基于改进SIFT的高鲁棒性特征点提取方法

Abstract

Abstract:

In order to extract high robust keypoints for the cognitive navigation of unmanned combat aerial vehicle (UCAV), a method named multi-quantifying Hessian-Affine iterative scale invariant feature transform (SIFT) with adaptive non-maximum suppression (ANMS) is proposed. Considering the demand of well-distributed keypoints, an optimization arithmetic based on ANMS is first presented to choose the keypoints. In order to ensure the chosen keypoints’ affine invariant property, a Hessian-Affine iterative arithmetic with an iterative adjusting factor is used to estimate the affine invariant regions, and then the main orientation assignment and cycle descriptor are further realized in the corresponding normalized cycle regions. In view of the deficiencies of analog feature vectors in balanced distribution and correct matching score, a method combining the multiple value quantization and reshaping operation is presented to quantify the analog feature vectors. The analysis and simulation results verify this quantifying method as having better properties. Simulation results prove that the method proposed in this paper has higher correct matching score. It is invariant to image rotation and scaling. It can improve the anti-noise property by over 10 dB, and it possesses robust affine invariant property within a large visual angle range.

Key words: cognitive navigation, iterative SIFT, affine invariant, quantization, adaptive non-maximum suppression

CLC Number:

V279

TAI Nengjian, WU Dewei, QI Junyi. A Method to Extract High Robust Keypoints Based on Improved SIFT[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2012, 33(12): 2313-2321.

References

[1] Wu D W, Tai N J, Qi J Y. A new research progress of UCAV intelligent navigation based on cognitive theory. Journal of Air Force Engineering University: Natural Science Edition, 2011, 12(4): 52-57. (in Chinese) 吴德伟, 邰能建, 戚君宜. 基于认知理论的UCAV智能导航研究新进展. 空军工程大学学报: 自然科学版, 2011, 12(4): 52-57.

[2] Cuperlier N, Quoy M, Gaussier P. Neurobiologically inspired mobile robot navigation and planning. Frontiers in Neurorobotics, 2007, 1: 1-15.

[3] Giovannangeli C, Gaussier P, Banquet J P. Robustness of visual place cells in dynamic indoor and outdoor environment. International Journal of Advanced Robotic Systems, 2006, 3(2): 115-124.

[4] Giovannangeli C, Gaussier P. Interactive teaching for vision-based mobile robots: a sensory-motor approach. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, 2010, 40(1): 13-28.

[5] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630.

[6] Lowe D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004, 60(2): 91-110.

[7] Tamimi H, Andreasson H, Treptow A, et al. Localization of mobile robots with omnidirectional vision using particle filter and iterative SIFT. Robotics and Autonomous Systems, 2006, 54(9): 758-765.

[8] Song R, Szymanski J. Well-distributed SIFT features. Electronics Letters, 2009, 45(6): 308-310.

[9] Lindeberg T. Scale-space theory: a basic tool for analysing structures at different scales. Journal of Applied Statistics, 1994, 21(2): 224-270.

[10] Brown M, Szeliski R, Winder S. Multi-image matching using multi-scale oriented patches. Conference on Computer Vision and Pattern Recognition, 2005: 510-517.

[11] Lindeberg T, Garding J. Shape-adapted smoothing in estimation of 3-D shape cues from affine deformations of local 2-D brightness structure. Image and Vision Computing, 1997, 15(6): 415-434.

[12] Mikolajczyk K, Schmid C. Scale & affine invariant interest point detectors. International Journal of Computer Vision, 2004, 60(1): 63-86.

[13] Cui C H, Ngan K N. Scale-and affine-invariant fan feature. IEEE Transactions on Image Processing, 2011, 20(6): 1627-1640.

[14] Zhang L, Wang H L, Wu R B. Matching of interesting points based on improved SIFT algorithm. Journal of Electronics & Information Technology, 2009, 31(11): 2620-2625. (in Chinese) 张良, 王海丽, 吴仁彪. 基于改进局部不变特征的兴趣点匹配. 电子与信息学报, 2009, 31(11): 2620-2625.

[15] Peng S H, Kim D K, Lee S L, et al. A visual shape descriptor using sectors and shape context of contour lines. Information Sciences, 2010, 180(16): 2925-2939.

[16] Tai N J, Wu D W, Wu J. Design of wide-gap chaos modulation hopping pattern based on TOD. Journal of Beijing University of Posts and Telecommunications, 2009, 32(6): 77-82. (in Chinese) 邰能建, 吴德伟, 吴杰. TOD宽间隔混沌调制跳变图案设计. 北京邮电大学学报, 2009, 32(6): 77-82.

A Method to Extract High Robust Keypoints Based on Improved SIFT

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 6

Recommended Articles

Metrics

Comments

[1]	Hongzhu ZHANG, Dong YE, Zhaowei SUN. Predefined-time integrated pose control for spacecraft under input quantization [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(22): 328558-328558.
[2]	DING Wenrui, LIU Chunlei, LI Yue, ZHANG Baochang. Binary convolutional neural network: Review [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(6): 24504-024504.
[3]	YANG Yin, SHENG Weixing, HAN Yubing, MA Xiaofeng. Shaped-beam pattern synthesis based on quantization of element excitation amplitude [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2018, 39(4): 321653-321653.
[4]	ZENG Shang-chun;ZHU Zhao-da. A Novel Algorithm for SAR Raw Data Compression [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2007, 28(4): 959-963.
[5]	GUAN Zhen-hong;ZHU Zhao-da;ZHU Dai-yin. Compression of SAR Raw Data by Block Adaptive Spherical Vector Quantization [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2006, 27(1): 82-86.
[6]	LIAN Jun-xiang;HU De-wen;HU Xiao-ping;WU Wen-qi. Research on Coning Error and Quantization Error of SINS Attitude Algorithm [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2006, 27(1): 98-103.