ID 原文 译文
14385 该方法通过融合手持电话行为与讲话行为检测结果,实现对驾驶员打电话行为的检测。 The method combines the results of hand hand holding behavior and speech behavior to detect the driver's calling behavior.
14386 基于构建的浅层卷积神经网络,包含5层特征提取网络以及2层全连接层,可实现对听筒及免提接听两种手持电话行为的检测; The constructed shallow convolutional neural network (S-CNN) consists of five feature extraction layers and two fully-connected layers. It can detect two types of handset behavior;
14387 同时,通过级联形状回归算法得到嘴部18个特征点及其宽高比,并根据连续20帧图像的嘴巴宽高比振荡差值来检测讲话行为。 telephone receiver and hands-free answeAt the same time, the speech behavior is detected by the oscillation difference of the mouth width to height ratio of 20 consecutive images, which is obtained by the 18 feature points of the mouth generated by the cascading shape regression algorithm.
14388 实验结果表明,该方法在实际驾驶场景下的平均检测准确率达到95.6%,平均检测耗时低至230 ms/frame,综合检测性能得到明显改善。 The experimental results show that the average detection accuracy of the proposed method in actual driving scenarios reaches 95.6%,and the average detection time is as low as 230 ms/frame.The comprehensive detection performance of the method is improved obviously.
14389 针对正交频分复用(Orthogonal Frequency Division Multiplexing, OFDM)系统中传统信道估计算法复杂度高或估计精度低的问题,给出一种基于反向传播(Back Propagation, BP)神经网络的信道估计方法。 In order to improve the high complexity or low estimation accuracy of traditional channel estimation algorithms in orthogonal frequency division multiplexing(OFDM) systems, a channel estimation method based on back propagation(BP) neural network is proposed.
14390 采用Simulink仿真工具构建OFDM信号采集平台,建立了基于BP神经网络的OFDM系统信道估计模型,并以均方误差和误码率为主要评价指标,分析了不同网络参数和导频数量对信道估计性能的影响。 The OFDM signal acquisition platform is built by Simulink, and channel estimation model based on BP neural network for the OFDM system is established.Then the influence of different network parameters and pilot number on channel estimation performance is analyzed under the main evaluation indexes of mean square error (MSE) and bit error rate(BER).
14391 仿真结果表明,与传统信道估计算法相比,基于BP神经网络的信道估计算法可以提供更优的系统性能,而且可以减少导频数量,提高频带利用率。 The simulation results show that, compared with the traditional channel estimation algorithm, the channel estimation method based on BP neural network can not only provide better system performance, but also reduce number of pilots and improve spectral utilization.
14392 单传感器、单兵、单系统作战受空间、能量、频率等限制,难以应对日益复杂的战场环境和导弹目标威胁。 Limited by space, energy and frequency, it is difficult to deal with the increasingly complex battle environment and missile threat.
14393 协同是解决上述问题的有效手段。美军在协同系统研究、研制、部署和使用方面,均走在世界前列。 Cooperation is an effective way to solve the above problems.U.S. navy leads the world in the research, development, deployment and application of cooperative engagement systems (CEC).
14394 介绍了美军协同交战系统发展演变历程,通过分析美军典型的协同交战系统总结了其发展特点,并在此基础上给出了发展启示。 This paper introduces the development of U.S. navy's CEC,summarizes its characteristics through analyzing the typical systems.Finally, it gives development inspirations and suggestions for the further researches in this field.