基于视觉显著性车辆监控视频关键帧提取方法
|
摘要
针对道路车辆监控视频中车辆的关键帧提取问题,基于视觉显著性提出了一种关键帧提取方法。该方法首先对监控视频中的目标车辆进行检测、跟踪及背景分离,其次分别提取目标车辆的FT、LBP与边缘三种底层特征,并在RGB颜色空间根据改进后的加权欧氏距离得到车牌相似图。然后根据车牌相似度越小则给三种底层特征越大惩罚的思想,采用车牌相似图对FT、LBP与边缘三种底层特征图像进行优化,将三种优化后的底层特征图像进行加权平均融合,得到多特征融合图像。最后以多特征融合图像结果为参考,选取出目标显著性程度最大的融合图像对应的视频帧为关键帧。实验结果表明,该方法能提取监控区域的序列图像帧中车辆信息最丰富的图像,实现道路车辆监控视频中车辆数据的有效压缩。
A key frame extraction approach based on visual saliency is proposed aiming at extraction of the key frame of vehicle on road surveillance video. Firstly,the target vehicle in the surveillance video is detected,tracked and separated,then the FT,LBP and edge features of the target vehicle are extracted and the similarity map of the license plate is obtained according to the improved weighted Euclidean distance in RGB color space. Secondly,according to the idea that the smaller the similarity of license plates,the greater the penalty for the three underlying features,three underlying feature maps are optimized according to the similarity map of the license plate,and the multi-feature fusion image is obtained by weighted average fusion of three major feature maps. Finally,taking the best definition of the multi-feature fusion image as the reference,the frames whose fusion maps can pop out the objects best are selected as key frames. Experiment shows that for a series of vehicle images in the surveillance video,the algorithm presented effectively selects the most abundant image of vehicle,realizing effective compression of vehicle data for road vehicle surveillance.
A key frame extraction approach based on visual saliency is proposed aiming at extraction of the key frame of vehicle on road surveillance video. Firstly,the target vehicle in the surveillance video is detected,tracked and separated,then the FT,LBP and edge features of the target vehicle are extracted and the similarity map of the license plate is obtained according to the improved weighted Euclidean distance in RGB color space. Secondly,according to the idea that the smaller the similarity of license plates,the greater the penalty for the three underlying features,three underlying feature maps are optimized according to the similarity map of the license plate,and the multi-feature fusion image is obtained by weighted average fusion of three major feature maps. Finally,taking the best definition of the multi-feature fusion image as the reference,the frames whose fusion maps can pop out the objects best are selected as key frames. Experiment shows that for a series of vehicle images in the surveillance video,the algorithm presented effectively selects the most abundant image of vehicle,realizing effective compression of vehicle data for road vehicle surveillance.
引文
[1] 朱映映,周洞汝.一种从压缩视频流中提取关键帧的方法[J].计算机工程与应用,2003,39(18):13-14.
[2] 蒋鹏,秦小麟.基于视觉注意模型的自适应视频关键帧提取[J].中国图象图形学报,2009,14(8):1650-1655.
[3] 刘桂清.视频摘要技术的研究与实现[D].长沙:国防科学技术大学,2004.
[4] EJAZ N,MEHMOOD I,SAJJAD M,et al.Video summarization by employing visual saliency in a sufficient content change method[J].International Journal of Computer Theory & Engineering,2014,6(1):26-29.
[5] 袁晶,王炜,杨建,等.一种道路车辆监控视频中的关键帧提取方法[J].计算机工程,2014,40(12):282-286.
[6] 蓝章礼,帅丹,李益才.基于相关系数的道路监控视频关键帧提取算法[J].重庆交通大学学报:自然科学版,2016,35(1):129-133.
[7] LAI Jieling,YI Yang.Key frame extraction based on visual attention model[J].Journal of Visual Communication & Image Representation,2012,23:114-125.
[8] 刘云鹏,张三元,王仁芳,等.视觉注意模型的道路监控视频关键帧提取[J].中国图象图形学报,2013,18(8):933-943.
[9] 王丽娟.基于OpenCV与混合高斯建模的运动目标检测[J].电子测试,2009(9):86-90.
[10] LI Yibo,SHEN Xiaoling,BEI Shanshan.Real-time tracking method for moving target based on an improved Camshift algorithm[C]//International conference on mechatronic science,electric engineering and computer.Jilin,China:IEEE,2011:978-981.
[11] GAO H,XUE P,LIN W.A new marker-based watershed algorithm[C]//Proceedings of international symposium on circuits and systems.[s.l.]:[s.n.],2006.
[12] 宋克臣,颜云辉,陈文辉,等.局部二值模式方法研究与展望[J].自动化学报,2013,39(6):730-744.
[13] ACHANTA R,HEMAMI S,ESTRADA F,et al.Frequency-tuned salient region detection[C]//IEEE conference on computer vision and pattern recognition.Miami,FL,USA:IEEE,2009:1597-1604.
[14] ZHANG Dandan,ZHAO Shuang.An improved edge detection algorithm based on canny operator[J].Applied Mechanics & Materials,2011,347-350:3541-3545.
[2] 蒋鹏,秦小麟.基于视觉注意模型的自适应视频关键帧提取[J].中国图象图形学报,2009,14(8):1650-1655.
[3] 刘桂清.视频摘要技术的研究与实现[D].长沙:国防科学技术大学,2004.
[4] EJAZ N,MEHMOOD I,SAJJAD M,et al.Video summarization by employing visual saliency in a sufficient content change method[J].International Journal of Computer Theory & Engineering,2014,6(1):26-29.
[5] 袁晶,王炜,杨建,等.一种道路车辆监控视频中的关键帧提取方法[J].计算机工程,2014,40(12):282-286.
[6] 蓝章礼,帅丹,李益才.基于相关系数的道路监控视频关键帧提取算法[J].重庆交通大学学报:自然科学版,2016,35(1):129-133.
[7] LAI Jieling,YI Yang.Key frame extraction based on visual attention model[J].Journal of Visual Communication & Image Representation,2012,23:114-125.
[8] 刘云鹏,张三元,王仁芳,等.视觉注意模型的道路监控视频关键帧提取[J].中国图象图形学报,2013,18(8):933-943.
[9] 王丽娟.基于OpenCV与混合高斯建模的运动目标检测[J].电子测试,2009(9):86-90.
[10] LI Yibo,SHEN Xiaoling,BEI Shanshan.Real-time tracking method for moving target based on an improved Camshift algorithm[C]//International conference on mechatronic science,electric engineering and computer.Jilin,China:IEEE,2011:978-981.
[11] GAO H,XUE P,LIN W.A new marker-based watershed algorithm[C]//Proceedings of international symposium on circuits and systems.[s.l.]:[s.n.],2006.
[12] 宋克臣,颜云辉,陈文辉,等.局部二值模式方法研究与展望[J].自动化学报,2013,39(6):730-744.
[13] ACHANTA R,HEMAMI S,ESTRADA F,et al.Frequency-tuned salient region detection[C]//IEEE conference on computer vision and pattern recognition.Miami,FL,USA:IEEE,2009:1597-1604.
[14] ZHANG Dandan,ZHAO Shuang.An improved edge detection algorithm based on canny operator[J].Applied Mechanics & Materials,2011,347-350:3541-3545.