摘要
提出了一种在连续时空空间对序列图像中运动目标的速度进行估计的算法。该算法克服了以往序列图像目标提取方法的缺点,通过在动态环境里对时间和空间轴求偏导并用三维拟合模板进行数值逼近,较为精确地估计目标的运动速度。算法对目标遮挡和形状变化较大的情形有鲁棒性,计算机模拟实验的结果验证了算法的良好性能。
This paper presents an algorithm for moving target moving target velocity estimation in continuousspatio-temporal space. The algorithm makes it possible to overcome the shortage of existingones for target tracking in sequential images;By calculating the partial derivatives of thetemporal axis and spatial axis under continuous dynamic conditions and with numerical approximation by the three-dimensional fitting templet,the velocity of a moving target can beaccurately estimated. The algorithm is robust for cases where target occlusion and rapidshape change exist.Results by computer simulation show that the performance of the algo-rithm proposed is satisfactory.
出处
《华中理工大学学报》
CSCD
北大核心
1994年第5期69-72,共4页
Journal of Huazhong University of Science and Technology
基金
航天航空工业部航天基础性研究基金
关键词
图像处理
目标提取
速度估计
image processing
sequence image
target tracking
velocity estimation