一种快速有效的机载目标识别算法

计算机科学 ›› 2014, Vol. 41 ›› Issue (Z6): 150-152.

一种快速有效的机载目标识别算法

潘铭星,孙涵

南京航空航天大学计算机科学与技术学院南京210016;南京航空航天大学计算机科学与技术学院南京210016

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受国家自然科学基金(61203246),江苏省“青蓝工程”,南京航空航天大学基本科研业务费(NZ2013002)资助

Fast and Efficient Algorithm for Airborne Target Recognition

PAN Ming-xing and SUN Han

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 针对机载三维运动、复杂场景下特定目标识别困难的问题,提出了一种快速有效的算法。先采用基于颜色的目标检测技术,快速实现目标兴趣区域的粗定位；然后根据链码跟踪方法提取兴趣区域的特征；再根据样本视频总结归纳出的决策规则对兴趣区域的特征进行判断；最终实现特定目标的识别。实验表明,新算法速度快,实用性强,适合实时处理。

关键词: 兴趣区域,链码,特征值,决策树,无人机中图法分类号TP391.4文献标识码A

Abstract: Because the target recognition is very difficult under the complex scene and with 3D motion of airplane,a fast and efficient algorithm was proposed．First using a color-based object detection method,the coarse positions of region of interest(ROI) are achieved quickly．Then the features of ROI are extracted according to chain code tracing method．And then the decision rules for special targets are concluded based on sample video,and are used to judge whether each ROI is the true target．Finally the recognition for special targets detection is realized．Experiments also show that the new algorithm is fast,practical and suitable for real-time processing.

Key words: Region of interest,Chain code,feature,Decision tree,UAV

潘铭星,孙涵. 一种快速有效的机载目标识别算法[J]. 计算机科学, 2014, 41(Z6): 150-152. https://doi.org/

PAN Ming-xing and SUN Han. Fast and Efficient Algorithm for Airborne Target Recognition[J]. Computer Science, 2014, 41(Z6): 150-152. https://doi.org/

参考文献

[1] Barnich O,Van Droogenbroeck M．ViBe:a powerful randomtechnique to estimate the background in video sequences[C]∥IEEE International Conference on．Acoustics,Speech and Signal Processing．2009:945-948
[2] Barnich O,Van Droogenbroeck M．ViBe:A universal back-ground subtraction algorithm for video sequences[J]．IEEE Transactions on,Image Processing,2011,20(6):1709-1724
[3] Lin F,Dong X,Chen B M,et al．A robust real-time embedded vision system on an unmanned rotorcraft for ground target following[J]．IEEE Transactions on Industrial Electronics,2012,59(2):1038-1049
[4] Conte G,Doherty P．An integrated UAV navigation systembased on aerial image matching[C]∥Aerospace Conference,IEEE．2008:1-10
[5] Liu Yong-Kui．Research on the compression algorithm for Freeman chain code[J]．Chinese Journal of Computers,2001,24(12):1294-1298
[6] Ren Ming-Wu,Yang J,Sun Han．A New Contour Filling Algorithm Based on Chain Codes Description[J]．Journal of Image and Graphics,2001,6(4):348-522
[7] Kim H S,Kim J H．A two-step circle detection algorithm from the intersecting chords[J]．Pattern recognition letters,2001,22(6):787-798
[8] Ballard D H．Generalizing the Hough transform to detect arbitrary shapes[J]．Pattern recognition,1981,13(2):111-122
[9] Lei Xu,Oja E,Kultanen P．A new curve detection method:randomized Hough transform(RHT)[J]．Pattern recognition letters,1990,11(5):331-338
[10] Duda R O,Hart P E．Use of the Hough transformation to detect lines and curves in pictures[J]．Communications of the ACM,1972,15(1):11-15
[11] Kaaniche K,Champion B,Pégard C,et al．A vision algorithm for dynamic detection of moving vehicles with a UAV[C]∥Proceedings of the 2005IEEE International Conference on Robotics and Automation．ICRA．2005:1878-1883
[12] Conte G,Doherty P．An integrated UAV navigation systembased on aerial image matching[C]∥Aerospace Conference,2008IEEE．2008:1-10
[13] Cesetti A,Frontoni E,Mancini A,et al．A vision-based guidance system for UAV navigation and safe landing using natural landmarks[C]∥Selected papers from the 2nd International Symposium on UAVs,Reno,Nevada,USA 2009．Springer Netherlands,2010:233-257

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed