|本期目录/Table of Contents|

[1]李旋,韩天园,吕凯光,等.基于改进SIFT算法的交通事故图像匹配*[J].中国安全生产科学技术,2021,17(1):182-188.[doi:10.11731/j.issn.1673-193x.2021.01.029]
　LI Xuan,HAN Tianyuan,LYU Kaiguang,et al.Images matching of traffic accident based on improved SIFT algorithm[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(1):182-188.[doi:10.11731/j.issn.1673-193x.2021.01.029]
点击复制

基于改进SIFT算法的交通事故图像匹配*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
17
期数:
2021年1期
页码:
182-188
栏目:
职业安全卫生管理与技术
出版日期:
2021-01-31

文章信息/Info

Title:
Images matching of traffic accident based on improved SIFT algorithm
文章编号:
1673-193X(2021)-01-0182-07
作者:
李旋; 韩天园; 吕凯光; 刘永涛
(长安大学 汽车学院，陕西 西安 710064)
Author(s):
LI Xuan;  HAN Tianyuan;  LYU Kaiguang;  LIU Yongtao
(School of Automobile,Chang’an University,Xi’an Shaanxi 710064,China)
关键词:
交通事故; 尺度不变特征变换; 改进的高斯金字塔; 局部线性嵌入; 分区域特征点匹配
Keywords:
traffic accident;  scaleinvariant feature transformation;  improved Gaussian pyramid;  local linear embedding;  regional feature point matching
分类号:
X951
DOI:
10.11731/j.issn.1673-193x.2021.01.029
文献标志码:
A
摘要:
为解决无人机航拍交通事故现场图像特征点数量较少、匹配成功率较低、耗时过长的问题，提出1种改进的SIFT算法，使用Gabor滤波对图像进行特征提取，基于改进的高斯金字塔和多方向多尺度Gabor频谱特点提取出具有尺度、旋转不变性的特征点，结合LLE算法对特征描述符进行降维处理，通过DBSCAN算法对特征点进行密度聚类，计算区域内的特征点距离的梯度下降一致性程度，结合蚁群算法判断特征点是否匹配成功。结果表明：改进的SIFT算法无论是在匹配精度还是在匹配效率上都优于同类算法，证明提出算法的有效性。
Abstract:
In order to solve the problems of small number of feature points,low matching success rate and long timeconsuming for the UAC aerial field images of traffic accidents,an improved SIFT algorithm was proposed.The Gabor filter was used to extract the image features,and the feature points with the scale and rotation invariance were extracted based on the improved Gaussian pyramid and multidirectional multiscale Gabor spectrum features.The dimension reduction of feature descriptors was carried out combining with LLE algorithm,and the density clustering of feature points was conducted through the DBSCAN algorithm.The consistency degree of gradient descent for the distances of feature points in the region was calculated,and the ant colony algorithm was applied to determine whether the feature points were matched successfully.The results showed that the improved SIFT algorithm was superior to similar algorithms in both matching accuracy and matching efficiency,which proved the effectiveness of the proposed algorithm.

参考文献/References:

［1］LOWE D G.Distinctive image features from scale-invariant keypoints［J］.International Journal of Computer Vision,2004,60(2):91-110.
［2］丁苏楠,张秋菊.基于改进SIFT算法的图像匹配方法［J］.传感器与微系统,2020,39(10):45-47,50. DING Sunan,ZHANG Qiuju.Image matching method based on improved SIFT algorithm ［J］.Sensors and Microsystems,2020,39(10):45-47,50.
［3］张培佩,王永波,宋伟.基于改进SIFT算法的无人机影像匹配［J］.湖南科技大学学报（自然科学版）,2019,34(2):90-95. ZHANG Peipei,WANG Yongbo,SONG Wei.UAV image matching based on improved SIFT algorithm ［J］.Journal of Hunan University of Science and Technology (Natural Science),2019,34(2):90-95.
［4］孙雪强,黄旻,张桂峰,等.基于改进SIFT的多光谱图像匹配算法［J］.计算机科学,2019,46(4):280-284. SUN Xueqiang,HUANG Min,ZHANG Guifeng,et al.Multi-spectral image matching algorithm based on improved SIFT ［J］.Computer Science,2019,46(4):280-284.
［5］卢鹏,卢奇,邹国良,等.基于改进SIFT的时间序列图像拼接方法研究［J］.计算机工程与应用,2020,56(1):196-202. LU Peng,LU Qi,ZOU Guoliang,et al.Study on time series image stitching based on improved SIFT ［J］.Computer Engineering and Applications,2020,56(1):196-202.
［6］韩宇,宗群,邢娜.基于改进SIFT的无人机航拍图像快速匹配［J］.南开大学学报（自然科学版）,2019,52(1):5-9. HAN Yu,ZONG Qun,XING Na.Improved SIFT based UAV aerial image fast matching ［J］.Journal of Nankai University (Natural Science),2019,52(1):5-9.
［7］SADEGHIPOUR E,SAHRAGARD N.Face recognition based on improved SIFT algorithm ［J］.International Journal of Advanced Computer Sciences and Applications,2016,7(1):548-551.
［8］耿庆田,赵浩宇,王宇婷,等.基于改进SIFT特征提取的车标识别［J］.光学精密工程,2018,26(5):1267-1274. GENG Qingtian,ZHAO Haoyu,WANG Yuting,et al.Identification of vehicle logo based on improved SIFT feature extraction ［J］.Optical Precision Engineering,2018,26(5):1267-1274.
［9］张护望,林浒,王诗宇,等.一种基于改进SIFT算法的轨道板图像匹配方法［J］.组合机床与自动化加工技术,2018(3):1-3,7. ZHANG Huwang,LIN Hu,WANG Shiyu,et al.A track board image matching method based on improved SIFT algorithm ［J］.Modular Machine Tools and Automated Processing Technology,2018(3):1-3,7.
［10］穆莉莉,姚潘涛,郭枫,等.BP神经网络在SLAM特征匹配中的应用［J］.测绘科学,2020,45(10):27-32. MU Lili,YAO Pantao,GUO Feng,et al.Application of BP neural network in SLAM feature matching ［J］.Science of Surveying and Mapping,2020,45(10):27-32.
［11］周宏浩,易维宁,杜丽丽,等.基于卷积神经网络的SIFT特征描述符降维方法［J］.激光与光电子学进展,2019,56(14):121-128. ZHOU Honghao,YI Weining,DU Lili,et al.SIFT feature descriptor dimensionality reduction method based on convolutional neural network ［J］.Advances in Laser and Optoelectronics,2019,56(14):121-128.
［12］张俞晴,何宁,魏润辰.基于卷积神经网络融合SIFT特征的人脸表情识别［J］.计算机应用与软件,2019,36(11):161-167. ZHANG Yuqing,HE Ning,WEI Runchen.Facial expression recognition based on convolutional neural network incorporating SIFT features ［J］.Computer Applications and Software,2019,36(11):161-167.
［13］YU L L,DAI Q.Improved SIFT feature matching algorithm ［J］.Computer Engineering,2011,37(2):210-212.
［14］ZHANG Y,WU Y J.Improved SIFT image feature matching algorithm ［J］.Computer Engineering & Applications,2014,50(9):167-169.
［15］IOANNIDIS K,BATTY C,TURNER C,et al.Exvivo detection and quantification of apically extruded volatile compounds and disinfection by-products by SIFT-MS,during chemomechanical preparation of infected root canals ［J］.Dental Materials,2020,36(2):257-269.

相似文献/References:

[1]房曰荣,沈斐敏.道路交通事故发展趋势分析与预测[J].中国安全生产科学技术,2012,8(3):141.
　FANG Yue rong,SHEN Fei min.Development trend analysis and prediction of traffic accident[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(1):141.
[2]房曰荣,沈斐敏.交通运输企业交通事故法律适用问题探讨[J].中国安全生产科学技术,2010,6(2):12.
　FANG Yue-rong,SHEN Fei-min.A study on the legal application of the transportation enterprises’ traffic accidents[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2010,6(1):12.
[3]鲁守东,周国华,孙景冬.基于MMESE模型的高速铁路运营系统可靠性研究* ——以“723”甬温线动车事故为例[J].中国安全生产科学技术,2013,9(3):19.[doi:10.11731/j.issn.1673-193x.2013.03.04]
　LU Shou dong,ZHOU Guo hua,SUN Jing dong.Study on operation system reliability of highspeed railway based on MMESE model—a case of "723" YongWen line accident[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2013,9(1):19.[doi:10.11731/j.issn.1673-193x.2013.03.04]
[4]陈定秋,朱德林.高速公路交通事故的季节变动规律分析及预测[J].中国安全生产科学技术,2013,9(3):188.[doi:10.11731/j.issn.1673-193x.2013.03.34]
　CHEN Ding qiu,ZHU De lin.Analysis on seasonal variation law and prediction on number of highway traffic accidents[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2013,9(1):188.[doi:10.11731/j.issn.1673-193x.2013.03.34]
[5]俞春俊,王长君.摩托车头盔与摩托车交通事故的相关研究[J].中国安全生产科学技术,2009,5(2):76.
　YU Chun jun,WANG Chang jun.Interrelated studies on safety helmet and traffic accidents involving motorcycles[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2009,5(1):76.
[6]辛督强.基于熵权-TOPSIS的陕西省各市区道路交通安全评价[J].中国安全生产科学技术,2015,11(10):116.[doi:10.11731/j.issn.1673-193x.2015.10.020]
　XIN Du-qiang.Evaluation on road traffic safety of the cities in Shaanxi province based on entropy-TOPSIS method[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2015,11(1):116.[doi:10.11731/j.issn.1673-193x.2015.10.020]
[7]熊睿,邓院昌.疲劳驾驶交通事故的严重程度影响因素分析*[J].中国安全生产科学技术,2022,18(4):20.[doi:10.11731/j.issn.1673-193x.2022.04.003]
　XIONG Rui,DENG Yuanchang.Analysis on factors affecting severity of traffic accidents caused by fatigue driving[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(1):20.[doi:10.11731/j.issn.1673-193x.2022.04.003]
[8]潘福全,张游,张丽霞,等.海底隧道交通事故风险耦合演化机理研究*[J].中国安全生产科学技术,2022,18(4):231.[doi:10.11731/j.issn.1673-193x.2022.04.033]
　PAN Fuquan,ZHANG You,ZHANG Lixia,et al.Study on coupling evolution mechanism of traffic accident risk in undersea tunnel[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(1):231.[doi:10.11731/j.issn.1673-193x.2022.04.033]

备注/Memo

备注/Memo:

* 基金项目： 陕西省重点研发计划项目（2020ZDLGY16-08）；中央高校基本科研业务费专项资金项目（300102220111，300102229668）
作者简介： 李旋，硕士研究生，主要研究方向为交通事故与图像处理。
通信作者： 刘永涛，博士，副教授，主要研究方向为交通事故与图像处理。
更新日期/Last Update: 2021-02-04