|
|
论文:2014,Vol:32,Issue(2):297-302 |
|
|
引用本文： |
|
|
张子龙, 薛静, 乔鸿海, 智永锋. 基于改进SURF算法的交通视频车辆检索方法研究[J]. 西北工业大学 |
|
|
Zhang Zilong, Xue Jing, Qiao Honghai, Zhi Yongfeng. The Vehicle Retrieval Methods of Traffic Video Based on Improved SURF Algorithm[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 基于改进SURF算法的交通视频车辆检索方法研究 |
|
| 张子龙, 薛静, 乔鸿海, 智永锋 |
|
| 西北工业大学 自动化学院, 陕西 西安 710072 |
| 摘要: |
| 针对传统车辆检索方法中存在准确性和区分度较低的问题,提出了一个基于改进SURF(speeded up robust features)算法的视频车辆检索方法。在车辆视频关键帧提取的基础上,根据改进SURF算法完成车辆图像的特征提取及匹配,其中包含改进FAST(features from accelerated segment test)特征点检测、SURF特征向量提取以及最近邻查询方法来进行特征点的匹配;通过计算比较待检索车辆图像与数据库车辆图像的相似度,算法完成图像筛选并反馈检索结果。实验结果表明:针对交通监控视频中待检索车辆,该方法能够较为准确地进行检索并反馈结果。 |
| 关键词:
车辆视频检索
改进SURF算法
改进FAST特征点
特征点匹配
相似度
|
|
| The Vehicle Retrieval Methods of Traffic Video Based on Improved SURF Algorithm |
|
| Zhang Zilong, Xue Jing, Qiao Honghai, Zhi Yongfeng |
|
| Department of Automatic Control, Northwestern Polytechnic University, Xi'an 710072, China |
| Abstract: |
| To overcome the problem low accuracy and discrimination of traditional vehicle retrieval methods, a new vehicle video retrieval method based on improved SURF algorithm is proposed. On the basis of vehicle video key frame extraction, the improved SURF algorithm is used for extracting and matching of vehicle image features, inclu-ding improved FAST angular point algorithm to extract the image feature points, including SURF algorithm to extract the image feature vector and including nearest neighbor query algorithm to get matching points;through cal-culating and comparing vehicle images to be retrieved and the database of vehicle images in similarity, image filte-ring is completed and the retrieval results are output. The experimental results and their analysis show preliminarily that this method not only can detect the video vehicle, but also can feedback retrieval results fairly accurately. |
| Key words:
algorithms
automobiles
calculations
computer programming languages
experiments
feature extraction
flowcharting
image matching
image retrieval
improved SURF(Speeded Up Robust Features) algorithm
improved FAST key points
key points matching
similarity
vehicle retrieval
|
|
| 收稿日期: 2013-10-30
修回日期:
|
| DOI: |
| 基金项目: 国家自然科学基金(61201321);西北工业大学研究生创业种子基金(Z2014153)资助 |
| 通讯作者:
Email： |
| 作者简介: 张子龙(1989-),西北工业大学硕士研究生,主要从事智能交通系统与模式识别研究。
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] Bay H, Tuytelaars T, Van Gool L. SURF: Speeded up Robust Features[J]. Computer Vision and Image Understanding, 2008,110(3): 346-359
[2] 蔡佳, 黄攀峰. 基于改进 SURF 和 P-KLT 算法的特征点实时跟踪方法研究[J]. 航空学报, 2013, 34(5): 1204-1214 Cai Jia, Huang Panfeng. Research of a Real-Time Feature Point Tracking Method Based on the Combination of Improved SURF and P-KLT Alogrithm[J]. Acta Aeronautica et Astronautica Sinica, 2013, 34(5): 1204-1214 (in Chinese)
[3] 赵璐璐, 耿国华, 李康. 基于 SURF 和快速近似最近邻搜索的图像匹配算法[J].计算机应用研究, 2013, 30(3): 921-923 Zhao Lulu, Geng Guohua, Li Kang. Images Matching Algorithm Based on SURF and Fast Approximate Nearest Neighbor Search [J]. Application Research of Computers, 2013, 30(3): 921-923 (in Chinese)
[4] Zhang Huijuan, Hu Qiong. Fast Image Matching Based-on Improved SURF Algorithm[C] ∥ International Conference on Electronics, Communications and Control (ICECC), 2011: 1460-1463
[5] 郭莉莎, 李俊山, 朱英宏. 基于多尺度 FAST-9 的图像快速匹配算法[J]. 计算机工程, 2012, 38(12): 208-210 Guo Lisha, Li Junshan, Zhu Yinghong. Fast Image Matching Algorithm Based on Multi-Scale FAST-9[J]. Computer Engineering, 2012, 38(12): 208-210 (in Chinese)
[6] 王永明, 王贵锦. 图像局部不变性特征与描述[M]. 北京: 国防工业出版社, 2010: 135-142 Wang Yongming, Wang Jingui. Image Local Invariant Features and Descriptors[M]. Beingjing, National Defence Industry Press, 2012: 135-142 (in Chinese)
[7] 叶银兰. 基于颜色和形状的图像检索[J]. 太原理工大学学报, 2008, 39(2): 127-131 Ye Yinlan. Image Retrieval Based on Color and Shape Feature[J]. Journal of Taiyuan University of Technology, 2008, 39(2):127-131 (in Chinese)
[8] 樊兆宾, 史忠科, 杨珺. 基于视频的车辆检测系统设计[J].计算机工程, 2008, 34(6): 255-257 Fan Zhaobin, Shi Zhongke, Yang Jun. Design of Video-Based Vehicle Detection System[J]. Computer Engineering, 2008, 34 (6): 255-257 (in Chinese) |
|
|
|
|
|
|
|
