ID 原文 译文
18705 该方法利用机器学习中的无监督聚类算法在线估计强散射点数量以及首次检测门限，然后再结合虚警率，确定2次检测门限，最后通过两次门限检测完成目标有无的判决。 Firstly, the unsupervised clustering algorithm in machine learning is used to estimate the number of strong scattering points and the first detection threshold adaptively. Then, the second detection threshold is determined according to false alarm rate. Finally, the existence of the target is determined through twodetection thresholds.
18706 该文分别利用仿真数据和实测数据进行了试验验证，并和其他算法进行了试验对比，通过虚警概率一定时的信噪比(SNR)-检测概率曲线验证了该文所提方法相对于传统算法有更高的稳健性，且该方法不需要目标散射点的任何先验信息。 The simulation data and the measured data are used to verify and compare with otheralgorithms. By comparing the Signal-to-Noise Ratio (SNR) -detection probability curves of various methodswith a given false alarm probability, it is verified that the proposed method has higher robustness than thetraditional algorithm, and the method does not need any priori information of target scattering points.
18707 为了解决绝缘子目标检测中无法精确定位的问题，该文基于深度学习提出一种绝缘子定向识别算法，通过在轴对齐检测框中加入角度信息，可有效解决常规深度学习算法无法精确定位目标的问题。 In order to solve the problem of inaccurate location in insulator target detection, this paper proposesan insulator orientation recognition algorithm based on deep learning. By adding angle information to the axisalignment detection frame, it can effectively solve the problem that conventional deep learning algorithm cannot accurately locate the target.
18708 该算法首先将角度旋转参数引入轴对齐矩形检测框中构成定向检测框，然后将该参数偏移量作为第5参数加入到损失函数中进行迭代回归，同时为提高检测精度在训练过程中使用Adam算法替代随机梯度下降(SGD)算法进行损失函数优化，最终可获得绝缘子定向检测模型。 First, the angular rotation parameters are introduced into the axially alignedrectangular detection frame to form a directional detection frame. Then the parameter offset is added as thefifth parameter to the loss function for iterative regression. At the same time, in order to improve the detectionaccuracy, Adam algorithm is used to replace Stochastic Gradient Descent (SGD) to optimize the loss function.Finally, the insulator directional detection model can be obtained.
18709 实验分析表明，加入旋转角度的定向检测框可有效对绝缘子目标进行精确定位。 The experimental results show that theorientation detection frame with rotation angle can effectively locate the insulator target accurately.
18710 手语识别涉及计算机视觉、模式识别、人机交互等领域，具有重要的研究意义与应用价值。 Sign language recognition involves computer vision, pattern recognition, human-computer interaction,etc. It has important research significance and application value.
18711 深度学习技术的蓬勃发展为更加精准、实时的手语识别带来了新的机遇。 The flourishing of deep learning technology brings new opportunities for more accurate and real-time sign language recognition.
18712 该文综述了近年来基于深度学习的手语识别技术，从孤立词与连续语句两个分支展开详细的算法阐述与分析。 This paper reviews the signlanguage recognition technology based on deep learning in recent years, formulates and analyzes the algorithmsfrom two branches - isolated words and continuous sentences.
18713 孤立词识别技术划分为基于卷积神经网络(CNN)、3维卷积神经网络(3D-CNN)和循环神经网络(RNN) 3种架构的方法； The isolated-word recognition technology isdivided into three structures: Convolutional Neural Network (CNN), Three-Dimensional Convolutional NeuralNetwork (3D-CNN) and Recurrent Neural Network (RNN) based method.
18714 连续语句识别所用模型复杂度更高，通常需要辅助某种长时时序建模算法，按其主体结构分为双向长短时记忆网络模型、3维卷积网络模型和混合模型。 The model used for continuous sentence recognition has higher complexity and is usually assisted with certain kind of long-term temporal sequence modeling algorithm. According to the major structure, there are three categories: the bidirectionalLSTM, the 3D convolutional network model and the hybrid model.