1) occlusion segmentation
遮挡分割
1.
Movement estimation frame based tracking method is proposed,and combined with parallelogram contour based occlusion segmentation method to realize realtime muhi-vehicle tracking.
本文针对这两个影响实时车辆检测与跟踪系统性能的主要因素,采用基于无偏卡尔曼滤波器(UKF)的方法为场景背景建模,提取出运动区域,再通过边缘特征检测出场景中的运动阴影,然后利用角点信息将目标与阴影分离;提出了一种基于运动预测框的目标跟踪算法,将它与基于车辆平行四边形轮廓的遮挡分割方法结合,构建了多车辆目标的实时跟踪系统,并用实验验证了它的实用性与鲁棒性。
2) occluded people segmentation
遮挡人体分割
3) occluded human segmentation
遮挡人体目标分割
4) partial occlusion
部分遮挡
1.
The experimental results show that the algorithm is computationally efficient and robust to scale invariant,partial occlusion and interactions of n.
实验显示,该算法计算简单,对相似目标能实现准确的跟踪,对非刚性目标的尺度变化、多目标的交叉及部分遮挡具有鲁棒性。
2.
Two experiments were made to study the different processes of the partial occlusion drawings ofparticipants of different styles.
本研究考察了５—６岁儿童不同认知方式对部分遮挡绘画任务的影响。
5) part occlusion
部分遮挡
1.
In order to deal with part occlusion,an IFGT based moving human interaction tracking approach was put for ward.
针对运动人体跟踪的部分遮挡问题,提出了一种基于IFGT的运动人体交互跟踪方法。
2.
In order to deal with part occlusion,a description interaction based moving human tracking approach is put forward.
针对运动人体跟踪的部分遮挡问题,提出了一种基于描述符交互的跟踪方法。
6) shelter analysis
遮挡分析
补充资料：遮挡
1.阻挡;遮蔽。 2.指可以遮蔽拦挡的东西。
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条