在復(fù)雜場景中多目標(biāo)物的檢測識(shí)別方法

本文提出了一種在復(fù)雜場景中實(shí)時(shí)檢測、識(shí)別多個(gè)目標(biāo)物體的方法。利用由矩陣碼（matrix code）構(gòu)成的 2D 矩陣來識(shí)別復(fù)雜場景中多個(gè)目標(biāo)物。算法不僅能適應(yīng)目標(biāo)物體在旋轉(zhuǎn)、縮放、平移變換下的不變性識(shí)別，而且能適應(yīng)仿射及射影變換下的不變性識(shí)別。試驗(yàn)結(jié)果證明所提供的算法在識(shí)別和監(jiān)視系統(tǒng)中有很好的魯棒性和實(shí)時(shí)性。
關(guān)鍵詞 ： 矩陣碼; 目標(biāo)識(shí)別； 拐角點(diǎn)提??； 透視變換； 圖像匹配；
Abstract: An method for real-time detection and recognition of multi-targets in complex scenes is presented.This method utilizes 2D matrix markers, being composed of matrix code ,which can identify a large number of objects.The algorithm can adapt to object recognition，invariant not only under rotation、scaling、 translation , but
under affine and projective transformation. Experimental results are given to demonstrate the robust adaptation and real-time of the algorithm in recognition and surveillance system.
Key words: matrix code; object recognition; corner detection; perspective transformation; image matching.