Underwater Visual Localization Using Machine Learning and LSTM: Method

We implement two different architectures. The first uses pretrained deep convolutional neural networks (DCNN) to extract features from the input images. The second architecture adds an additional LSTM layer between the DCNN and affine regressor to perform dimensionality reduction by assessing the spatial structure of the image.


This content originally appeared on HackerNoon and was authored by PoseNet

:::info Authors:

(1) Luyuan Peng, Acoustic Research Laboratory, National University of Singapore;

(2) Hari Vishnu, Acoustic Research Laboratory, National University of Singapore;

(3) Mandar Chitre, Acoustic Research Laboratory, National University of Singapore;

(4) Yuen Min Too, Acoustic Research Laboratory, National University of Singapore;

(5) Bharath Kalyan, Acoustic Research Laboratory, National University of Singapore;

(6) Rajat Mishra, Acoustic Research Laboratory, National University of Singapore.

:::

I Introduction

II Method

III Datasets

IV Experiments, Acknowledgment, and References

II. METHOD

\ Fig. 1. Neural network architecture overview.

\ We implement two different architectures. The first uses pretrained deep convolutional neural networks (DCNN) to extract features from the input images. The resulting feature map is then passed to an affine regressor consisting of dense neural layers to output a 7-dimensional pose vector estimates. The second architecture adds an additional LSTM layer between the DCNN and affine regressor to perform dimensionality reduction by assessing the spatial structure of the image. This is done by four LSTMs which parse the DCNN-output feature map in different directions starting at each of the four image corners to process the spatial trends, and compress it into lower-dimensional information which is easier processed by the affine regressor.

\ The input images used in the training are rescaled to 256×256 pixels before cropping into a 224×224 feature input using centre cropping. To speed up training, the images are normalized by the mean and standard deviation of the images. The poses are also normalized to lie within [-1, 1].

\ Fig. 2. Example images from our underwater tank datasets.

\ Fig. 3. Overview of simulated scene in underwater simulator (top) and the simulated image captured by the ROV (bottom).

\

:::info This paper is available on arxiv under CC BY 4.0 DEED license.

:::

\


This content originally appeared on HackerNoon and was authored by PoseNet


Print Share Comment Cite Upload Translate Updates
APA

PoseNet | Sciencx (2024-07-17T16:00:18+00:00) Underwater Visual Localization Using Machine Learning and LSTM: Method. Retrieved from https://www.scien.cx/2024/07/17/underwater-visual-localization-using-machine-learning-and-lstm-method/

MLA
" » Underwater Visual Localization Using Machine Learning and LSTM: Method." PoseNet | Sciencx - Wednesday July 17, 2024, https://www.scien.cx/2024/07/17/underwater-visual-localization-using-machine-learning-and-lstm-method/
HARVARD
PoseNet | Sciencx Wednesday July 17, 2024 » Underwater Visual Localization Using Machine Learning and LSTM: Method., viewed ,<https://www.scien.cx/2024/07/17/underwater-visual-localization-using-machine-learning-and-lstm-method/>
VANCOUVER
PoseNet | Sciencx - » Underwater Visual Localization Using Machine Learning and LSTM: Method. [Internet]. [Accessed ]. Available from: https://www.scien.cx/2024/07/17/underwater-visual-localization-using-machine-learning-and-lstm-method/
CHICAGO
" » Underwater Visual Localization Using Machine Learning and LSTM: Method." PoseNet | Sciencx - Accessed . https://www.scien.cx/2024/07/17/underwater-visual-localization-using-machine-learning-and-lstm-method/
IEEE
" » Underwater Visual Localization Using Machine Learning and LSTM: Method." PoseNet | Sciencx [Online]. Available: https://www.scien.cx/2024/07/17/underwater-visual-localization-using-machine-learning-and-lstm-method/. [Accessed: ]
rf:citation
» Underwater Visual Localization Using Machine Learning and LSTM: Method | PoseNet | Sciencx | https://www.scien.cx/2024/07/17/underwater-visual-localization-using-machine-learning-and-lstm-method/ |

Please log in to upload a file.




There are no updates yet.
Click the Upload button above to add an update.

You must be logged in to translate posts. Please log in or register.