ID	原文	译文
2243	与基于时间指针算法的调度结果相比，本身算法时间偏移率降低了 61% ;与基于遗传算法的调度结果相比，本文算法调度耗时仅为前者 1 ～ 2% 。	experienced a 61% reduction in the timeshifting rate(TSR)compared with the time pointer algorithm, and took only 1 ～ 2% of the time consumed by the genetic al-gorithm.
2244	为增强工业级机器视觉系统的实时性和稳定性，本文提出一种基于等积环投影与 Zernike 矩的具有旋转不变性的快速模板匹配方法，	In order to enhance the real-time performance and stability of industrial-level machine vision systems, This paper proposes a fast template matching method with rotation invariance based on equal-area ring projection and Zernike mo-ments.
2245	该方法采用由粗到精匹配策略，在粗匹配阶段以等积环投影向量作为特征进行匹配得到候选点集，再基于 Zenrike 矩进行精确匹配。	The method uses a coarse-to-fine matching strategy. The coarse matching stage uses the equal-area ring projection vector as the feature to obtain the candidates, and then use Zenrike moments to accurately match in candidates.
2246	主要创新点为提出复杂度低、抗噪性强和具有旋转不变性的等积环投影向量特征，并利用圆对称性在八分圆法基础上进一步降低 Zernike 矩计算量。	The main contributions of this paper are proposing the equal-are ring projection vector feature with low complexity, noise insensitive and rotation invariance, and further reducing the computational cost of Zernike moments based on the octant circle method u-sing circular symmetry.
2247	经理论分析和实验对比验证，此法在保障匹配精度前提下，其匹配速度胜于当前同类最优算法，且对高斯噪声及线性亮度变化有强鲁棒性。	Theoretical analysis and experimental results show that the proposed method is faster than the state-of-the-art algorithm under high matching accuracy, and it is robust to Gaussian noise and linear brightness variations.
2248	光流场是目标检测，无人机定位等众多计算机视觉任务的重要基础。	Optical flow field is an important basis for many computer vision tasks such as target detection and un-manned aerial vehicle positioning.
2249	本文针对非刚性大位移运动等困难运动类型图像序列光流计算的准确性与鲁棒性问题，提出一种基于非刚性稠密匹配的 TV-L1(Total Variational withL1 norm，TV-L1)大位移光流计算方法。	In order to develop the accuracy and robustness of optical flow estimation suffered from the difficult motion such as non-rigid movement and large displacement motion, this paper proposes a large displacement op-tical flow estimation approach based on non-rigid dense patch matching.
2250	首先，使用非刚性稠密块匹配计算图像序列初始最近邻域场，其次根据图像相邻块区域的相似性消除初始最近邻域场中的非一致性区域以得到准确的图像最近邻域场。	Firstly, we utilize the non-rigid dense patch matc-hing to compute the initial nearest neighbor field between the consecutive frames, and eliminate the inconsistent regions of the computed nearest neighbor field according to the consistency of the neighboring patches in the image to obtain an accu-rate image nearest neighbor field.
2251	然后，在图像金字塔分层计算框架下，将图像最近邻域场引入基于非局部约束的 TV-L1 光流估计模型，通过 Quadratic Pseudo-Boolean Optimization(QPBO)融合算法在金字塔分层图像光流计算时对 TV-L1 模型光流估计进行大位移运动补偿。	Secondly, we merge the nearest neighbor field into the TV-L1(Total Variational with L1norm, TV-L1)optical flow model, and employ the nearest neighbor field to compensate the large displacement optical flowof TV-L1 model by using the quadratic pseudo-Boolean optimization (QPBO)fusion algorithm during the coarse-to-fine computation scheme.
2252	最后，采用标准测试图像序列对本文方法和当前代表性的变分方法 LDOF(Large Displacement Optical Flow，LDOF)、Classic + NL、NNF(NearestNeighbor Fields，NNF)以及深度学习方法 FlowNet2.0 进行对比分析。	Finally, we employ the standard test image sequences to evaluate the performance of our approach and some state-of-the-art methods including LDOF(Large Displacement Optical Flow, LDOF), Classic + NL, NNF(NearestNeighbor Fields, NNF)and FlowNet2. 0.