基于快速尺度空间的无人机影像自适应稳像方法
|
摘要
为实现无人机航拍影像的实时稳像,针对稳像过程中特征检测的速度问题和运动滤波的发散现象,提出了一种改进的AGAST算法与自适应Kalman滤波相结合的实时稳像算法。对于无人机实时航拍视频序列,以当前帧的前一帧为基准进行稳像处理。改进的AGAST特征检测算法在尺度空间的基础上快速提取AGAST角点特征,用二进制描述符对其进行描述,然后用汉明距离匹配特征点。对于已获得的匹配特征点对集合,用RANSAC原则剔除误匹配点,再计算运动矢量。最后使用自适应Kalman滤波提取出运动矢量中的无人机主动扫描分量,进行运动补偿,获得稳像结果。实验数据使用标准测试图集和自己采集的无人机航拍视频,实验结果表明,所提算法在连续视频序列处理时效果显著、速度快,能够满足实时稳像的需求。
In order to realize the real-time image stabilization of the UAV aerial image and solve the problem of slow speed in feature detection and the divergence in motion filtering during the process of image stabilization,a real-time image stabilization algorithm is proposed combining the improved AGAST( Adaptive and Generic corner detection based on the Accelerated Segment Test) algorithm with the adaptive Kalman filter. For the real-time aerial video sequences, the image stabilization processing is based on the frame prior to the current frame. The improved AGAST feature detection algorithm rapidly extracts the features of AGAST corners on the basis of scale space, which are described by binary descriptors, and then the feature points are matched by using Hamming distance. For the matched sets of point pairs, the RANSAC principle is used to eliminate the mismatched points and then the motion vector is calculated. Finally, the adaptive Kalman filter is used to extract the active scanning component of the UAV in the motion vector, which performs motion compensation to obtain the result of image stabilization. The standard test atlases and the UAV aerial video collected by researchers serve as the experimental data. The experimental results show that the proposed algorithm is effective and fast in the processing of the continuous video sequence, and can meet the needs of real-time image stabilization.
In order to realize the real-time image stabilization of the UAV aerial image and solve the problem of slow speed in feature detection and the divergence in motion filtering during the process of image stabilization,a real-time image stabilization algorithm is proposed combining the improved AGAST( Adaptive and Generic corner detection based on the Accelerated Segment Test) algorithm with the adaptive Kalman filter. For the real-time aerial video sequences, the image stabilization processing is based on the frame prior to the current frame. The improved AGAST feature detection algorithm rapidly extracts the features of AGAST corners on the basis of scale space, which are described by binary descriptors, and then the feature points are matched by using Hamming distance. For the matched sets of point pairs, the RANSAC principle is used to eliminate the mismatched points and then the motion vector is calculated. Finally, the adaptive Kalman filter is used to extract the active scanning component of the UAV in the motion vector, which performs motion compensation to obtain the result of image stabilization. The standard test atlases and the UAV aerial video collected by researchers serve as the experimental data. The experimental results show that the proposed algorithm is effective and fast in the processing of the continuous video sequence, and can meet the needs of real-time image stabilization.
引文
[1] HOSSEIN-NEJAD Z,NASRI M. Image registration based on SIFT features and adaptive RANSAC transform[C]//International Conference on Communication and Signal Processing,2016. doi:10. 1109/ICCSP. 2016. 7754318.
[2] YANG Q.Real-time optical and digital image stabilization for adaptive optics scanning ophthalmoscopy:US,20150077706[P]. 2015-03-19.
[3] KIM S W,YIN S,YUN K,et al. Spatio-temporal weighting in local patches for direct estimation of camera motion in video stabilization[J]. Computer Vision&Image Understanding,2014,118(3):71-83.
[4]吕高杰,张国华,车宏.电子稳像算法精度评价方法研究[J].电光与控制,2011,18(3):76-79.
[5] DONG J,XIA Y,YU Q,et al. Instantaneous video stabilization for unmanned aerial vehicles[J]. Journal of Electronic Imaging,2014. doi:10. 1117/1. JEI. 23. 1. 013002.
[6]袁威,高跃清,吴金亮.基于灰度投影和块匹配的无人机视频稳像方法[J].无线电工程,2016,46(2):19-22.
[7] KIM P J,LEE K H,YOON Y K. Image stabilization method and electronic device therefor:US,20150062410A1[P]. 2015-03-05.
[8]张增,张巍,伍小洁,等.一种适用于电子稳像的图像补偿方法[J].光学与光电技术,2015,13(6):54-57.
[9] WALHA A,WALI A,ALIMI A M. Video stabilization for aerial video surveillance[J]. AASRI Procedia,2013,4:72-77.
[10] LEE T H,LEE Y G,SONG B C. Fast 3D video stabilization using ROI-based warping[J]. Journal of Visual Communication&Image Representation,2014,25(5):943-950.
[11]贾鹤鸣,杨泽文,宋文龙.基于中心差分卡尔曼滤波的初始对准方法研究[J].森林工程,2016,32(6):66-70.
[12]赵峰.基于无人机影像的景象匹配系统设计与实现[D].沈阳:东北大学,2010.
[13] JIANG W T,CHEN W D,LIANG F L I. Electronic image stabilization algorithm based on characteristic point tracking[J]. Journal of Applied Optics,2010,31(1):73-77.
[14] XU Z,LIU Y,MEI L,et al. Semantic based representing and organizing surveillance big data using video structural description technology[J]. Journal of Systems&Software,2015,102:217-225.
[15] ABDOU S. Devices and methods for minimally invasive spinal stablization and instrumentation:US,8764806[P].2014-01-07.
[2] YANG Q.Real-time optical and digital image stabilization for adaptive optics scanning ophthalmoscopy:US,20150077706[P]. 2015-03-19.
[3] KIM S W,YIN S,YUN K,et al. Spatio-temporal weighting in local patches for direct estimation of camera motion in video stabilization[J]. Computer Vision&Image Understanding,2014,118(3):71-83.
[4]吕高杰,张国华,车宏.电子稳像算法精度评价方法研究[J].电光与控制,2011,18(3):76-79.
[5] DONG J,XIA Y,YU Q,et al. Instantaneous video stabilization for unmanned aerial vehicles[J]. Journal of Electronic Imaging,2014. doi:10. 1117/1. JEI. 23. 1. 013002.
[6]袁威,高跃清,吴金亮.基于灰度投影和块匹配的无人机视频稳像方法[J].无线电工程,2016,46(2):19-22.
[7] KIM P J,LEE K H,YOON Y K. Image stabilization method and electronic device therefor:US,20150062410A1[P]. 2015-03-05.
[8]张增,张巍,伍小洁,等.一种适用于电子稳像的图像补偿方法[J].光学与光电技术,2015,13(6):54-57.
[9] WALHA A,WALI A,ALIMI A M. Video stabilization for aerial video surveillance[J]. AASRI Procedia,2013,4:72-77.
[10] LEE T H,LEE Y G,SONG B C. Fast 3D video stabilization using ROI-based warping[J]. Journal of Visual Communication&Image Representation,2014,25(5):943-950.
[11]贾鹤鸣,杨泽文,宋文龙.基于中心差分卡尔曼滤波的初始对准方法研究[J].森林工程,2016,32(6):66-70.
[12]赵峰.基于无人机影像的景象匹配系统设计与实现[D].沈阳:东北大学,2010.
[13] JIANG W T,CHEN W D,LIANG F L I. Electronic image stabilization algorithm based on characteristic point tracking[J]. Journal of Applied Optics,2010,31(1):73-77.
[14] XU Z,LIU Y,MEI L,et al. Semantic based representing and organizing surveillance big data using video structural description technology[J]. Journal of Systems&Software,2015,102:217-225.
[15] ABDOU S. Devices and methods for minimally invasive spinal stablization and instrumentation:US,8764806[P].2014-01-07.