HFR-video-based Image Pattern Recognition Using Pixel-level Temporal Frequency Response Matching
HFR-video-based Image Pattern Recognition Using Pixel-level Temporal Frequency Response Matching
复制标题
DOI：
10.1109/coase.2018.8560517
复制
发表时间：
2018-08
期刊：
影响因子：
--
通讯作者：
Kohei Shimasaki;Tomoaki Okamura;Mingjun Jiang;T. Takaki;I. Ishii;Kazuhiko Yamamoto
中科院分区：
文献类型：
--
作者：
Kohei Shimasaki;Tomoaki Okamura;Mingjun Jiang;T. Takaki;I. Ishii;Kazuhiko Yamamoto
在本文中，我们提出了一种新的方法，基于动态的图像模式识别，可用于检查一个指定的振动模式，通过计算时变亮度信号的时间频率响应在一个高帧速率的视频序列的所有像素。时间频率响应是时变亮度信号中的时间频率分量的直方图，可以使用短期傅立叶变换来计算时间频率响应，并且将它们与参考振动图案的时间频率响应逐像素地匹配，以确定是否识别出特定的振动图案。我们的基于动力学的图像模式识别方法的有效性证明了使用几个振动源定位结果飞行多旋翼和昆虫，旋转或扑动频率的范围内的数百赫兹。
In this paper, we propose a novel method for dynamics-based image-pattern recognition that can be used to inspect a specified vibrating pattern by computing temporal frequency responses in time-varying brightness signals at all the pixels of a high-frame-rate video sequence. The temporal frequency responses, which are the histograms of temporal frequency components in time-varying brightness signals, can be calculated using the short-term Fourier transform, and they are matched pixelwise with those of a reference vibrating pattern to determine whether a specific vibrating pattern is recognized. The effectiveness of our dynamics-based image pattern-recognition method is demonstrated using several vibration-source localization results for flying multicopters and insects, the rotating or flapping frequencies of which were in the range of hundreds of Hertz.