Diferenzas

Isto amosa as diferenzas entre a revisión seleccionada e a versión actual da páxina.

--- hiperespectral:sae-cd [2018/01/16 17:18] – [Downloads] javier.lopez.fandino
+++ hiperespectral:sae-cd [2018/01/16 17:53] – [Outputs] javier.lopez.fandino
@@ Liña 9: / Liña 9: @@
-===== Downloads =====
+==== Input datasets ====
-=== Input datasets ===
 //All the images are avaiable in Matlab (.mat) format, among others. For further information see the readme in the files.//
@@ Liña 17: / Liña 15: @@
 * [[https://citius.usc.es/investigacion/datasets/hyperspectral-change-detection-dataset|Hermiston]]
-=== Results ===
+==== Experimental setup ====
-== Experimental setup ==
 * Codes were run in Ubuntu 14.04.
 * Caffe framework 1.0.0-rc3 to perform the feature extraction by means of SAE.
-* The SAE is configured to obtain 12 features.
+  * The SAE is configured to obtain 12 features.
-* Two consecutive layers reduce the dimensionality of the data from 242 to 100 and from 100 to 12 features,respectively.
+  * Two consecutive layers reduce the dimensionality of the data from 242 to 100 and from 100 to 12 features,respectively.
-* The SAE is trained with 20% of the available pixels randomly chosen.
+  * The SAE is trained with 20% of the available pixels randomly chosen.
-* A batch of 64 pixels per iteration is used
+  * A batch of 64 pixels per iteration is used.
-* The iteration limit is fixed to 300000 iterations.
+  * The iteration limit is fixed to 300000 iterations.
-* The back-propagation process uses a Stochastic Gradient Descent (SGD) and the ’inv’ learning rate policy [inv = base lr ∗ (1 + γ ∗ i)^(−power)] being i the iteration number and with a base learning rate (base lr) of 0.01, and values for the parameters γ and power of 0.0001 and 0.75 respectively.
+  * The back-propagation process uses a Stochastic Gradient Descent (SGD) and the ’inv’ learning rate policy [inv = base lr ∗ (1 + γ ∗ i)^(−power)] being i the iteration number and with a base learning rate (base lr) of 0.01, and values for the parameters γ and power of 0.0001 and 0.75 respectively.
 * NWFE and PCA used for comparision purposes retaining 12 features.
 * ELM and SVM trained with 5% of the reference data available for each class.
-* Training samples randomly chosen in each run.
+  * Training samples randomly chosen in each run.
-* 10 independent runs for each classifier.
+  * 10 independent runs for each classifier.
-* SVM classification carried out using the LIB-SVM library and the Gaussian radial basis function (RBF)
+  * SVM classification carried out using the LIB-SVM library and the Gaussian radial basis function (RBF).
-* ELM configured with a sigmoidal activation function.
+  * ELM configured with a sigmoidal activation function.
+==== Outputs ====
+=== Image files ===
+|Reference data of changes |Binary CD map |Multiclass CD map|
+|{{:hiperespectral:referencedatacolorhermiston5.png?200|}}|{{:hiperespectral:binarycd.png?200|}}|{{:hiperespectral:svmcolorhermiston.png?200|}}|
+=== Accuracy results ===
+==Binary CD accuracies==
+|Corect |Missed Alarms|False Alarms |Total Error|
+|77020 (98.74%) |509 |471 |980 (1.25%) |
+==Multiclass CD accuracies==
+|**Classifier**   | **Parameters**     |**FE**   | **OA (%)**  | **AA (%)**  | **Kappa**  |
+| ELM             | N=120              | PCA     | 91.73       | 76.06       | 86.83      |
+| ELM             | N=120              | NWFE    | 91.76       | 76.75       | 86.83      |
+| ELM             | N=60               | SAE     | 95.19       | 90.45       | 92.31      |
+| SVM             | C: 64.0 γ: 32.0    | PCA     | 91.46       | 71.16       | 86.46      |
+| SVM             | C: 32.0 γ: 16.0    | NWFE    | 91.29       | 90.61       | 86.05      |
+| SVM             | C: 32.0 γ: 0.0625  | SAE     | 95.52       | 92.56       | 92.90      |
+C: penalty term in the training of the SVM. γ: radius of the gaussian function of the SVM. N: Number of neurons in the hidden layer of the ELM. FE: Feature Extraction method.
 ===== License =====
 :cc-by-nc-nd: