Superresolution for ultrasonic imaging in air using neural networks
Superresolution for ultrasonic imaging in air using neural networks
复制标题
使用神经网络进行空气中超声成像的超分辨率
DOI：
--
复制
发表时间：
1988
期刊：
影响因子：
--
通讯作者：
J. Winters
中科院分区：
文献类型：
--
作者：
J. Winters
研究了一组换能器在空气中的超声成像。作者描述了一种超分辨率技术，该技术利用大多数表面作为空气中超声波脉冲的完美反射器来生成精确的物体识别地图。该技术涉及在非线性等式约束下的二次目标函数的最小化。作者表明，这种最小化可以通过两步惩罚函数方法来实现，尽管在通用计算机上不实用，但可以在一对神经网络上实时运行。结果表明，即使在低接收信噪比的情况下，该技术也能生成精确的地表图
Ultrasonic imaging in air using an array of transducers is studied. The authors describe a superresolution technique that uses the fact that most surfaces act as perfect reflectors to ultrasonic pulses in air to generate accurate maps for object identification. The technique involves the minimization of a quadratic objective function subject to a nonlinear equality constraint. The authors show that this minimization can be accomplished by a two-step penalty function method, which, although not practical on a general-purpose computer, can operate in real time on a pair of neural networks. Results demonstrate that the technique generates accurate surface maps even with low receive signal-to-noise ratios.<<ETX>>