Vehicle identification from remote sensing image based on image symmetry
CHEN Ren1,2, HUANG Huixian2, TAN Yuan2, WANG Chengxiao2
1. Hunan NOVASKY Electronic Technology Ltd, Changsha 410205, China;
2. The College of Information Engineering, Xiangtan University, Xiangtan 411105, China
The plan view of the vehicle image is symmetrical, which leads to the existence of repeated characteristics in the image. In view of such a situation, the authors present an optimal selection method for Haar-like features. Within the detection window, the two types of features are selected: a half of the detection window's height is taken, and then all the rectangular features are extracted; in the original detection window, only the features that are symmetrical about the symmetry axis of detection window are used, and the upper and lower parts' difference is described. We can fully express the image information and also reduce the repetitive characteristics by using this method. The cascade classifier is trained by extracting these features in samples' grayscale and saturation images, while each layer is trained by using AdaBoost algorithm. The experimental results show that the proposed approach can significantly reduce the number of features and improve the training speed, thus achieving good recognition results.
[1] 余勇,郑宏.基于形态神经网络的高分辨率卫星影像车辆检测[J].哈尔滨工程大学学报,2006,27(s1):189-193. Yu Y,Zheng H.Vehicle detection from high resolution satellite imagery based on the morphological neural network[J].Journal of Harbin Engineering University,2006,27(s1):189-193.
[2] 郑宏,胡学敏.高分辨率卫星影像车辆检测的抗体网络[J].遥感学报,2009,13(5):913-927. Zheng H,Hu X M.An antibody networks approach for vehicle detection from high resolution satellite imagery[J].Journal of Remote Sensing,2009,13(5):913-927.
[3] 吴小波,杨辽,沈金祥,等.基于背景迭代搜索的高分辨遥感图像汽车检测[J].国土资源遥感,2011,23(4):46-51.doi:10.6046/gtzyyg.2011.04.09. Wu X B,Yang L,Shen J X,et al.Car detection by using high resolution remote sensing image based on background iterative search[J].Remote Sensing for Land and Resources,2011,23(4):46-51.doi:10.6046/gtzyyg.2011.04.09.
[4] 李世武,徐艺,孙文财,等.基于自反馈模板提取的车辆遥感图像识别[J].华南理工大学学报:自然科学版,2014,42(5):97-102. Li S W,Xu Y,Sun W C,et al.Remote sensing image recognition for vehicles based on self-feedback template extraction[J].Journal of South China University of Technology:Natural Science Edition,2014,42(5):97-102.
[5] 秦彦光.高分辨率遥感图像道路网及车辆信息提取[D].长春:吉林大学,2014. Qin Y G.Study on Road Network and Automobile Information Extraction Based on High Resolution Remote Sensing Image[D].Changchun:Jilin University,2014.
[6] 曹天扬,申莉.基于交通遥感图像处理的车辆目标识别方法[J].计算机测量与控制,2014,22(1):222-224. Cao T Y,Shen L.Vehicles identification method based on traffic remote sensing image[J].Computer Measurement & Control,2014,22(1):222-224.
[7] Papageorgiou C P,Oren M,Poggio T.A general framework for object detection[C]//Proceedings of the 6th International Conference on Computer Vision.Bombay:IEEE,1998:555-562.
[8] Viola P,Jones M.Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the Computer Society Conference on Computer Vision and Pattern Recognition.Kauai,HI,USA:IEEE,2001,1:8-14.
[9] 蔡益红.多特征融合的道路车辆检测方法[J].计算技术与自动化,2013,32(1):98-102. Cai Y H.Fusing multiple features to detect on-road vehicles[J].Computing Technology and Automation,2013,32(1):98-102.
[10] Freund Y,Schapire R E.Experiments with a new Boosting algorithm[C]//Proceedings of the 13th Conference on Machine Learning.Murray Hill,NJ:AT&T Bell Laboratories,1996:148-156.
[11] Freund Y.Boosting a weak learning algorithm by majority[J].Information and Computation,1995,121(2):256-285.
[12] Schapire R E,Singer Y.Improved boosting algorithms using confidence-rated predictions[J].Machine Learning,1999,37(3):297-336.
[13] 彭英辉,张东波,沈奔.基于多尺度匹配滤波和集成学习的眼底图像微脉瘤检测[J].计算机应用,2013,33(2):543-546,566. Peng Y H,Zhang D B,Shen B.Microaneurysm detection based on multi-scale match filtering and ensemble learning[J].Journal of Computer Applications,2013,33(2):543-546,566.
[14] 莫琛.基于视觉的道路前方运动车辆检测与跟踪[D].广州:华南理工大学,2013. Mo C.Vision-Based Front Vehicle Detection and Tracking[D].Guangzhou:South China University of Technology,2013.
2016, Vol. 28 
