中国机械工程
中國機械工程
중국궤계공정
CHINA MECHANICAl ENGINEERING
2012年
11期
1297-1301
,共5页
杨幸芳%黄玉美%韩旭炤%杨新刚
楊倖芳%黃玉美%韓旭炤%楊新剛
양행방%황옥미%한욱소%양신강
SIFT特征%特征匹配%相似性度量%最近邻%次近邻
SIFT特徵%特徵匹配%相似性度量%最近鄰%次近鄰
SIFT특정%특정필배%상사성도량%최근린%차근린
SIFT(scale invariant feature transform) feature%feature matching%similarity measurement%nearest neighbor%second-nearest neighbor
为了提高SIFT特征匹配的效率,首先改造了SIFT特征描述符相似性度量的形式,以街区距离代替欧氏距离作为特征描述符之间的相似性度量,降低了相似性度量公式的时间复杂度;其次,提出了最近邻和次近邻假设算法,即假设待匹配图像中任意2个特征点为最近邻点和次近邻点,通过比较当前特征点与待匹配图像中其他特征点之间的距离,以及当前特征点与假设的最近邻和次近邻之间的距离,实现最近邻和次近邻的替换,最终得到实际的最近邻点和次近邻点。算法减少了相似性计算过程中特征点比较的次数,从而减小了算法的计算量。实验结果表明,提出的算法在保持鲁棒性的同时提高了SIFT特征匹配的效率,能够为一些快速性应用提供保障。
為瞭提高SIFT特徵匹配的效率,首先改造瞭SIFT特徵描述符相似性度量的形式,以街區距離代替歐氏距離作為特徵描述符之間的相似性度量,降低瞭相似性度量公式的時間複雜度;其次,提齣瞭最近鄰和次近鄰假設算法,即假設待匹配圖像中任意2箇特徵點為最近鄰點和次近鄰點,通過比較噹前特徵點與待匹配圖像中其他特徵點之間的距離,以及噹前特徵點與假設的最近鄰和次近鄰之間的距離,實現最近鄰和次近鄰的替換,最終得到實際的最近鄰點和次近鄰點。算法減少瞭相似性計算過程中特徵點比較的次數,從而減小瞭算法的計算量。實驗結果錶明,提齣的算法在保持魯棒性的同時提高瞭SIFT特徵匹配的效率,能夠為一些快速性應用提供保障。
위료제고SIFT특정필배적효솔,수선개조료SIFT특정묘술부상사성도량적형식,이가구거리대체구씨거리작위특정묘술부지간적상사성도량,강저료상사성도량공식적시간복잡도;기차,제출료최근린화차근린가설산법,즉가설대필배도상중임의2개특정점위최근린점화차근린점,통과비교당전특정점여대필배도상중기타특정점지간적거리,이급당전특정점여가설적최근린화차근린지간적거리,실현최근린화차근린적체환,최종득도실제적최근린점화차근린점。산법감소료상사성계산과정중특정점비교적차수,종이감소료산법적계산량。실험결과표명,제출적산법재보지로봉성적동시제고료SIFT특정필배적효솔,능구위일사쾌속성응용제공보장。
In order to solve this problem,the authors reformed the form of similarity measurement of SIFT feature descriptors by using city-block distance instead of Euclidean distance to decrease the time complexity of the similarity measurement formula.Besides,a hypothesis algorithm about the nearest neighbor and the second-nearest neighbor was proposed,which supposed arbitrary two features in the image to be matched were the nearest neighbor point and the second-nearest neighbor point respectively and these two points can be replaced by comparing the distance of the current feature from other features in the image to be matched and the distance of the current feature from the supposed two features,finally the actual nearest neighbor point and the second-nearest neighbor point were gotten.The algorithm reduces the number of compares of features involved in the process of similarity computation and thereby decreases the amount of the computation of the algorithm.Experiments show that the proposed algorithm improves matching efficiency of SIFT features while keeping robustness unchanged,and which can provide safeguard for those applications with high real-time requirements.