Underwater high-precision panoramic 3D image generation

Author(s):  
Zhaolun Li ◽  
Rushi Lan ◽  
Zhuo Chen ◽  
Xiaonan Luo ◽  
Ji Li ◽  
...  
2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Yun Shi ◽  
Cong Tao ◽  
Xiaoping Wang ◽  
Liyan Zhang

The application of artificial intelligence and deep learning in the fields of wireless communication, image and speech recognition, and 3D reconstruction has successfully solved some difficult modeling problems. This paper focuses on the high-precision 3D reconstruction of the motion-blurred cooperative markers, including the Chinese character coded targets (CCTs) and the noncoded circular markers. A simulation-based motion-blurred image generation model is constructed to provide sufficient samples for training the convolutional neural network to identify and match the motion-blurred CCTs on the moving object. The blurred noncoded marker matching is performed through homography. The 3D reconstruction of the markers is realized via the optimization of the spatial moving path within the exposure period. The midpoint of the moving path of the markers is taken as the final reconstruction result. The experimental results show that the 3D reconstruction accuracy of the markers with a certain motion blur effect is about 0.08 mm.


2021 ◽  
Vol 161 ◽  
pp. S221-S222
Author(s):  
M. Boucsein ◽  
J. Müller ◽  
T. Suckert ◽  
E. Beyreuther ◽  
M. Alber ◽  
...  

2018 ◽  
Vol 72 (1) ◽  
pp. 253-254 ◽  
Author(s):  
Xiuqiang Jiang ◽  
Shuang Li ◽  
Long Gu ◽  
Jun Sun ◽  
Dongdong Xiao

2005 ◽  
Vol 76 ◽  
pp. S31
Author(s):  
C. Eccles ◽  
M. Hawkins ◽  
J-P. Bissonnette ◽  
D. Moseley ◽  
K. Brock ◽  
...  

2018 ◽  
Vol 72 (1) ◽  
pp. 229-252 ◽  
Author(s):  
Xiuqiang Jiang ◽  
Shuang Li ◽  
Long Gu ◽  
Jun Sun ◽  
Dongdong Xiao

A high-precision line-of-sight extraction technique is essential for autonomous optical navigation during the Mars approach phase. To support future Mars exploration missions, an optical image simulation system is a necessary ground verification facility for Mars image generation and line-of-sight extraction algorithm tests. In this paper, an optical image generation procedure is first developed according to projection relationships, reference flight profiles and camera parameters. Next, a hybrid image processing and subpixel-level line-of-sight extraction algorithm is proposed through modification of moment-based sub-pixel edge detection and improvement of direct least-square fitting approaches. Finally, an optical image simulation system is established, and the experimental results show that the proposed procedure can effectively simulate the optical image in the field-of-view of a Mars spacecraft, and the hybrid extraction algorithm can obtain high-precision Mars centroid information.


Sign in / Sign up

Export Citation Format

Share Document