ID	原文	译文
1493	文章首先根据远距离磁偶极子的磁场等效性，建立了多初值滤波跟踪模型，	Firstly, based on the magnetic field equivalence of long-distance magnetic dipoles, amulti-initial filter tracking model is established.
1494	然后基于最大似然选择理论推导了如何从多模型中选择最佳结果，即多初值模型的选择方法，	Then based on the maximum likelihood selection theory, the method of howto choose the best result from multiple models is derived.
1495	最后以SRCDKF 滤波器为滤波单元，得到了基于 SRCDKF 的自适应磁性目标跟踪算法。	Finally, using SRCDKF filter as the filtering unit, an adaptive mag-netic target tracking algorithm based on SRCDKF is obtained.
1496	经过仿真试验表明:(1)多初值模型建立和选择方法的有效性;	The simulation experiments show that:(1)the validity of themulti-initial model establishment and selection method;
1497	(2)基于 SRCDKF 的自适应磁性目标跟踪算法，在初始位置信息缺失的情况下，能够有效完成对磁性目标的跟踪;	(2)the adaptive magnetic target tracking algorithm based on SRCD-KF can effectively complete the tracking of magnetic targets in the absence of initial position information;
1498	(3)以不同滤波器为滤波单元的自适应跟踪算法跟踪试验结果表明，多初值模型的解决框架可解决初值先验未知下的跟踪问题。	(3)the trackingresults of the adaptive tracking algorithm with different filters as the filtering unit show that the solution framework of themulti-initial value model can provide a method to solve the tracking problem under the initial value unknown.
1499	为了处理诸如高斯、伽马、极值、瑞利、均匀或贝塔等基本灰度分布情形下的阈值选取难题，本文提出了一种跨域香农熵最大化导向的自动阈值选取方法。	When the basic distribution constituting one gray level histogram is presented as a non-Gaussian distribu-tion, such as gamma, extreme value, Rayleigh, uniform or beta distribution, how to automatically select the best possible seg-mentation threshold is still quite challenging. To deal with the issue of threshold selection in the above-mentioned differentgray level distributions, we propose an automatic method of threshold selection that is guided by maximizing cross-regionShannon entropy under edge guidance and contour constraints.
1500	该方法利用不变的引导边缘图像和变化的约束轮廓图像共同构造出一系列持续变化的一维灰度直方图，并采用香农熵作为熵计算模型，	This method utilizes constant guiding edges and dynamically changing contours to construct a series of continuously changing one-dimensional gray level histograms, and adopts Shannonentropy as the entropy calculation model.
1501	从而得以跨越图像中若干局部区域去计算跨域香农熵，并以最大跨域香农熵对应的阈值作为最终阈值。	Therefore, it can calculate the cross-region Shannon entropy across several local re-gions in the image, and it takes the threshold corresponding to the maximum cross-region Shannon entropy as the final seg-mentation threshold.
1502	在 40 幅合成图像和 50 幅真实世界图像上的实验结果表明，该方法虽然在计算效率方面不优于 Masi 熵阈值方法、Tsallis 熵阈值方法、局部香农熵阈值方法和迭代三类阈值方法，但在分割适应性方面有显著增强，且在误分割率方面有显著下降。	The proposed method is compared with Masi entropy thresholding, Tsallis entropy thresholding, Shan-non entropy thresholding, and iterative triclass thresholding on 40 synthetic images and 50 real-world images. The results show that the proposed method is not superior to the 4 compared methods in computational efficiency, but it has significantenhancement in segmentation adaptability and a significant decrease in the mis-segmentation rate.