diff --git a/otbtf_pres/illustrations/gif_2160.gif b/otbtf_pres/illustrations/gif_2160.gif index 692aa15592d490c0c4b7984ef641f8cad3667d1d..08512907e038413395ee398cfa7ec3b903e80198 100644 Binary files a/otbtf_pres/illustrations/gif_2160.gif and b/otbtf_pres/illustrations/gif_2160.gif differ diff --git a/otbtf_pres/illustrations/net_semseg_spot67.jpg b/otbtf_pres/illustrations/net_semseg_spot67.jpg new file mode 100644 index 0000000000000000000000000000000000000000..d14ee9ed2d8cfb803964c64c1a3fe47484d85826 Binary files /dev/null and b/otbtf_pres/illustrations/net_semseg_spot67.jpg differ diff --git a/otbtf_pres/illustrations/pyotbadvert.gif b/otbtf_pres/illustrations/pyotbadvert.gif new file mode 100644 index 0000000000000000000000000000000000000000..816b2980a1cb8441105ebaca2c3e4f1c9f1941c4 Binary files /dev/null and b/otbtf_pres/illustrations/pyotbadvert.gif differ diff --git a/otbtf_pres/illustrations/pyotbadvert.png b/otbtf_pres/illustrations/pyotbadvert.png index e457f102bf2875ab5f752d71b4673bb1f4d56fac..f77b214d8c9eaf4164887125600c2d571cfb49b9 100644 Binary files a/otbtf_pres/illustrations/pyotbadvert.png and b/otbtf_pres/illustrations/pyotbadvert.png differ diff --git a/otbtf_pres/index.html b/otbtf_pres/index.html index 01a1caec486afc9091c7326ecc9dce5b72853381..28d8d8277a0046995c6e4984750af2100f5e4ca9 100644 --- a/otbtf_pres/index.html +++ b/otbtf_pres/index.html @@ -271,7 +271,7 @@ tf_ds = TFRecords("/path/to/tfrecords_dir").read() <br> <ul> <li>Ease the <h>implementation of deep nets</h> in python</li> - <li>Provides all the necessary to work smoothly with TensorflowModelServe</li> + <li>Provides everything to work smoothly with TensorflowModelServe</li> </ul> <br> <img width="50%" data-src="illustrations/modelbase.png"> @@ -379,7 +379,11 @@ app.write("output_y.tif") <img width="50%" data-src="illustrations/fig12.10_new.png"> <br> <p><h>Example</h>: simple U-Net like model for dense pixel classification</p> - <p><small>Cresson, R. (2020). Deep Learning for Remote Sensing Images with Open Source Software. CRC Press.</small></p> + <p><small> + Cresson, R. (2020). + Deep Learning for Remote Sensing Images with Open Source Software. + CRC Press. + </small></p> </section> </section> @@ -396,10 +400,22 @@ app.write("output_y.tif") <section> <h2>Large scale land cover mapping</h2> - <h4>Semantic segmentation of buildings footprint over france mainland at 1.5m spacing</h4> + <h4>Buildings footprint over france mainland from Spot-6/7</h4> <img width="65%" data-src="illustrations/tosca.png"> - <p><small>Product available at <a href="https://www.theia-land.fr/en/product/buildings-footprint" - target="_blank">https://www.theia-land.fr/en/product/buildings-footprint/</a></small></p> + <p><small> + Product available at + <a href="https://www.theia-land.fr/en/product/buildings-footprint" + target="_blank">https://www.theia-land.fr/en/product/buildings-footprint/</a> + </small></p> + </section> + + <section> + <h4>Model designed for Spot-6/7 products</h4> + <img width="40%" data-src="illustrations/net_semseg_spot67.jpg"> + <p><small> + Semantic segmentation network that inputs separately <h>multispectral</h> and + <h>panchromatic</h> rasters of Spot-6/7 images + </small></p> </section> <section data-background-image='illustrations/gif_2160.gif'></section> @@ -424,6 +440,7 @@ app.write("output_y.tif") <section> <h4>Easy to run</h4> + <img width="48px" data-src="illustrations/cli.png" style="float:left;padding-left:15%;margin:30px"> <pre style="width:1000px"><code data-trim class="bash"> # Download pre-trained model wget https://tinyurl.com/sr4rsmodelv2 @@ -490,7 +507,7 @@ if __name__ == "__main__": # if you need to write: infer.write("out", out_fn) </code></pre> - <img width="20%" data-src="illustrations/pyotbadvert.png"> + <img width="20%" data-src="illustrations/pyotbadvert.gif"> </section> <section> @@ -539,10 +556,11 @@ if __name__ == "__main__": <ul> <li><h>Blog</h>: https://mdl4eo.irstea.fr/2022/04/09/bye-bye-clouds/</li> <li><h>Paper</h>: https://doi.org/10.5194/isprs-archives-XLIII-B3-2022-1317-2022</li> - <li><h>Code</h> https://github.com/cnes/decloud</li> </ul> <img width="50%" data-src="illustrations/crga_os2_unet_slide3.png"> - <p><small>Cresson, R., Narçon, N., Gaetano, R., Dupuis, A., Tanguy, Y., May, S., and Commandré, B.: COMPARISON OF CONVOLUTIONAL NEURAL NETWORKS FOR CLOUDY OPTICAL IMAGES RECONSTRUCTION FROM SINGLE OR MULTITEMPORAL JOINT SAR AND OPTICAL IMAGES, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2022, 1317–1326</small></p> + <p><small>Cresson, R., Narçon, N., Gaetano, R., Dupuis, A., Tanguy, Y., May, S., and Commandré, B.: + Comparison of CNNs or cloudy optical images reconstruction from single or multitemporal + joint SAR and optical images, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2022, 1317–1326</small></p> </section> <section>