昆明理工大学学报(自然科学版)
昆明理工大學學報(自然科學版)
곤명리공대학학보(자연과학판)
JOURNAL OF KUNMING UNIVERSITY OF SCIENCE AND TECHNOLOGY(SCIENCE AND TECHNOLOGY)
2015年
1期
50-54
,共5页
吕恒利%尚振宏%刘辉%吁冬兰
呂恆利%尚振宏%劉輝%籲鼕蘭
려항리%상진굉%류휘%우동란
SIFT%Harris%匹配%特征点%稳定性
SIFT%Harris%匹配%特徵點%穩定性
SIFT%Harris%필배%특정점%은정성
SIFT%Harris%matching%feature point%stability
车辆图像匹配广泛应用于车辆识别和跟踪,其中 SIFT(Scale Invariant Feature Transform)特征匹配算法是当前国内外特征点匹配研究的热点,但针对车辆等刚体特征明显的目标,SIFT 算法在时间复杂度和稳定性方面留出了改进空间。针对车辆图像匹配,本文基于 Harris 角点检测对SIFT 算法进行改进。实验结果表明:该方法在车辆图像匹配时,稳定性和实时性优于 SIFT 算法。
車輛圖像匹配廣汎應用于車輛識彆和跟蹤,其中 SIFT(Scale Invariant Feature Transform)特徵匹配算法是噹前國內外特徵點匹配研究的熱點,但針對車輛等剛體特徵明顯的目標,SIFT 算法在時間複雜度和穩定性方麵留齣瞭改進空間。針對車輛圖像匹配,本文基于 Harris 角點檢測對SIFT 算法進行改進。實驗結果錶明:該方法在車輛圖像匹配時,穩定性和實時性優于 SIFT 算法。
차량도상필배엄범응용우차량식별화근종,기중 SIFT(Scale Invariant Feature Transform)특정필배산법시당전국내외특정점필배연구적열점,단침대차량등강체특정명현적목표,SIFT 산법재시간복잡도화은정성방면류출료개진공간。침대차량도상필배,본문기우 Harris 각점검측대SIFT 산법진행개진。실험결과표명:해방법재차량도상필배시,은정성화실시성우우 SIFT 산법。
Vehicle image matching algorithms are widely used in the field of vehicle identification and tracking, and SIFT(Scale invariant feature transform)is the research focus both at home and abroad for feature points matching.However,SIFT still needs to be improved in time complexity and stability for the objects which have obvious rigid -body characteristics like vehicles.For vehicle image matching,SIFT is improved in this paper on the basis of the Harris corner detection.The experiment results show that this improved algorithm has better sta-bility and real -time performance than SIFT when matching vehicle images.