ID	原文	译文
22105	数值仿真表明，与传统 MUSIC, IL1-SRACV, L1-SVD 子空间算法及稀疏重构加权 L1 算法相比，所提算法能显著抑制非均匀噪声影响，具有较好 DOA 估计性能，且在低信噪比条件下，亦具有较高估计精度和分辨力。	Numerical simulations show that the proposed algorithm outperforms the traditional DOA algorithms such as MUltiple SIgnal Classification (MUSIC), Improved L1-SRACV (IL1-SRACV), L1-norm-Singular Value Decomposition (L1-SVD) subspace and sparse reconstruction weighted L1 methods in the following respects: suppressing the influence of the non-uniform noise significantly, bettering DOA estimation performance, as well as improving estimation accuracy and resolution with low Signal-Noise Ratio (SNR).
22106	该文针对压缩跟踪算法无法适应目标尺度的变化以及没有考虑样本权重的问题，提出一种基于粒子滤波与样本加权的压缩跟踪算法。	To solve the problem that Compressive Tracking (CT) algorithm is unable to adapt to the scale change of the object and ignores the sample weight, an optimized compressive tracking algorithm based on particle filter and sample weighting is presented.
22107	首先，对压缩特征进行改进，提取归一化矩形特征用于构建目标表观模型。	Firstly, the compressive feature is improved for building a target apparent model with normalized rectangle features.
22108	然后，引入样本加权的思想，根据正样本与目标之间距离的不同赋予正样本不同的权重，提高分类器的分类精度。	Then, the thought of sample weighting is utilized. In order to increase the precision of the classifier, different weights are given to the positive samples in accordance with the different distances between the positive samples and the object.
22109	最后，在粒子滤波的框架下融合尺度不变压缩特征进行动态状态估计，在粒子预测阶段利用 2 阶自回归模型对粒子状态进行估计与预测，借助观测模型对粒子状态进行更新，并且对粒子进行重采样以防止粒子退化。	Finally, the dynamic state estimation is made under the particle filter frame with integrating the scale invariant feature. At the phase of particle prediction, a second-order autoregressive model is utilized to obtain the estimation and prediction of the particle state. The particle state is updated with the observation model. The particles resampling is used to prevent the degradation of particles.
22110	实验结果表明，相比于原始压缩跟踪算法，改进算法能够更好地跟踪目标尺度的变化，提高跟踪的稳定性和准确性。	Experimental results demonstrate that the improved algorithm can adapt to the scale change of object, and the accuracy and stability of the compressive tracking algorithm is improved.
22111	针对鲁棒主成分分析(Robust Principal Component Analysis, RPCA)算法中将动态背景误检为运动目标的问题，该文提出一种运动目标检测优化算法。	Since dynamic background may be erroneously detected as a moving object in the Robust Principal Component Analysis (RPCA) algorithm, a RPCA-based moving object detection optimization algorithm is proposed to improve it.
22112	在 RPCA 算法初步检测出运动目标后，利用动态背景在时间域上满足高斯分布的特性，以及动态背景和运动目标在整个视频流上检出点均值和方差的差异特性，进一步将动态背景和运动目标分离开来。	After detected by the RPCA algorithm, the moving object will be separated from dynamic background according to the Gaussian distribution of dynamic background in the time domain and the difference of mean value and variance between dynamic background and moving object in the whole video stream.
22113	实验结果表明，所提算法能够有效地处理动态背景的问题，并在一定程度上完整检测出运动目标。	The results show that the algorithm can deal with dynamic background effectively and detect the moving objects well.
22114	为了降低低剂量 CT 肺部噪声对肺癌筛查后期诊断的影响，该文提出一种基于深度卷积神经网络的低剂量CT 肺部去噪算法。	In order to reduce the effect of low dose CT lung noise on the late diagnosis of lung cancer screening, a denoising model of low-dose CT lung based on deep convolution neural network is proposed.