1) multi-view tracking data fusing
多目视觉数据融合
1.
This paper proposes a novel multi-view object tracking algorithm, which includes binocular stereo tracking and multi-view tracking data fusing.
首先进行双目视觉立体跟踪:采用扩展Kalman进行预测,根据外极线约束剔出预测区域内的错误候选目标;然后进行多目视觉数据融合:利用基于可变阈值的最邻近数据融合算法对已获得的多个双目跟踪数据进行处理,解决了标记点遮挡、丢失问题;最后得到了标记点的三维运动数据。
2) vision and inertial data fusion
视觉/惯性数据融合
3) multi visual cue integration
多视觉信息融合
1.
To improve the adaptability of visual tracking system for various circumstances in space,a visual tracking strategy based on fuzzy multi visual cue integration is proposed,which synthesizes multi visual cue together to represent the features of object.
为了提高视觉跟踪系统在空间环境对外界变化的适应能力,提出一种模糊化多视觉信息融合的视觉跟踪策略。
4) multi-data fusion
多数据融合
1.
This paper introduced dimensional parameters and nondimensional parameters in time domain analysis,built multi-data fusion fault diagnosis system,which included data level fusion module,feature level fusion module and decision level data fusion module,adopted the neuronal networks to conquer the shortcoming of neural network and to solve the abuse of evidence theory which is difficult to gain BPA.
介绍了时域分析中的有纲量参数和无纲量参数,构建了多数据融合故障诊断系统。
5) visual information fusion
视觉融合
6) video data amalgamation
视频数据融合
补充资料：多数
较大的数量：绝大～ㄧ少数服从～ㄧ～人赞成这个方案。
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