感知与规避技术中的入侵目标检测的特征选择
|
摘要
论文针对基于视觉的感知与规避技术中的入侵目标检测,提出了一套稀疏表示框架下的图像特征选择机制。基于稀疏编码和空间金字塔匹配算法(sc-SPM)的低层特征描述子常用的是方向梯度直方图(HOG)特征和尺度不变特征转换(SIFT)特征,而论文通过对在复杂背景下不同天气情况的入侵目标检测结果的查全率(recall)曲线来比较这两种特征描述子性能,最后选择性能最好的特征描述子作为sc-SPM特征提取算法的底层特征。实验结果表明,SIFT特征描述子更能适用于多种不同天气情况并且具有更好的鲁棒性。
In this paper,an image feature selection mechanism under the framework of sparse representation is proposed forintruder detection in vision based on sense and avoid system. Based on the framework of Spatial Pyramid Matching using Sparse Cod-ing,the low-level feature usually adopts the Histogram of Oriented Gradient(HOG)feature descriptor or the Scale-Invariant Fea-ture Transform(SIFT)feature descriptor. In this paper,recall of the intruder detection results is used to compare the HOG featuredescriptor and the SIFT feature descriptor under different weathers with complex background. The best-performing feature descrip-tor is chosen as the low-level feature of sc-SPM method. The experimental results show that the SIFT feature descriptor is more suit-able for a variety of different weathers and has better robustness.
In this paper,an image feature selection mechanism under the framework of sparse representation is proposed forintruder detection in vision based on sense and avoid system. Based on the framework of Spatial Pyramid Matching using Sparse Cod-ing,the low-level feature usually adopts the Histogram of Oriented Gradient(HOG)feature descriptor or the Scale-Invariant Fea-ture Transform(SIFT)feature descriptor. In this paper,recall of the intruder detection results is used to compare the HOG featuredescriptor and the SIFT feature descriptor under different weathers with complex background. The best-performing feature descrip-tor is chosen as the low-level feature of sc-SPM method. The experimental results show that the SIFT feature descriptor is more suit-able for a variety of different weathers and has better robustness.
引文
[1]Yu X,Zhang Y. Sense and avoid technologies with appli-cations to unmanned aircraft systems:Review and pros-pects[J]. Progress in Aerospace Sciences,2015(74):152-166.
[2]Lyu Y,Pan Q,Zhao C,et al. A vision based sense andavoid system for small unmanned helicopter[C]//Un-manned Aircraft Systems(ICUAS),2015 InternationalConference on. IEEE,2015:586-592.
[3]Richard K,Barnhart S,Hottman D. Introduction to un-manned aircraft systems[M]. CRC Press Inc,2011.
[4]Clark M,Kern Z,Prazenica R J. A Vision-Based Propor-tional Navigation Guidance Law for UAS Sense and Avoid[C]//AIAA Guidance,Navigation,and Control Confer-ence,2015:0074.
[5]Zhang Z,Cao Y,Ding M,et al. An intruder detection al-gorithm for vision based sense and avoid system[C]//Un-manned Aircraft Systems(ICUAS),2016 InternationalConference on. IEEE,2016:550-556.
[6]Tomic T,Schmid K,Lutz P,et al. Toward a fully autono-mous UAV:Research platform for indoor and outdoor ur-ban search and rescue[J]. IEEE robotics&automationmagazine,2012,19(3):46-56.
[7] Sahawnehand L R,Beard R W. Chain based CollisionAvoidance for UAV Sense and Avoid System[C]//Presentat AIAA Guidance,Navigation and Control Conf. 2013.
[8]Tan T,Huang Y,Zhang J. Recent progress on object clas-sification and detection[C]//Iberoamerican Congress onPattern Recognition. Springer,Berlin,Heidelberg,2013:1-8.
[9]Felzenszwalb P F,Girshick R B,McAllester D,et al. Ob-ject detection with discriminatively trained part-basedmodels[J]. IEEE transactions on pattern analysis and ma-chine intelligence,2010,32(9):1627-1645.
[10]Zitnick C L,Dollár P. Edge boxes:Locating object pro-posals from edges[C]//European Conference on Comput-er Vision. Springer,Cham,2014:391-405.[11]LoweD G.
[11]DG Lowe. Distinctive image features from scale-invari-ant keypoints[J]. International journal of computer vi-sion,2004,60(2):91-110.
[12]Dalal N,Triggs B. Histograms of oriented gradients for human detection[C]//Computer Vision and Pattern Rec-ognition,2005. CVPR 2005. IEEE Computer SocietyConference on. IEEE,2005(1):886-893.
[13]Yang J,Yu K,Gong Y,et al. Linear spatial pyramidmatching using sparse coding for image classification[C]//Computer Vision and Pattern Recognition,2009.CVPR 2009. IEEE Conference on. IEEE, 2009:1794-1801.
[14]Zhang Z,Cao Y,Ding M,et al. Candidate regions ex-traction of intruder airplane under complex backgroundfor vision-based sense and avoid system[J]. IET Sci-ence,Measurement&Technology,2017.
[15]Liu H,Liu S,Huang T,et al. Infrared spectrum blinddeconvolution algorithm via learned dictionaries andsparse representation[J]. Applied optics, 2016, 55(10):2813-2818.
[16]Borji A,Itti L. State-of-the-art in visual attention mod-eling[J]. IEEE transactions on pattern analysis and ma-chine intelligence,2013,35(1):185-207.
[2]Lyu Y,Pan Q,Zhao C,et al. A vision based sense andavoid system for small unmanned helicopter[C]//Un-manned Aircraft Systems(ICUAS),2015 InternationalConference on. IEEE,2015:586-592.
[3]Richard K,Barnhart S,Hottman D. Introduction to un-manned aircraft systems[M]. CRC Press Inc,2011.
[4]Clark M,Kern Z,Prazenica R J. A Vision-Based Propor-tional Navigation Guidance Law for UAS Sense and Avoid[C]//AIAA Guidance,Navigation,and Control Confer-ence,2015:0074.
[5]Zhang Z,Cao Y,Ding M,et al. An intruder detection al-gorithm for vision based sense and avoid system[C]//Un-manned Aircraft Systems(ICUAS),2016 InternationalConference on. IEEE,2016:550-556.
[6]Tomic T,Schmid K,Lutz P,et al. Toward a fully autono-mous UAV:Research platform for indoor and outdoor ur-ban search and rescue[J]. IEEE robotics&automationmagazine,2012,19(3):46-56.
[7] Sahawnehand L R,Beard R W. Chain based CollisionAvoidance for UAV Sense and Avoid System[C]//Presentat AIAA Guidance,Navigation and Control Conf. 2013.
[8]Tan T,Huang Y,Zhang J. Recent progress on object clas-sification and detection[C]//Iberoamerican Congress onPattern Recognition. Springer,Berlin,Heidelberg,2013:1-8.
[9]Felzenszwalb P F,Girshick R B,McAllester D,et al. Ob-ject detection with discriminatively trained part-basedmodels[J]. IEEE transactions on pattern analysis and ma-chine intelligence,2010,32(9):1627-1645.
[10]Zitnick C L,Dollár P. Edge boxes:Locating object pro-posals from edges[C]//European Conference on Comput-er Vision. Springer,Cham,2014:391-405.[11]LoweD G.
[11]DG Lowe. Distinctive image features from scale-invari-ant keypoints[J]. International journal of computer vi-sion,2004,60(2):91-110.
[12]Dalal N,Triggs B. Histograms of oriented gradients for human detection[C]//Computer Vision and Pattern Rec-ognition,2005. CVPR 2005. IEEE Computer SocietyConference on. IEEE,2005(1):886-893.
[13]Yang J,Yu K,Gong Y,et al. Linear spatial pyramidmatching using sparse coding for image classification[C]//Computer Vision and Pattern Recognition,2009.CVPR 2009. IEEE Conference on. IEEE, 2009:1794-1801.
[14]Zhang Z,Cao Y,Ding M,et al. Candidate regions ex-traction of intruder airplane under complex backgroundfor vision-based sense and avoid system[J]. IET Sci-ence,Measurement&Technology,2017.
[15]Liu H,Liu S,Huang T,et al. Infrared spectrum blinddeconvolution algorithm via learned dictionaries andsparse representation[J]. Applied optics, 2016, 55(10):2813-2818.
[16]Borji A,Itti L. State-of-the-art in visual attention mod-eling[J]. IEEE transactions on pattern analysis and ma-chine intelligence,2013,35(1):185-207.