ID 原文 译文
14205 通过SPOT算法对多目标进行跟踪,以确定新一帧中各目标最优位置; Multi-scale Retinex algorithm is used to preprocess the image sequence.Structure Preserving Object Tracking(SPOT) algorithm is used to track multiple targets, so as to determine the optimal position of each target in the new frame.
14206 采用判别型尺度空间跟踪算法训练尺度滤波器,以新一帧中各目标最优位置为中心,利用尺度滤波器的最大值确定新一帧中各目标的最优尺度; Discriminant Scale Space Tracking(DSST) algorithm is used to train the scale filter, whose maximum value is used to determine the optimal scale of each target in the new frame by taking the optimal position of each target in the new frame as the center.
14207 采用随机梯度下降法并结合双线性插值更新特征分类器的权重。 Stochastic Gradient Descent(SGD)and bilinear interpolation are used to update the weight of the feature classifier.
14208 实验结果表明,提出的多目标跟踪算法在应对场景光照和目标尺度变化等方面,具有良好的鲁棒性和准确性。 The experimental results show that the proposed multi-target tracking algorithm has good robustness and accuracy in dealing with illumination variation and changes in the target's scale.
14209 目前人们针对不同场景设计和研究出各种基于混沌的图像加密算法并取得不俗的研究成果,但仍有一些图像加密算法存在不足之处,因而相关专家学者们不断研究新的图像加密方法并对传统的各种加密算法进行改进。 At present, various chaos-based image encryption algorithms have been designed and developed for different scenarios, but there are still shortcomings of some of the image encryption algorithms. Therefore, relevant experts and scholars continue to study new image encryption methods and improve traditional encryption algorithms.
14210 针对目前低维混沌算法存在的明显缺点,提出一种基于CNN超混沌与S盒结合的图像加密算法,仿真实验表明,该算法能够有效地抵挡明文(密文)攻击,实现了一次一密,而且拥有更大的密钥空间,具有优良的加密效果及速度快、复杂度低的优点。 In order to overcome the obvious shortcomings of the current low-dimensional chaotic algorithm, this paper presents an image encryption algorithm based on the combination of CNN hyperchaotid sequence and S-box.Simulation experiments show that :1) The proposed algorithm can effectively resist the attack on the image in the form of plain text or cipher text, realize one-time one-encryption, and have a larger key space ;and 2) This algorithm has excellent encryption effects with high speed and low complexity.
14211 针对组网雷达系统对探测目标进行参数联合估计,提出了一种针对该参数估计的组网雷达欺骗干扰策略。 The enemy's netted radar system often jointly estimates the parameters of the detected targets. In order to supress its parameter estimation performance, a deception jamming strategy against the enemys netted radar is proposed.
14212 首先,分析了电子干扰机编队对组网雷达实施欺骗干扰的原理,并建立了欺骗干扰下的目标回波信号模型。 Firstly, analysis is made to the principle of deception jamming against the enemy's netted radar, which is conducted by an electronic jammer formation, and then the target's echo signal model under the deception jamming is established.
14213 然后,在此基础上给出了欺骗干扰特征矢量参数的费希尔信息矩阵(FIM),并分析了其估计性能。 Based on this, the Fisher Information Matrix( FIM) of feature vector parameters of deception jamming is presented and then the estimation performance is analyzed.
14214 最后,推导了达到待估计参数克拉美罗下界(CRLB)的充分条件,提出了使得组网雷达参数估计性能最差化的欺骗干扰策略。 Finally, the sufficient condition of reaching the Cramer-Rao Lower Bound (CRLB) of the parameter to be estimated is derived, and a deception jamming strategy for supressing the parameter estimation performance of the enemy's netted radar is given.