One-step Local Feature Extraction using CNN
作者： Yunpeng Zhou , Zhangqing Zhu , Bo Xin
DOI: 10.1109/ICNSC48988.2020.9238094
关键词: Feature matching 、 Process (computing) 、 Feature extraction 、 Artificial intelligence 、 Feature (computer vision) 、 Computer science 、 Convolutional neural network 、 Structure from motion 、 Differentiable function 、 Detector 、 Pattern recognition
摘要: We propose a one-step Local Feature Extraction Network framework to solve the sparse feature matching problem. In our network, we use raw camera data and Structure from Motion (SfM) algorithm restore corresponding relationships of different map. Our network combines detector descriptor as one step build an end-to-end network. At same time, whole process is differentiable train by loss Finally, on indoor datasets prove its accuracy rapidity advantage over other methods.
sci-hub.st 参考文章(20)
Jan Stühmer, Stefan Gumhold, Daniel Cremers, Real-time dense geometry from a handheld camera dagm conference on pattern recognition. pp. 11- 20 ,(2010) , 10.1007/978-3-642-15986-2_2
Diederik P. Kingma, Jimmy Ba, Adam: A Method for Stochastic Optimization arXiv: Learning. ,(2014)
Peter Henry, Michael Krainin, Evan Herbst, Xiaofeng Ren, Dieter Fox, RGB-D mapping: Using Kinect-style depth cameras for dense 3D modeling of indoor environments The International Journal of Robotics Research. ,vol. 31, pp. 647- 663 ,(2012) , 10.1177/0278364911434148
A. Alahi, R. Ortiz, P. Vandergheynst, FREAK: Fast Retina Keypoint computer vision and pattern recognition. pp. 510- 517 ,(2012) , 10.1109/CVPR.2012.6247715
Ethan Rublee, Vincent Rabaud, Kurt Konolige, Gary Bradski, ORB: An efficient alternative to SIFT or SURF international conference on computer vision. pp. 2564- 2571 ,(2011) , 10.1109/ICCV.2011.6126544
Herbert Bay, Andreas Ess, Tinne Tuytelaars, Luc Van Gool, Speeded-Up Robust Features (SURF) Computer Vision and Image Understanding. ,vol. 110, pp. 346- 359 ,(2008) , 10.1016/J.CVIU.2007.09.014
David G. Lowe, Distinctive Image Features from Scale-Invariant Keypoints International Journal of Computer Vision. ,vol. 60, pp. 91- 110 ,(2004) , 10.1023/B:VISI.0000029664.99615.94
N. Dalal, B. Triggs, Histograms of oriented gradients for human detection computer vision and pattern recognition. ,vol. 1, pp. 886- 893 ,(2005) , 10.1109/CVPR.2005.177
K. Mikolajczyk, C. Schmid, A performance evaluation of local descriptors IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 27, pp. 1615- 1630 ,(2005) , 10.1109/TPAMI.2005.188
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Deep Residual Learning for Image Recognition computer vision and pattern recognition. pp. 770- 778 ,(2016) , 10.1109/CVPR.2016.90