Latest Contributions by RichardFairhurst

Based on the classified tile samples shown in the notebook, it seems clear that you are getting tiles that have buildings in them.  It seems like the tiles I am getting are not at all what I should expect.  In fact it looks like the tiles I am getting are exactly the opposite of the set of tiles that I want.  I don't need any of those tiles, but I need all of the tiles that were not generated. At this point I am thinking of developing my own script to replace the Export Training Data for Deep Learning tool to output the set of tiles that I believe I need.  I am thinking that I would need to use the RasterToNumPyArray and NumPyArrayToRaster to be able to achieve an acceptable level of performance, since I know the Clip Raster tool is very slow.  Dan, can you comment on the possibility and practicality of using NumPy to take the raster inputs shown above and output a set of 500 x 500 classified tiles that includes buildings rather than excludes them?  The tool won't need to handle every possible input and output like the Esri tool.  It just needs to work for the raster inputs outlined in my previous post based on Sandeep's procedure (pixel depth, cell size, bands, etc). ... View more

I tried again to follow your notebook example more exactly.  I used ObjectID rather than the classValue field as input to the Polygon To Raster tool: I then used the Reclassify tool to assign all buildings to 1 and NODATA to 0 (I had deleted the background feature so my ObjectIDs started at 2 rather than 1). I ran the Export Data tool based on the settings you showed. I changed the layer to Thematic. The Raster and its properties look like this: When I ran the Export Training Data using that label raster I get the same set of tiles that have no buildings in them like I did in the previous post: If I change the NODATA property of the label raster to 0 in Catalog then the background disappears when I bring the raster into ArcGIS Pro, but when I use that as my input the Export Training Data tool doesn't output any classified tiles at all. So is this the best output I am going to get with the Export Training Data tool and will these tiles work if I tried to do the other steps in the notebook? ... View more

Sandeep: I tried to follow your instructions.  I am using ArcGIS PRo 2.4.1.  First I used the Identity tool to create a background polygon surrounding my building footprint polygons so that I could classify the entire feature extent.  I assigned a classValue of 1 to the building footprint polygons and a classValue of 2 to the background polygon.  I used the Polygon to Raster tool to output a raster of the buildings and background.  I changed the raster format from Generic to Thematic in the output and the NODATA value from 3 to 0, but noticed the output was a 2-bit pixel-depth output, not an 8-bit unsigned pixel depth output.  So I used the Copy Raster tool to make a copy that was 8-bit unsigned, and verified that the layer format was Thematic and the NODATA value was 0.  I verified that both my aerial image and my label raster have identical Extents and Spatial References and that all of the pixels are assigned a value in the label raster. Here is a picture of how the aerial image and the label image appear in the map Table of Contents legend of ArcGIS Pro 2.4.1: Here is a picture of the label raster and the raster properties of the label raster in Catalog: Here is a picture of the aerial and its Catalog properties: Here are the Export Training Data for Deep Learning tool settings: The output of the tool has no image chips with buildings, only image chips without any buildings: Here are the label tiles: The output is identical when I check the Output No Feature Tiles option on the Export tool.  The output is also identical if I copy the aerial and label rasters into the ArcGIS Pro project File Geodatabase and use those rasters as inputs for the tool. Why is the Export tool failing to output any image chips with buildings in them?  Is this output what I should expect?  What do the output tiles look like for the rasters shown in your notebook? ... View more

With ArcMap 10.6 the Export Training Data tool has a Start Index parameter that will overwrite the existing tiles if you specify a starting index that overlaps any of the indexes used by previous tiles.  If you are using that version of the tool you have to manually set the Start Index to a number that comes after the last existing tile index to append tiles and not overwrite tiles. I believe the tool automatically never overwrites and always appends only if you are using the Export Training Data tool at ArcMap 10.7 or ArcGIS Pro 2.4.  The ArcMap 10.7 and ArcGIS Pro 2.4 versions of the tool dropped the Start Index parameter and apparently starts at 0 if there are no existing tiles in a directory or else it starts indexing tiles after the last used tile index to avoid overwriting the outputs.  I think the notebook requires or assumes that you are using the ArcMap 10.7 and ArcGIS Pro 2.4 version of the tool.  This version of the tool also creates different output files that are needed by the learn.ai module that the ArcMap 10.6 version did not create, so I am pretty sure you have to use the ArcMap 10.7 and ArcGIS Pro 2.4 version of the tool to follow the notebook. ... View more

Sandeep: Your blog makes it seem like it is a simple task to create a classified raster from building footprint polygons that the Export Training Data tool will accept. Extracting building footprints We used the existing building footprints as training data to train another deep learning model for extracting building footprints. This time, the model that we had to train was a pixel classification model, wherein each pixel belonging to a building needed to be labelled as such. Pixel classification for extracting buildings Exporting training data ArcGIS Pro has support for exporting training samples in the Classified Tiles format for training such models. All we had to do was convert the existing building footprint layer to a classified raster and feed it into the tool. So it is clear that I need to create a classified raster and use the Classified Tiles output from the Export Training Data tool to Extract Building Footprints.  Your blog makes it sound like you and your team think it should be obvious to everyone what steps they need to follow to create a classified raster from a building footprint layer, but I assure you that it is not.  There is nothing obvious about it and I have wasted days searching the ArcGIS Pro and ArcMap help documents for anything that creates an identical output that works with the Export Training Data tool.  All of my outputs that resemble yours are rejected by the tool as not being Thematic.  Is there any user out there who has a clue what actually needs to be done to complete this step? ... View more

I am really struggling to understand how to use building polygons to create an output that will work with the Export Training Data for Deep Learning tool.  I am making an assumption that I need to create classified tiles for use with the Classify Pixels Deep Learning Model, but that assumption could be wrong.  I cannot figure out how to make it create classified tiles that make any sense to me.  When I run the Polygon to Raster tool with just the building footprint shapes it creates a raster with no background.  When I use that raster with the Export Training Data tool it says it worked but no image chips are created.  (Aerial with Polygon to Raster output on top.  No training image chips are created when these two raster are used as inputs to the Export Training Data for Deep Learning tool) I tried running the Segment Mean Shift tool.  It creates a raster with an added background surrounding the buildings that seems to work with the Export tool.  However, that raster seems to treat the buildings as the no data values and the background as the raster feature.  When I run the Export Training Data tool it only creates classified tile chips of the portions of my aerial that contain no buildings. It doesn't seem like that output will do me any good for classifying pixels as buildings.  (Segment Mean Shift Tool output based on Polygon to Raster input) (Training Image Chips are created by the Export Training Data for Deep Learning Tool when I use the Segment Mean Shift raster as the classified raster, but none of the chips have buildings in them.  They only cover portions of the aerial that had no buildings at all within the chip. The Output No Feature Tiles option made no difference) I have no idea what I should expect from these tools, because the documentation and examples are no help.  I have tried at least 50 workflow variants to try to get classified tile chips that show buildings and nothing has worked.  Outputs have ranged from the Export tool creating nothing, to creating only chips without buildings, to errors stating that the raster is incompatible with the Export Training Data tool.  The Segment Mean Shift tool output shown above is the best result I have had so far. My trial and error definitely seems to just be error at this point.  I am sure Esri support will be useless for this task, since at this point it is clear to me that they know less than I do.  Sandeep I really, really need someone to provide more details about your building footprints workflow than what your blog says ... View more

Sandeep: When do you expect to release the notebook you are working on?  I have managed to use aspects of the learn.ai module code in the land cover notebook with my local data, so I expect I will be able to make use of the notebook for building footprints.  I have several questions about the approach you described.  Did you use the Classified_Tiles metadata output from your Export Training Data for Deep Learning tool, and did you have to first convert your building footprint polygons to rasters in order to do that?  Or were you able to use a different metadata format output that worked with the original building footprint polygons you had?  Also, were you able to use the Classify Pixel modelling with just a single class of buildings, or did you have to have two classes of buildings and non-buildings (everything surrounding your building footprints).  Anyway, I would prefer to benefit from your experience on this task, otherwise I will have to do all of the trial and error process on my own, since I am going to come up with a building footprint creation process one way or the other. ... View more

Sandeep: I would very much like to see the UNet model your team used to extract building footprints.  Did your model include a RefineNet subroutine to enhance the quality of the classified image output or did you just rely on the Regularize Building Footprint tool to clean up lower resolution raster images? ... View more

The notebook really confused me since it caused me to read the online help for Image Server and not for ArcGIS Pro or Desktop, so I thought the tool only worked with Image Server.  Since I have Spatial Analyst, I decided to just try the Export Training Data for Deep Learning tool on my own data in Desktop and to output it to a local directory.  I found that my Image Service was too large and had download restrictions that caused a 999999 error, so I used the Clip tool to extract a GDB raster of a smaller portion.  My Building Footprint feature class was also too large so I selected footprints that overlapped the image I had clipped and exported them.  I made sure that there were 5 fields that matched the Image Classification Manager fields added to my building footprint polygons (Classname - text 256 char, Classvalue - Long, RED - Long, GREEN - Long and BLUE - Long) and populated them.  That finally worked to output PNG files to a local directory and KITTI_rectangles metadata. For the benefit of anyone like me that wants a real life example of what the tool produces rather than just the description given in the tool help, the output created an images directory and a labels directory and a stats.txt file.  There were 644 PNG files in the images directory based on the number of pixels and stride I specified and the number of images that contained a polygon, and there were 644 text files in the labels directory all with numeric file names padded with leading zeros (ie., 000000000.png and 000000000.txt respectively)  A sample image and label text file are shown below:   Image output to the images directory                                image shown with building polygons (not part of output) labels text file: 1 0.00 0 0 0.00 433.91 24.63 507.57 0 0 0 0 0 0 0 1 0.00 0 0 33.03 497.67 82.45 512.00 0 0 0 0 0 0 0 1 0.00 0 0 85.77 384.83 198.12 512.00 0 0 0 0 0 0 0 1 0.00 0 0 408.83 386.81 512.00 506.69 0 0 0 0 0 0 0 1 0.00 0 0 388.53 195.90 502.51 290.04 0 0 0 0 0 0 0 1 0.00 0 0 409.18 0.00 512.00 18.65 0 0 0 0 0 0 0 The tool says the first position in each line of the text file is the classification code, the next three are skipped, the next four are image coordinates that define the minimum bounding rectangle of the polygon and the rest of the positions are skipped.  The minimum bounding rectangle defines separate training chips within the image that will be used by the deep learning classifier for each building.   The stats.txt file summarized the output of the tool as follows: images = 644 *3*512*512 features = 4539 features per image = [min = 1, mean = 7.05, max = 14] classes = 1 cls name cls value images features min size mean size max size Buildings 1 644 4539 0.02 1978.09 6068.74 ... View more

I will not be using Esri tools for deep learning as long as Esri only publishes examples that rely on Image Server, since I cannot and will not work in that environment.  Telling me working outside of Image Server can be done does me no good without any examples or clear explanation showing how to actually do it.  I called Esri help and they could not tell me how to adapt the code the Esri deep learning team provided in their notebook to work outside of Image Server, so I really need an example where Image Server is not used by the Export Training Data for Deep Learning tool. I only had a trial license for Image Analyst that expired while I was trying to get help from Esri to show me how to actually use the Export Training Data for Deep Learning tool without Image Server.  I believe My organization is still trying to get an Image Analyst license added to our Enterprise license, but I am frustrated that the deep learning team notebooks were unusable without Image Server access. I do have an Advanced license, a Spatial Analyst license and a 3D Analyst license, so I can use the Eliminate tool, the Classify Pixel for Deep Learning tool, Majority Filter tool and the Regularize Building Footprint tool shown in the model builder diagram for the Building Footprint Extraction portion of the blog.  However, I will not be getting access to Image Server, so I really need help making your notebook work without using Image Server. The deep learning team really needs to lay out all of these license requirements in the notebooks up front more clearly, so that people don't waste their time trying them when they don't have the necessary licenses.  And please provide an alternative option that doesn't involve Image Server if it is only highly recommended but not an absolute requirement. ... View more

The notebook this post was originally based on was set up to use Image Services and Image Server.  Will your code work with data stored locally rather than online or using Image Server?  Will it work with just an Image Analyst licence in ArcGIS Pro? ... View more

I had not seen that.  Is there any code I could see that is related to the image?  What was involved in training the model? ... View more

Most likely the basemap is in Geographic Coordinate System WGS 1984 and all of your other layers are in a different coordinate system (probably a local projection suited to your area of interest).  Your dataframe was probably using the basemap coordinate system, which means all of your other layers needed to be projected on the fly pretty much every time the map refreshed.  That can take a long time if you have a lot of layers that need to project on the fly, especially if you are zoomed out pretty far.  I don't use basemaps for this reason and my jurisdiction bought our own aerials and serve them in my local projection, so performance is always good. You may want to try making the data frame use your local projection and make the basemap project on the fly, and set the basemap visibility to turn off when you zoom out beyond a certain amount so that it does not project on the fly over a large area.  Of course if you have control over the imagery and have Image Server, you want to make sure the imagery is projected into your local coordinate system projection.  Mixing coordinate systems in an editing map is generally a bad idea and the effort of projecting all of the data into the same coordinate system is worth it if you will regularly be using your editing map. ... View more

Ben: A Linear Referenced Route feature class is a standard feature class that is just M coordinate enabled (which is no different from a feature class with Z coordinates enabled) and when it is created in a file geodatabase it has an ObjectID, so there actually is nothing special about routes vs any other feature class.  I have not tried ArcGIS Pro for modifying tables, but in ArcMap you cannot use the Catalog view to edit a schema if the feature class is a layer in a map document, so maybe ArcGIS Pro is the same.  Anyway, in both ArcMap and ArcGIS Pro you should be able to use the Add Field tool even if the feature class is open in a map document. Assuming you can get through all of the steps, please post back with pictures of the final results, especially if it didn't work out as expected or if you find that there are a lot of situations where this approach needs adjustment.  Although I have applied similar techniques to my own problems, I have never actually used this exact process myself with data like yours, so I am curious to see how well it worked. ... View more