Tracking feature extraction techniques with improved SIFT for video identification
Tracking feature extraction techniques with improved SIFT for video identification
复制标题
DOI：
10.1007/s11042-015-2694-2
复制
发表时间：
2017-02
影响因子：
3.6
通讯作者：
Ruichen Jin;Jongweon Kim
中科院分区：
文献类型：
--
作者：
Ruichen Jin;Jongweon Kim
提出了一种利用改进的尺度不变特征变换(SIFT)跟踪目标运动和检测特征的方法来识别视频内容。由于SIFT特征描述符对均匀的尺度、方向不变，对仿射失真和光照变化部分不变，即使在杂波和部分遮挡的情况下，SIFT也能稳健地识别目标。即使视频丢帧或受到攻击，我们的方法也能提取特征。在我们的方法中，我们通过跟踪目标的运动来检测视频特征，并用特征序列建立一个数据集来识别视频。与现有的跟踪技术相比，我们的方法识别出了可靠的目标坐标。开发的算法将是一个完整的跟踪和识别系统的重要组成部分。为了评估所提出的方法的性能，我们对几种类型的视频进行了实验。与原来的SIFT算法相比，匹配的处理时间减少了5%。并且在跟踪方法中指定目标区域的位置，使得该方法自动、快速、有效。
This paper presents a method for tracking of object movements and detecting of feature to identify video content using improved Scale-Invariant Feature Transform (SIFT). SIFT can robustly identify objects even among clutter and under partial occlusion, because the SIFT feature descriptor is invariant to uniform scaling, orientation, and also partially invariant to affine distortion and illumination changes. Even if the video drops frames or attacked, our method can extract the features. In our method we detect the video features from tracking the object’s movement and make a dataset with feature sequences to identify video. In contrast to the existing tracking techniques, our method recognized reliable object coordinate. The developed algorithm will be an essential part of a completely tracking and identification system. To evaluate the performance of the proposed approach, we was experimenting with several genres of video. Compare with the original SIFT algorithm, we reducing up to 5 % in processing time was achieved for matching. Also appoint the position of the object area in tracking method make the proposed method automatic, fast and effective.