Inter-vehicle distance detection based on keypoint matching for stereo images

2017 ◽  
Author(s):  
Yoshihiro Shima
Keyword(s):  
Stereo Images ◽  
Keypoint Matching

Stereo imaging in the shadow electron microscope

1978 ◽  
Vol 36 (1) ◽  
pp. 120-121
Author(s):  
W. C. T. Dowell
Keyword(s):  
Electron Microscopy ◽  
Electron Microscope ◽  
Convenient Method ◽  
Patent Application ◽  
Standard Technique ◽  
Stereo Imaging ◽  
Stereo Images ◽  
Specimen Height

Stereo imaging is not new to electron microscopy. Von Ardenne, who first published transmission pairs nearly forty hears ago, himself refers to a patent application by Ruska in 1934. In the early days of the electron microscope von Ardenne employed a pair of magnetic lenses to view untilted specimens but soon opted for the now standard technique of tilting the specimen with respect to the beam.In the shadow electron microscope stereo images can, of course, be obtained by tilting the specimen between micrographs. This obvious method suffers from the disadvantage that the magnification is very sensitive to small changes in specimen height which accompany tilting in the less sophisticated stages and it is also time consuming. A more convenient method is provided by horizontally displacing the specimen between micrographs. The specimen is not tilted and the technique is both simple and rapid, stereo pairs being obtained in less than thirty seconds.

scholarly journals Learning Collision-Free Space Detection from Stereo Images: Homography Matrix Brings Better Data Augmentation

2021 ◽  
pp. 1-1
Author(s):  
Rui Fan ◽  
Hengli Wang ◽  
Peide Cai ◽  
Jin Wu ◽  
Junaid Bocus ◽  
...  
Keyword(s):  
Free Space ◽  
Data Augmentation ◽  
Stereo Images

scholarly journals Matching Large Baseline Oblique Stereo Images Using an End-to-End Convolutional Neural Network

2021 ◽  
Vol 13 (2) ◽  
pp. 274
Author(s):  
Guobiao Yao ◽  
Alper Yilmaz ◽  
Li Zhang ◽  
Fei Meng ◽  
Haibin Ai ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Stereo Matching ◽  
Least Square ◽  
Affine Invariant ◽  
Stereo Images ◽  
Distance Ratio ◽  
Matching Algorithm ◽  
End To End

The available stereo matching algorithms produce large number of false positive matches or only produce a few true-positives across oblique stereo images with large baseline. This undesired result happens due to the complex perspective deformation and radiometric distortion across the images. To address this problem, we propose a novel affine invariant feature matching algorithm with subpixel accuracy based on an end-to-end convolutional neural network (CNN). In our method, we adopt and modify a Hessian affine network, which we refer to as IHesAffNet, to obtain affine invariant Hessian regions using deep learning framework. To improve the correlation between corresponding features, we introduce an empirical weighted loss function (EWLF) based on the negative samples using K nearest neighbors, and then generate deep learning-based descriptors with high discrimination that is realized with our multiple hard network structure (MTHardNets). Following this step, the conjugate features are produced by using the Euclidean distance ratio as the matching metric, and the accuracy of matches are optimized through the deep learning transform based least square matching (DLT-LSM). Finally, experiments on Large baseline oblique stereo images acquired by ground close-range and unmanned aerial vehicle (UAV) verify the effectiveness of the proposed approach, and comprehensive comparisons demonstrate that our matching algorithm outperforms the state-of-art methods in terms of accuracy, distribution and correct ratio. The main contributions of this article are: (i) our proposed MTHardNets can generate high quality descriptors; and (ii) the IHesAffNet can produce substantial affine invariant corresponding features with reliable transform parameters.

Sign in / Sign up

Export Citation Format

Share Document