Research on high-speed and robust image measurement method based on spatial and temporal unique information

点击翻译按钮获取中文摘要

In this research, a new image measurement method has been proposed. By using a small number of image information, our method has achieved high speed image matching and object recognition. Its processing time is approximately 1000 times shorter than conventional methods.I have shown that useful information for image matching is unique pixels and it can be calculated by estimation of probability of co-occurrence of pixel intensity. Robustness for varying illumination was performed by measuring spatial and temporal co-occurrence behaviors. In addition, stable classification ability has been realized by estimating distinguishability of the data for similar objects around the target object. Moreover, I have proposed additional methods to apply this basic idea to 3D object recognition and robust matching for partial occlusion.I have proved that the proposed method can realize high-speed and reliable image matching by setting appropriate strategy for reducing amount of data.