在機器人遙操作系統(tǒng)中，目前普遍采用預測仿真的方法來克服信號傳輸時延對遙操作的
影響。但虛擬環(huán)境與實際環(huán)境往往不是完全一致的，因而僅僅依靠仿真圖形來輔助完成遙操作任務是不可靠的。針對預測仿真的不足，本文詳細介紹了視頻融合中的關鍵技術，使仿真圖形能精確的與視頻圖像相匹配，從而直觀的為操作者提供仿真模型與真實機器人運動是否一致的信息，輔助操作者正確可靠的完成遙操作任務。
關鍵詞視頻融合；機器人遙操作；預測顯示；相機標定
Abstract: In telerobotic systems, predictive displays are widely used to overcome the affection of time delay at present. But it is not reliable to accomplish the remote-servicing task by the assistant of the simulated graphic models because of the lack of accurate matching between the virtual environment and the real environment. This paper presents key techniques about an overlay of the three dimensional graphical models over video images. It can offer the operator the accurate matching between the simulated model and the video image of the actual robot, and assist the operator to accomplish the remote control task correctly and reliably.
key words: graphics overlay on video images; telerobotic operation;predictive display;camera calibration