sum1lim / sea_ice_remote_sensing Goto Github PK

Deep Learning models for Sea Ice Concentration classification generated from the architectures of Neural Network, 1D-CNN and concatenation of the two.

Python 96.88% Shell 2.29% Batchfile 0.82%

classification deep-learning machine-learning remote-sensing satellite-imagery

sea_ice_remote_sensing's People

Contributors

Stargazers

Watchers

Forkers

omarkawach xyt556

sea_ice_remote_sensing's Issues

Extract train and test data form different images

Currently, create-dataset script extracts data relying solely on randomness, thus train and test data can share the same source images. However, this does not allow us to test the accuracy fairly since the resulting model can be biased or overfitted on the features that indicate what image a sample came from. To solve this, test data should be extracted from the images that are not used for creating the training dataset.

Data normalization requires standard data

Except for the training data, normalization should have standard min & max values instead of calculating such values within the dataset. The standard values are usually from the training dataset.

object based feature extraction

Using the SOBEL edge detection, segment images into objects and extract features per each object.

extract coordinates of patch locations (x, y)

Add padding to feature sequences for 1D CNN

Add padding at the end of the feature sequences "to involve every possible combination into convolution" [1].

[1] R. Kestur, S. Farooq, R. Abdal, E. Mehraj, O. Narasipura, and M. Mudigere, “UFCN: a fully convolutional neural network for road extraction in RGB imagery acquired by remote sensing from an unmanned aerial vehicle,” Journal of Applied Remote Sensing, vol. 12, no. 01, p. 1, 2018.

neural network for multi-class classification

Define a strategy for pixel-based sea ice classification using neural network

Expert data statistics

The expert data are provided in the mask directory of the provided dataset. Add functionality to generate the data distribution statistics. csv output preferred. Refrer to https://github.com/asylve/Sea-Ice

Resolve command not found in Windows

After the package installation, python scripts are supposed to run as a command instead of python path/to/script, but Windows cannot find the commands. Find an ideal installation strategy for the Windows environment.

Add metadata attributes after convolution layers

Enable CNN script to add additional attributes to the convolution layers, which might improve the performance of the model.

Add pixel value thresholding functionality

Thresholding is important for object segmentation and extracting other stuff. Implement a strategy to accomplish this.

GLCM correlation

Add GLCM correlation features to the dataset.

K-fold K=5

For reliable results, perform K-fold validation with K=10 [1].

[1] P. Refaeilzadeh, L. Tang, and H. Liu, “Cross-Validation,” Encyclopedia of Database Systems, pp. 532–538, 2009.

pixel based feature extraction

Features for machine learning should be extracted for each sample pixel. Derive a strategy for the extraction. Suggested features: RGB bands, year, month, day, AOI location, etc.

1D CNN

GLCM features do not work well with the regular neural network and degrade the performance of the model. It is suspected that the addition of the features makes the network too complicated, which prevents finding the global minimum of the loss function. Write a script for a 1D convolutional neural network as a potential solution.