无人机飞行目标导航定位图像优化匹配仿真
|
摘要
传统的半全局立体匹配算法很好地兼顾了匹配算法的精确性和实时性,但是算法在处理图像中深度不连续区域误匹配率偏高。针对以上问题,提出了融合快速均值漂移(Fast Mean Shift,FMS)图像分割的无人机(Unmanned Aerial Vehicle,UAV)半全局立体匹配算法。将FMS图像分割算法融合到匹配算法的全局能量函数中,重新构造出更加合理的全局能量函数,解决了因为不同原因造成视差跳跃而赋值同一的惩罚系数的问题。该算法在Middleburry测试平台进行仿真测试以及基于算法进行无人机实景图像实验,结果表明:该算法有效降低了图像在深度视差突变区域的误匹配率,并且能够有效兼顾算法的匹配精度和匹配速度。由此,改进后的算法满足无人机视觉辅助导航的需求。
The traditional semi-global stereo matching algorithm well balances the accuracy and real-time performance of matching algorithm, however, which has a high mismatching rate of the depth discontinuity regions in the image processing. In view of the above problem, the unmanned aerial vehicle(UAV) Semi-global Matching Algorithm through Fusion of Fast Mean Shift(FMS)Image Segmentation is proposed. The FMS image segmentation algorithm was integrated into the global energy function of the matching algorithm to reconstruct a more reasonable global energy function, which solves the problem of assigning the same penalty coefficient for disparity mutations due to different reasons. The simulation test based on the algorithm was carried out on the Middle burry test platform. And based on the proposed algorithm, a real scene image filmed by UAV experiment was conducted. The results show that the algorithm effectively reduces the mismatching rate of the images in the depth disparity mutation regions and balances the matching accuracy and matching speed of the algorithm. Therefore, the improved algorithm can meet the requirements of UAV vision assisted navigation.
The traditional semi-global stereo matching algorithm well balances the accuracy and real-time performance of matching algorithm, however, which has a high mismatching rate of the depth discontinuity regions in the image processing. In view of the above problem, the unmanned aerial vehicle(UAV) Semi-global Matching Algorithm through Fusion of Fast Mean Shift(FMS)Image Segmentation is proposed. The FMS image segmentation algorithm was integrated into the global energy function of the matching algorithm to reconstruct a more reasonable global energy function, which solves the problem of assigning the same penalty coefficient for disparity mutations due to different reasons. The simulation test based on the algorithm was carried out on the Middle burry test platform. And based on the proposed algorithm, a real scene image filmed by UAV experiment was conducted. The results show that the algorithm effectively reduces the mismatching rate of the images in the depth disparity mutation regions and balances the matching accuracy and matching speed of the algorithm. Therefore, the improved algorithm can meet the requirements of UAV vision assisted navigation.
引文
[1] 顾苏杭,陆兵,马正华. 基于轮廓和ASIFT特征的目标检测与跟踪算法[J]. 计算机仿真, 2017,34(6):266-271.
[2] 张黎. 基于立体视觉的三维建筑物重建技术研究[D]. 上海师范大学, 2012.
[3] D Scharstein, R Szeliski. A Taxonomy and Evaluation of Dense Two-frame Stereo Correspondence Algorithms[J]. International Journal of Computer Vision, 2002,47(1): 7-42.
[4] H Hirschmüller. Accurate and Efficient Stereo Processing by Semi-global Matching and Mutual Information[J]. Computer Vision and Pattern Recognition, 2005,2(2): 807-814.
[5] 宁晓斐. 双目立体视觉中半全局立体匹配算法的研究[D]. 辽宁大学, 2014.
[6] 葛忠孝,等. 基于树形结构的半全局立体匹配算法[J]. 计算机工程, 2016,42(8): 243-248.
[7] S Birchfield, C Tomasi. Depth Discontinuities by Pixel-to-pixelStereo[C]. Proceedings of the 6th International Conference on Computer Vision.Washington D.C. USA: IEEE Press, 1998:1073-1080.
[8] 高波,马利庄. 加入结构约束的半全局立体匹配算法[J]. 计算机应用与软件, 2009,26(2):244-247.
[9] 陈智君,等. 区域生长的半全局密集匹配算法[J]. 测绘科学, 2017,42(5):12-16.
[10] 倪伟基,等. 基于色彩分割和自适应窗口的快速立体匹配[J]. 仪器仪表学报, 2011,32(1):194-200.
[11] 赵胜男,王文剑. 一种快速均值漂移图像分割算法[J]. 数据采集与处理, 2015,30(1):192-201.
[12] 殷虎. 基于图像分割的立体匹配算法研究[D]. 南京航空航天大学, 2010.
[13] 盛捷,等. Mean Shift算法优化带宽的自动搜索[J]. 系统仿真学报, 2011,23(12): 2744-2749.
[2] 张黎. 基于立体视觉的三维建筑物重建技术研究[D]. 上海师范大学, 2012.
[3] D Scharstein, R Szeliski. A Taxonomy and Evaluation of Dense Two-frame Stereo Correspondence Algorithms[J]. International Journal of Computer Vision, 2002,47(1): 7-42.
[4] H Hirschmüller. Accurate and Efficient Stereo Processing by Semi-global Matching and Mutual Information[J]. Computer Vision and Pattern Recognition, 2005,2(2): 807-814.
[5] 宁晓斐. 双目立体视觉中半全局立体匹配算法的研究[D]. 辽宁大学, 2014.
[6] 葛忠孝,等. 基于树形结构的半全局立体匹配算法[J]. 计算机工程, 2016,42(8): 243-248.
[7] S Birchfield, C Tomasi. Depth Discontinuities by Pixel-to-pixelStereo[C]. Proceedings of the 6th International Conference on Computer Vision.Washington D.C. USA: IEEE Press, 1998:1073-1080.
[8] 高波,马利庄. 加入结构约束的半全局立体匹配算法[J]. 计算机应用与软件, 2009,26(2):244-247.
[9] 陈智君,等. 区域生长的半全局密集匹配算法[J]. 测绘科学, 2017,42(5):12-16.
[10] 倪伟基,等. 基于色彩分割和自适应窗口的快速立体匹配[J]. 仪器仪表学报, 2011,32(1):194-200.
[11] 赵胜男,王文剑. 一种快速均值漂移图像分割算法[J]. 数据采集与处理, 2015,30(1):192-201.
[12] 殷虎. 基于图像分割的立体匹配算法研究[D]. 南京航空航天大学, 2010.
[13] 盛捷,等. Mean Shift算法优化带宽的自动搜索[J]. 系统仿真学报, 2011,23(12): 2744-2749.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |