摘要
花卉生长过程原始视频数据量大,冗余信息多。为了获得便于研究人员使用的压缩比高、数据量小、包含丰富生长细节信息、流畅自然、花卉生长过程视频,引入了关键帧提取方法对原始视频进行处理。根据花卉生长过程的特点,选择运动检测相关算法进行测试。对传统的帧间差分法进行了仿真分析,并提出了一种新的基于光流法及运动方向信息熵统计的关键帧提取方法。试验证明,该方法明显优于帧间差分法,在提取相同数量关键帧的情况下,能够更完整的表现花卉运动细节。该研究可为花卉生长过程的动态监测提供参考。
The original video of flower growth process contains large amount of data and plenty of redundance information.In order to obtain the video of flower growth process to facilitate the researchers,which is endowed with high compression ratio,small amount of data,rich growth details information and natural fluency,a key frame extraction method was introduced to process the original video.According to the characteristics of flower growing process,he motion detection algorithm was chosen to take tests on them.Through the simulation analysis of frame difference method,this paper proposed a new key frame extraction method based on optical flow and direction information entropy.Experiment showed that in the case of extracting the same number of key frames,this method can perform details of the flower movement better,which is superior to the frame difference method.
出处
《农业工程学报》
EI
CAS
CSCD
北大核心
2012年第17期125-130,共6页
Transactions of the Chinese Society of Agricultural Engineering
基金
北京市自然科学基金资助项目(6123035)
关键词
图像处理
熵
光流
关键帧提取
花卉
image processing
entropy
optical flows
key frame retrieval
flowers
