Research On Sun Shadow Positioning Genetic Algorithm Based On BP Neural Network

DOI

10.2991/ameii-16.2016.275How to use a DOI?

Keywords

Fitting shadow length, Least square fitting, Genetic algorithm based on BP neural network, Global search, Simulated annealing

Abstract

In this paper, the model of the solar shadow end plane coordinates and the measurement of the latitude and longitude, and the measuring time are established. The solution of the video shooting location and date is given by the change of the length of the shadow in the video. And the application of genetic algorithm based on BP neural network to the model error test and evaluation. If there were the date and time in the video, then the angle could be obtained, and the declination angle would be found directly by the relationship between the latitude angle and the dates with the known to rod length. Then because the ratio of is equal to the length of the rod and the shadow length, we can find out high noon sun angle and obtain the latitude and longitude after the fitting of the short film, corresponding to the calculated the noon solar altitude angle. When there was no date and time in the video, then according to the data of the solar shadow vertex coordinates of a fixed straight bar on the horizontal ground, the most suitable place and date of the straight rod is determined. This is an optimization problem, combined with global search and simulated annealing, two methods are listed to solve the objective function.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Ying Xu
PY  - 2016/04
DA  - 2016/04
TI  - Research On Sun Shadow Positioning Genetic Algorithm Based On BP Neural Network
BT  - Proceedings of the 2nd International Conference on Advances in Mechanical Engineering and Industrial Informatics (AMEII 2016)
PB  - Atlantis Press
SN  - 2352-5401
UR  - https://doi.org/10.2991/ameii-16.2016.275
DO  - 10.2991/ameii-16.2016.275
ID  - Xu2016/04
ER  -