CAJ | 학술논문

利用光流法可以对视频中运动目标进行特征点跟踪，当目标存在较大尺度运动时，光流法图像一致性假设难以满足，导致特征点跟踪丢失。针对此问题，提出了一种基于 Lucas-Kanade（L-K）金字塔光流算法的运动人体特征点跟踪方法。首先，利用帧间差分法得到帧差图像序列，获取行人的运动区域；然后用尺度不变特征变换（SIFT）算法检测选定初始帧中的特征点；最后运用 L-K 金字塔光流算法跟踪这些特征点在后续帧中的位置。实验结果表明，该算法对较大尺度运动的特征点跟踪有很好的效果，提高了跟踪的准确性。
이용광류법가이대시빈중운동목표진행특정점근종，당목표존재교대척도운동시，광류법도상일치성가설난이만족，도치특정점근종주실。침대차문제，제출료일충기우 Lucas-Kanade（L-K）금자탑광류산법적운동인체특정점근종방법。수선，이용정간차분법득도정차도상서렬，획취행인적운동구역；연후용척도불변특정변환（SIFT）산법검측선정초시정중적특정점；최후운용 L-K 금자탑광류산법근종저사특정점재후속정중적위치。실험결과표명，해산법대교대척도운동적특정점근종유흔호적효과，제고료근종적준학성。
The feature points of the moving target in the video can be tracked through optical flow algorithm.When the target exists a movement with a relatively large scale,it is difficult to meet the image consistency hypothesis of optical flow, which results in the loss of tracked feature points.Concerning this problem,a method of moving human feature points track-ing based on Lucas-Kanade pyramidal optical flow algorithm was proposed.First,the moving region of the human was ob-tained by the difference between the consecutive frames.Then,some feature points of the start frame were detected with the SIFT algorithm.Finally,the feature points were tracked in the subsequent frames through the image pyramidal optical flow. The experimental results suggest that the algorithm performs well on the feature points tracking of large scale movement and the tracking accuracy is improved.