结合全局信息的对称SURF算法在车辆检测中的应用

doi:10.3969/j.issn.1006-2475.2015.01.016

计算机与现代化

结合全局信息的对称SURF算法在车辆检测中的应用

(南京航空航天大学计算机科学与技术学院，江苏南京210016)

收稿日期:2014-10-30 出版日期:2015-01-19 发布日期:2015-01-21
作者简介:熊琰铖(1990-)，男，回族，江苏南京人，南京航空航天大学计算机科学与技术学院硕士研究生，研究方向：计算机视觉，智能交通；孙涵(1978-)，男，江苏扬州人，副教授，博士，研究方向：数字图像处理，计算机视觉。
基金资助:
国家自然科学基金资助项目（61203246，61375021）；江苏省自然科学基金资助项目(SBK201322136)

Application of Symmetrical SURF with Global Context in Vehicle Detection

(College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China)

Received:2014-10-30 Online:2015-01-19 Published:2015-01-21

摘要/Abstract

摘要： SURF（SpeedUp Robust Features）是一种鲁棒且快速的算法，可以应用于多种场合，但是它不能检测对称匹配，也没有考虑全局信息。本文将对称SURF和全局信息结合起来，既通过镜像变换增强了SURF检测对称匹配特征的能力，又可以在图像有多个相似区域的情况下减少错误匹配。该算法应用在车辆检测中，实验表明结合全局信息的对称SURF提高了特征匹配的准确率，从而提高了车辆检测的准确率。


关键词: 对称SURF, 全局信息, 车辆检测

Abstract: SURF（SpeedUp Robust Features） is a robust and fast descriptor for many applications, but neither can it detect symmetrical matches, nor can it consider global context. This paper combines symmetrical SURF with global context. It enables SURF to detect symmetrical matches through mirroring transformation and reduces mismatches when local descriptors are similar. The proposed algorithm is used in vehilce detection. The experiments show that symmetrical SURF with global context improves the accuracy of feature matches and vehicle detection.


Key words: symmetrical SURF, global context, vehicle detection

中图分类号:

TP391

熊琰铖，孙涵. 结合全局信息的对称SURF算法在车辆检测中的应用[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2015.01.016.

XIONG Yan-cheng, SUN Han. Application of Symmetrical SURF with Global Context in Vehicle Detection[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2015.01.016.

参考文献

［1］Lowe D,Vancouver B C. Object recognition from local scaleinvariant features［C］// Proceedings of the 7th International Conference on Computer Vision. 1999,2:1150-1157.
［2］Lowe D G. Distinctive image features from scaleinvariant keypoints［J］. International Journal of Computer Vision, 2004,60(2):91-110.
［3］Matas J, Chum O, Urban M, et al. Robust widebaseline stereo from maximally stable extremal regions［C］// Proceedings of the 2002 British Machine Vision Conference. 2002:384393.
［4］Vincent L, Soille P. Watersheds in digital spaces: An efficient algorithm based on immersion simulations［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991,13(6):583-598.
［5］Bay H, Ess A, Tuytelaars T, et al. Speededup robust features (SURF)［J］. Computer Vision and Image Understanding, 2008,110(3):346-359.
［6］Hsieh J, Chen L, Chen D. Symmetrical SURF and its applications to vehicle detection and vehicle make and model recognition［J］. IEEE Transactions on Intelligent Transportation Systems, 2014,15(1):6-20.
［7］Mortensen E N, Deng H, Shapiro L G. A SIFT descriptor with global context［C］// Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2005,1:184-190.
［8］Li Canlin, Ma Lizhuang. A new framework for feature descriptor based on SIFT［J］. Pattern Recognition Letters, 2009,30(5):544-557.
［9］Carmichael G, Laganiere R, Bose P. Global context descriptors for SURF and MSER feature descriptors［C］// Proceedings of the 2010 Canadian Conference on Computer and Robot Vision. 2010:309-316.
［10］齐美彬,杨爱丽,蒋建国，等. 一种基于改进码本的车辆检测和跟踪方法［J］. 中国图象图形学报, 2011,16(3):406-412.
［11］Veeraraghavan H, Masoud O, Papanikolopoulos N. Visionbased monitoring of intersections［C］// Proceedings of the 5th International Conference on Intelligent Transportation Systems. 2002:7-12.
［12］Zhang zhaoxiang, Cai Yinghao, Huang Kaiqi, et al. Realtime moving object classification with automatic scene division［C］// Proceedings of the 2007 IEEE International Conference on Image Processing. 2007,5:149-152.
［13］Faro A, Giordano D, Spampinato C. Adapative background modeling integrated with luminosity sensors and occlusion processing for reliable vehicle detection［J］. IEEE Transactions on Intelligent Transportation Systems, 2011,12(4):1398-1412.
［14］Unmo H, Ojuma K, Hayashibe K, et al. Vehicle motion tracking using symmetry of vehicle and background subtraction［C］// Proceedings of the 2007 Intelligent Transportation Symposium. 2007:1127-1131.
［15］Jazayeri A, Cai H, Zheng J, et al. Vehicle detection and tracking in car video based onmotion model［J］. IEEE Transactions on Intelligent Transportation Systems, 2011,12(2):583-595.
［16］Chen S, Hsieh J. Jointing edge labeling and geometrical constraint for lane detection and its application to suspicious driving behavior analysis［J］. Jonrnal of Information Science and Engineering, 2011,27(2):715-732.
［17］Hsieh J. Vehicle Make and Model Recognition［DB/OL］. http://mmplab.cs.ntou.edu.tw/MMR/, 2014-06-25.

[1]	张文丽, 徐丽, 刘星星. 基于卷积神经网络的夜间车辆检测算法[J]. 计算机与现代化, 2022, 0(05): 108-113.
[2]	胡昌冉, 樊彦国, 禹定峰. 嵌入空洞卷积模块的改进YOLOv3车辆检测算法[J]. 计算机与现代化, 2021, 0(04): 53-60.
[3]	刘雁斌1,2. 高速公路收费站防盗卡系统设计与实现[J]. 计算机与现代化, 2014, 0(4): 191-194.
[4]	杨小伟;徐贵力;王彪;郭瑞鹏;田裕鹏;何银南. 一种基于局部梯度矢量的车辆检测方法[J]. 计算机与现代化, 2013, 1(2): 9-14.
[5]	杨志奇. 车辆检测系统中背景提取与更新算法研究 [J]. 计算机与现代化, 2010, 1(7): 111-114.

结合全局信息的对称SURF算法在车辆检测中的应用

Application of Symmetrical SURF with Global Context in Vehicle Detection

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价