方法是光流计算中的经典方法之一。
HS method is one of the most classical methods for optical flow computation.
本文采用基于梯度的光流场计算方法。
为了获取运动目标的运动参数，采用了光流法。
In order to get the motion parameters of the moving object, optical flow method is introduced.
因此本文结合两种方法，采用稀疏光流法进行计算。
Thus, we adopt sparse optical flow approach by combing that two approaches in this paper.
提出一种基于光流特征与序列比对的行为识别算法。
This paper Proposed an action recognition algorithm based on optical-flow feature and sequence alignment.
本文给出了一种利用神经网络计算光流场的新算法。
A new algorithm for optical flow computation is presented using neural networks.
提出了一套基于光流特征和序列比对的行为识别算法。
Propose an action recognition algorithm based on optical-flow feature and Sequence Alignment.
它也通常被称为光流计算的，尤其是在计算机视觉文献。
It is also commonly referred to as optical flow computation especially in the computer vision literature.
给出一种新的基于活动轮廓与光流约束的椭圆跟踪算法。
A new ellipse-tracking algorithm based on the active contour and the optical flow technique was proposed.
视觉运动分析分为基于特征的方法和基于光流场的方法。
The main ways of visual motion analysis can be classified into feature based and optical flow based.
基于块的相关算法来计算光流，并利用光流跟踪双手的运动。
Optical flow was computed based on the block relative algorithm, which is used for hand tracking.
而光流场的各种计算方法中，块匹配光流算法的效果比较好。
Moreover, block matching algorithm is the better one in the computational methods of optical flow.
文中还介绍这种轮廓光流场检测对心脏临床压学的实际应用。
The paper also shows the detection for contour-based optical flow field in clinical application of the heart.
研究了心脏左室轮廓光流场检测的一种聚类中心特征点匹配算法。
The paper discusses the detections for contour-based optical flow field of the LV of heart. The detection is an application of matching algorithm of boundary cluster centers.
研究了心脏左室轮廓光流场检测的一种聚类中心特征点匹配算法。
The paper discusses the detections for contour-based optical flow field of the LV of heart.
通常呈现白色的中性光表面，根据光流的变化能够作出显著的变化。
The space that has the white neutral light surface in customary mode is able to be changed dramatically due to the variation of light flow.
针对这些不足，通过使用动态速度约束和光流法对算法进行了改进。
To surmount these disadvantages, dynamic speed constraint and optical flow method were introduced.
为了获得较为精确的结果，用加权最小二乘法来估计序列图像的光流。
In order to obtain more accurate results, the optical flow of sequence image is estimated by the method of weighted least-squares.
算法主要包括图像的预处理，车辆的运动检测和基于光流场的行为分析。
The algorithm is mainly composed of image preprocessing, the vehicle motion detection and behavior analysis based on optical flow.
将这个算法与光流场的计算相结合，大大减少了运算量，提高了运算速度。
If combined with optical flow computing, this algorithm can highly reduce the computation amounts and enhance the computing rate.
原始l -K光流算法用于面部特征点跟踪时，易出现跟踪不稳定的情况。
L-K optical flow algorithm is not very suitable in facial feature point tracking.
与传统光流法、M估计法比较，该算法只在压缩域上进行，不需迭代，具较强实时性。
Compared with traditional optical flow and m estimation methods, the proposed algorithm only calculates in the DC domain and does not iterate, so it can segment almost in real time.
通过位移预补偿方式减小了时域微分估计中的不准确性，极大地提高了光流计算精度。
However, the error of the optical flow estimation derived from the error of temporal differential estimation is not taken into account in above methods.
分析了光流计算中产生时域微分估计误差的各种因素，提出了光流的逐次逼近计算模型。
The factors, which introduce the error of temporal differential estimation are, analyzed. The successive approximation calculation model for the optical flow estimation is put forward.
基于光流场的检测与跟踪是其常用的方法之一，但其计算结果和效率是不能令人满意的。
One of their common methods is based on the detection and tracking of optical flow field, but their calculation results and efficiency are unsatisfied.
为了满足实时跟踪控制的需要，提高两幅图象之间对应点的匹配效率，提出了稀疏光流算法。
Sparse optical flow method was proposed for satisfying the requirement of real-time control and improving the efficiency of matching corresponding points in two im ages.
为了满足实时跟踪控制的需要，提高两幅图象之间对应点的匹配效率，提出了稀疏光流算法。
Sparse optical flow method was proposed for satisfying the requirement of real-time control and improving the efficiency of matching corresponding points in two im ages.
应用推荐