafe areas for the robot to go. It might additionally provide some tracking of a small number of interesting feature, for example the lander. The system is designed t.o be self contained. It has its own camera and on board processing unit. It draws a small amount of power and exchanges a very small amount of information with the host robot. The project has two parts, first the construction of a hardware platform, and second the implementation of a successful vision algorithm. For the first part of the project, which is nearly complete, we have built a small self contained vision system. It employs a cheap but fast general purpose microcontroller (a 68332) connected to a Charge Coupled Device (CCD). The CCD provides the CPU with a continuous series of medium resolution gray-scale images (64 by 48 pixels with 256 gray levels at 10-15 frames a second). In order to accommodate our goals of low power, light weight, and small size we are bypassing the traditional NTSC video and using a purely digital solution. As the frames are captured any desired algorithm can then be implemented on the microcontroller to extract the desired information from the image
Low level edge detection operators usually do not generate contiguous edges, leaving objects in images with discontinuous borders. This, coupled with inherent signal noises, makes it difficult to identify objects in i...
详细信息
ISBN:
(纸本)0819413208
Low level edge detection operators usually do not generate contiguous edges, leaving objects in images with discontinuous borders. This, coupled with inherent signal noises, makes it difficult to identify objects in images. Here we describe a new algorithm that connects disjoint edge pixels to form continual object boundaries. We model the edge images as potential fields deployed with energies at the edge pixel positions all over the images. Pixels at the edge disjoint positions are charged by the combining forces of these edge pixels in proportion to the relative distances and directions of these pixels. An intrinsic part of the process is the identification of terminal edge pixels (TEP), accompanying with a classification of edge pixels in terms of the pixel connection patterns, to provide critical information for possible connectivity of edge segments. The algorithm applies a potential evaluation function to measure the likelihood of edge linking in certain directions for given TEPs. To reduce the computational overhead and improve the efficiency of the algorithm, an informed search method is used to locate significant edge pixels that present the most strong linking forces to a given TEP. The potential value for the TEP is calculated with respect to the edge directions dominated by the linking forces. When the potential value exceeds a given threshold in a direction, an extension is made at the TEP position in that direction. The process iterates until desired results are attained, using a global edge pattern evaluation scheme.
The conference materials contain 69 papers grouped into twelve sessions dealing with different topics in computervision. Pattern recognition;human face recognition algorithms and systems;image processing including fe...
详细信息
ISBN:
(纸本)0819407445
The conference materials contain 69 papers grouped into twelve sessions dealing with different topics in computervision. Pattern recognition;human face recognition algorithms and systems;image processing including feature spaces, edge and contour methods, optical character recognition and morphology;Packaging, materials handling, software and manipulation;fuzzy image processing and image understanding are the main topics covered.
This conference Proceedings contains 58 papers presented in 8 sessions dealing with: vision and robotics problems needing solutions;pattern recognition for computervision;image processing;intelligent materials handli...
详细信息
This conference Proceedings contains 58 papers presented in 8 sessions dealing with: vision and robotics problems needing solutions;pattern recognition for computervision;image processing;intelligent materials handling and vision;novel preprocessing algorithms and hardware;technology to support intelligentrobots and automated systems;fuzzy logic in intelligent systems and computervision;image segmentation techniques. The topics considered include the following, among others: learning procedure for the recognition of 3-D objects from 2-D images;flexible gray-level vision system based on multiple cell feature description and Hough transform;extraction of the foveal center and lesion boundary from fundus images;design and characterization of a space-variant CCD sensor;toward a general formula for analogical learning leading to more autonomous systems;image analysis using attributed fuzzy tournament matching algorithm;fuzzy logic for fault diagnosis;color segmentation using minimum description length (MDL) clustering;segmentation using range data and structured light;finding distinctive colored regions in images;multiresolution segmentation of forward-looking IP and SAR imagery using neural networks.
The authors ask what is the complexity of computing equilibria for physically realizable analog networks like those of J.J. Hopfield (1984) and T.J. Sejnowski (1981) with arbitrary connectivity. It is shown that, if t...
详细信息
The authors ask what is the complexity of computing equilibria for physically realizable analog networks like those of J.J. Hopfield (1984) and T.J. Sejnowski (1981) with arbitrary connectivity. It is shown that, if the amplifiers are piecewise-linear, then such networks are instances of a game-theoretic model known as polymatrix games. Equilibria for the latter may be computed by vertex pivoting algorithms similar to the simplex method for linear programming, which are in practice of low order polynomial complexity. These algorithms appear to be the only ones both guaranteed to work and which are polynomial in practice. These results suggest that networks with few nonstable equilibria would be computationally attractive.< >
暂无评论