{"id":2983781,"date":"2026-10-02T10:23:10","date_gmt":"2026-10-02T17:23:10","guid":{"rendered":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=2983781"},"modified":"2026-10-02T10:23:10","modified_gmt":"2026-10-02T17:23:10","slug":"classify-point-clouds-using-embedding-based-image-analysis","status":"publish","type":"blog","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis","title":{"rendered":"Classify Point Clouds Using Embedding Based Image Analysis"},"author":314032,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","format":"standard","meta":{"_acf_changed":false,"_searchwp_excluded":""},"categories":[23771,770712,22931],"tags":[757081,781242,24381],"industry":[],"product":[36561],"class_list":["post-2983781","blog","type-blog","status-publish","format-standard","hentry","category-3d-gis","category-geoai","category-imagery","tag-deep-learning-models","tag-embeddings","tag-lidar","product-arcgis-pro"],"acf":{"short_description":"Use information from imagery to classify lidar points without training a custom model. ","flexible_content":[{"acf_fc_layout":"content","content":"

A fully classified point cloud can support many geospatial workflows. Ground points can be used for terrain modeling in construction, hydrology, and surface analysis. Vegetation classes support forestry and corridor encroachment analysis. Classified objects can be extracted into 3D objects that are foundational in a geospatial digital twin.<\/span>\u00a0<\/span><\/p>\n

Point cloud classification can be challenging as it often requires several automated tools followed by manual cleanup. Some features, such as power lines or transmission towers, may require a deep learning model. Pretrained point cloud classification models are available in ArcGIS Living Atlas of the World<\/a><\/span>, but training a custom model requires labeled data, time, and AI experience.<\/span>\u00a0<\/span><\/p>\n

When imagery and point clouds cover the same area, several AI tools and models can provide another path. If you can identify features of interest within the imagery, then you can use that information to help classify overlapping point clouds. This is especially powerful when the imagery and point cloud are collected at the same time.<\/span>\u00a0<\/span><\/p>\n

Two complementary approaches can help:<\/span>\u00a0<\/span><\/p>\n

    \n
  1. Use a pretrained foundation model, such as a prompt-based segmentation model (e.g. <\/span>SAM3<\/span><\/a>), to identify features of interest in the imagery.<\/span>\u00a0<\/span><\/li>\n<\/ol>\n
      \n
    1. Use the Embedding-Based Analysis toolset to classify imagery by comparing semantic similarity.<\/span>\u00a0<\/span><\/li>\n<\/ol>\n

      The first approach uses prompts to find familiar objects in imagery and is covered in several ArcGIS Blogs, like this one on extracting GIS features with text prompts<\/a> or doing multiresolution object detection with Text SAM<\/a><\/span>. This article focuses on the second approach: using imagery embeddings to find a feature and transfer the result to a point cloud.<\/span>\u00a0<\/span><\/p>\n"},{"acf_fc_layout":"content","content":"

      Use imagery embeddings to classify a point cloud<\/span>\u00a0<\/span><\/h3>\n

      Embeddings are numerical descriptions of patterns in data such as imagery or lidar. Features that look similar often have similar embeddings. This makes it possible to find a feature using only a few examples instead of training a custom model.<\/span>\u00a0<\/span><\/p>\n

      For more information on embeddings, refer to this ArcGIS Blog by Catherine David: <\/span>An Introduction to Embeddings for GIS Analysts.<\/span><\/a>\u00a0<\/span><\/p>\n

      ArcGIS provides several pretrained models that create embeddings from imagery, all available on the Living Atlas<\/a><\/span>. In this workflow, you will create embeddings and select those that represent the target feature, find similar, and then use the result to classify point cloud data.<\/span>\u00a0<\/span><\/p>\n

      This method works best for features with a clear visual pattern, such as rail lines, roads, solar panels, or specific roof types. It can reduce labeling and provide a useful starting point without training a point cloud model.<\/span>\u00a0<\/span><\/p>\n"},{"acf_fc_layout":"content","content":"

      Example: Extract railroad tracks at the Dangermond Preserve<\/span>\u00a0<\/span><\/h3>\n

      For this example, Esri worked with Wingtra, UC Santa Barbara, and The Nature Conservancy to collect high resolution imagery and lidar for the Jack and Laura Dangermond Preserve near Santa Barbara, California. We processed these data into 2D and 3D geospatial products using ArcGIS Reality. The preserve includes several different classes: coastal cliffs, vegetation (trees and chaparral), buildings, roads (paved and unpaved), solar panels, and a railroad corridor.<\/span>\u00a0<\/span><\/p>\n"},{"acf_fc_layout":"image","image":{"ID":2983927,"id":2983927,"title":"Jack and Laura Dangermond Preserve","filename":"1_JLD_preserve-1.png","filesize":3065831,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/1_JLD_preserve-1.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis\/1_jld_preserve-2","alt":"","author":"312432","description":"","caption":"Screenshot: A Gaussian Splat layer of the Jack & Laura Dangermond Reserve; created with ArcGIS Reality","name":"1_jld_preserve-2","status":"inherit","uploaded_to":2983781,"date":"2026-10-02 17:14:39","modified":"2026-10-02 17:15:13","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":1917,"height":1029,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/1_JLD_preserve-1-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/1_JLD_preserve-1.png","medium-width":464,"medium-height":249,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/1_JLD_preserve-1.png","medium_large-width":768,"medium_large-height":412,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/1_JLD_preserve-1.png","large-width":1917,"large-height":1029,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/1_JLD_preserve-1-1536x824.png","1536x1536-width":1536,"1536x1536-height":824,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/1_JLD_preserve-1.png","2048x2048-width":1917,"2048x2048-height":1029,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/1_JLD_preserve-1-826x443.png","card_image-width":826,"card_image-height":443,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/1_JLD_preserve-1.png","wide_image-width":1917,"wide_image-height":1029}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

      Standard ArcGIS tools can classify many ground, building, and vegetation points. The railroad tracks are harder<\/span> to <\/span>identify<\/span> from point cloud <\/span>shape<\/span> alone, but they are <\/span>easy to see<\/span> in the true orthophoto. <\/span>This<\/span> makes them a <\/span>good<\/span> candidate for <\/span>embedding<\/span> based <\/span>analysis<\/span>.<\/span><\/span>\u00a0<\/span><\/p>\n"},{"acf_fc_layout":"content","content":"

      Workflow<\/span><\/h3>\n

      1. Prepare the imagery and point cloud<\/strong><\/p>\n

      Add the true orthophoto and overlapping LAS dataset to ArcGIS Pro. Confirm that they cover the same area and use compatible projected coordinate systems. If the point cloud already has useful classes, preserve them so only the target points are updated.<\/span>\u00a0<\/span><\/p>\n"},{"acf_fc_layout":"image","image":{"ID":2983855,"id":2983855,"title":"2_trueortho_LPC","filename":"2_trueortho_LPC.png","filesize":1577230,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/2_trueortho_LPC.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis\/2_trueortho_lpc","alt":"Screenshot: True orthophoto (left) and Lidar point cloud (right) displayed over a portion of the railroad corridor.","author":"314032","description":"Screenshot: True orthophoto (left) and Lidar point cloud (right) displayed over a portion of the railroad corridor. ","caption":"Screenshot: True orthophoto (left) and Lidar point cloud (right) displayed over a portion of the railroad corridor. ","name":"2_trueortho_lpc","status":"inherit","uploaded_to":2983781,"date":"2026-10-01 20:28:51","modified":"2026-10-01 20:29:29","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":1367,"height":575,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/2_trueortho_LPC-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/2_trueortho_LPC.png","medium-width":464,"medium-height":195,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/2_trueortho_LPC.png","medium_large-width":768,"medium_large-height":323,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/2_trueortho_LPC.png","large-width":1367,"large-height":575,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/2_trueortho_LPC.png","1536x1536-width":1367,"1536x1536-height":575,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/2_trueortho_LPC.png","2048x2048-width":1367,"2048x2048-height":575,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/2_trueortho_LPC-826x347.png","card_image-width":826,"card_image-height":347,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/2_trueortho_LPC.png","wide_image-width":1367,"wide_image-height":575}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

      2. Generate imagery embeddings<\/strong><\/p>\n

      Use a pretrained imagery model to create embeddings from the true orthophoto. Choose an output resolution that keeps the narrow railroad features visible. Each feature in the embeddings output stores a numerical description of the imagery at that location. This description is used by AI models and tools to efficiently find similar features.<\/span>\u00a0<\/span><\/p>\n"},{"acf_fc_layout":"image","image":{"ID":2983857,"id":2983857,"title":"3_generate_embeddings","filename":"3_generate_embeddings.png","filesize":1432628,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/3_generate_embeddings.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis\/3_generate_embeddings","alt":"Screenshot: Embedding tool parameters and the resulting embedding feature.","author":"314032","description":"Screenshot: Embedding tool parameters and the resulting embedding feature. ","caption":"Screenshot: Embedding tool parameters and the resulting embedding feature. ","name":"3_generate_embeddings","status":"inherit","uploaded_to":2983781,"date":"2026-10-01 20:31:24","modified":"2026-10-01 20:31:46","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":1452,"height":975,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/3_generate_embeddings-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/3_generate_embeddings.png","medium-width":389,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/3_generate_embeddings.png","medium_large-width":768,"medium_large-height":516,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/3_generate_embeddings.png","large-width":1452,"large-height":975,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/3_generate_embeddings.png","1536x1536-width":1452,"1536x1536-height":975,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/3_generate_embeddings.png","2048x2048-width":1452,"2048x2048-height":975,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/3_generate_embeddings-692x465.png","card_image-width":692,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/3_generate_embeddings.png","wide_image-width":1452,"wide_image-height":975}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

      3. Find embeddings that are similar to the railroad tracks<\/strong><\/p>\n

      Select a few clear examples of the railroad tracks. Avoid shadows, vegetation, crossings, and nearby surfaces when possible. Use the Embedding-Based Analysis Find Similar interactive tool to test out different areas and parameters.<\/span>\u00a0<\/span><\/p>\n

      Review the result in several areas. If it includes unrelated surfaces, adjust the threshold and run the analysis again. The goal is a reliable mask of the railroad corridor, not a perfect result on the first attempt. Once satisfied, you can use the <\/span>Find Similar Features Using Embeddings<\/span><\/a> geoprocessing tool across full the image.<\/span>\u00a0<\/span><\/p>\n"},{"acf_fc_layout":"image","image":{"ID":2983863,"id":2983863,"title":"embeddings_railroad_findsimilar_under100mb","filename":"embeddings_railroad_findsimilar_under100mb.gif","filesize":103893927,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/embeddings_railroad_findsimilar_under100mb.gif","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis\/embeddings_railroad_findsimilar_under100mb","alt":"GIF: Selecting railroad samples and running embedding-based similarity analysis.","author":"314032","description":"GIF: Selecting railroad samples and running embedding-based similarity analysis. ","caption":"GIF: Selecting railroad samples and running embedding-based similarity analysis. ","name":"embeddings_railroad_findsimilar_under100mb","status":"inherit","uploaded_to":2983781,"date":"2026-10-01 20:44:51","modified":"2026-10-01 20:45:34","menu_order":0,"mime_type":"image\/gif","type":"image","subtype":"gif","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":1826,"height":1080,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/embeddings_railroad_findsimilar_under100mb-213x200.gif","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/embeddings_railroad_findsimilar_under100mb.gif","medium-width":441,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/embeddings_railroad_findsimilar_under100mb.gif","medium_large-width":768,"medium_large-height":454,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/embeddings_railroad_findsimilar_under100mb.gif","large-width":1826,"large-height":1080,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/embeddings_railroad_findsimilar_under100mb-1536x908.gif","1536x1536-width":1536,"1536x1536-height":908,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/embeddings_railroad_findsimilar_under100mb.gif","2048x2048-width":1826,"2048x2048-height":1080,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/embeddings_railroad_findsimilar_under100mb-786x465.gif","card_image-width":786,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/embeddings_railroad_findsimilar_under100mb.gif","wide_image-width":1826,"wide_image-height":1080}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

      4. Review and merge the result<\/strong><\/p>\n

      Once you have the results completed for the entire railroad corridor, perform a visual assessment of the results. If needed, use GIS Editing tools to help aid with any needed cleanup. Once satisfied with the result, perform a Pairwise Dissolve to create one single feature for the entire railroad corridor. This step is optional but will help improve performance during the point cloud classification.<\/span>\u00a0<\/span><\/p>\n"},{"acf_fc_layout":"image","image":{"ID":2983858,"id":2983858,"title":"4_findsimilar","filename":"4_findsimilar.png","filesize":2625585,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/4_findsimilar.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis\/4_findsimilar","alt":"Screenshot: Refined railroad mask over the true orthophoto.","author":"314032","description":"Screenshot: Refined railroad mask over the true orthophoto. ","caption":"Screenshot: Refined railroad mask over the true orthophoto. ","name":"4_findsimilar","status":"inherit","uploaded_to":2983781,"date":"2026-10-01 20:33:30","modified":"2026-10-01 20:33:52","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":1393,"height":862,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/4_findsimilar-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/4_findsimilar.png","medium-width":422,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/4_findsimilar.png","medium_large-width":768,"medium_large-height":475,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/4_findsimilar.png","large-width":1393,"large-height":862,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/4_findsimilar.png","1536x1536-width":1393,"1536x1536-height":862,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/4_findsimilar.png","2048x2048-width":1393,"2048x2048-height":862,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/4_findsimilar-751x465.png","card_image-width":751,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/4_findsimilar.png","wide_image-width":1393,"wide_image-height":862}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

      5. Transfer the class to the point cloud<\/strong><\/p>\n

      No matter the approach you used (embeddings or prompt-based segmentation), you can easily transfer the resulting feature to improve the point cloud classification by using the <\/span>Set LAS Class Codes Using Features<\/span><\/a> geoprocessing tool. Assign the new class code for rail – 10 (based on <\/span>ASPRS Classification<\/span><\/a>) to the LAS Dataset. If needed, you can even apply a buffer directly within the tool to create a cleaner result. The feature supplies the region to apply the new class code to the point cloud.<\/span>\u00a0<\/span><\/p>\n"},{"acf_fc_layout":"image","image":{"ID":2983859,"id":2983859,"title":"5_classifyLASfeatures","filename":"5_classifyLASfeatures.png","filesize":48393,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/5_classifyLASfeatures.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis\/5_classifylasfeatures","alt":"Screenshot: Set LAS Class Codes Using Features geoprocessing tool parameters.","author":"314032","description":"Screenshot: Set LAS Class Codes Using Features geoprocessing tool parameters. ","caption":"Screenshot: Set LAS Class Codes Using Features geoprocessing tool parameters. ","name":"5_classifylasfeatures","status":"inherit","uploaded_to":2983781,"date":"2026-10-01 20:34:16","modified":"2026-10-01 20:34:32","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":597,"height":630,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/5_classifyLASfeatures-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/5_classifyLASfeatures.png","medium-width":247,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/5_classifyLASfeatures.png","medium_large-width":597,"medium_large-height":630,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/5_classifyLASfeatures.png","large-width":597,"large-height":630,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/5_classifyLASfeatures.png","1536x1536-width":597,"1536x1536-height":630,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/5_classifyLASfeatures.png","2048x2048-width":597,"2048x2048-height":630,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/5_classifyLASfeatures-441x465.png","card_image-width":441,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/5_classifyLASfeatures.png","wide_image-width":597,"wide_image-height":630}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

      Review the results<\/span>\u00a0<\/span><\/h3>\n

      Display the LAS dataset symbolized by class and compare it with the orthophoto. Check road crossings, vegetation edges, shadows, and hidden track sections. You can correct small errors by using the <\/span>Manual LAS classification<\/span><\/a> tools or by adjusting your embeddings threshold value and retrying.<\/span>\u00a0<\/span><\/p>\n"},{"acf_fc_layout":"image","image":{"ID":2983860,"id":2983860,"title":"6_lidarclassified","filename":"6_lidarclassified.png","filesize":1635308,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/6_lidarclassified.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis\/6_lidarclassified","alt":"Screenshot: Final railroad class shown in the point cloud, with a before (left) and after (right) comparison.","author":"314032","description":"Screenshot: Final railroad class shown in the point cloud, with a before (left) and after (right) comparison.","caption":"Screenshot: Final railroad class shown in the point cloud, with a before (left) and after (right) comparison.","name":"6_lidarclassified","status":"inherit","uploaded_to":2983781,"date":"2026-10-01 20:34:57","modified":"2026-10-01 20:35:26","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":1311,"height":517,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/6_lidarclassified-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/6_lidarclassified.png","medium-width":464,"medium-height":183,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/6_lidarclassified.png","medium_large-width":768,"medium_large-height":303,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/6_lidarclassified.png","large-width":1311,"large-height":517,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/6_lidarclassified.png","1536x1536-width":1311,"1536x1536-height":517,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/6_lidarclassified.png","2048x2048-width":1311,"2048x2048-height":517,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/6_lidarclassified-826x326.png","card_image-width":826,"card_image-height":326,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/6_lidarclassified.png","wide_image-width":1311,"wide_image-height":517}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

      Why use this approach?<\/span>\u00a0<\/span><\/h3>\n

      Embedding based analysis connects the visual detail in imagery with the 3D structure of lidar. It is useful when the feature is easy to see in imagery but difficult to separate using height, elevation, or point cloud return information.<\/span>\u00a0<\/span><\/p>\n

      Use ArcGIS and the 3D Analyst tools for classifying point clouds for common classes like ground, vegetation, and buildings, then combine with AI tools and models to use embeddings for visually distinct features, or train your own custom point cloud classification models when you need to repeat the workflow across many datasets.<\/span>\u00a0<\/span><\/p>\n"}],"authors":[{"ID":314032,"user_firstname":"Chad","user_lastname":"Lopez","nickname":"Chad Lopez","user_nicename":"clopez","display_name":"Chad Lopez","user_email":"CLopez@esri.com","user_url":"","user_registered":"2022-06-28 20:07:35","user_description":"Chad Lopez works within Esri's Imagery and Remote Sensing team specializing in drone solutions. Chad has worked at Esri since 2018 and holds a GIS Professional Certification (GISP), a Part 107 Remote Pilot Certificate, and a Master of Science in GIS from the University of Redlands. Chad also teaches GIS part time at several higher education institutions in Southern California. Chad is based in Esri's Redlands, California office.","user_avatar":""},{"ID":312432,"user_firstname":"Brian","user_lastname":"Connolly","nickname":"Brian Connolly","user_nicename":"arcgis_imagery-2","display_name":"Brian Connolly","user_email":"bconnolly@esri.com","user_url":"","user_registered":"2022-06-08 15:43:53","user_description":"Brian Connolly is a Senior Solution Engineer supporting ArcGIS Imagery and Reality Mapping. With a passion for earth science, reality capture, and emerging 3D technologies, he helps organizations unlock the value of lidar, meshes, Gaussian splats, and other 3D spatial data. His work focuses on bringing imagery and 3D GIS together to power digital twins and compelling geospatial experiences.","user_avatar":""}],"show_article_image":false,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/Lidarblogcard.jpg","wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/Lidarblogbanner.jpg","related_articles":[{"ID":2337132,"post_author":"19291","post_date":"2024-05-16 04:14:48","post_date_gmt":"2024-05-16 11:14:48","post_content":"","post_title":"Multiresolution Object Detection with Text SAM","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"multiresolution-object-detection-with-text-sam","to_ping":"","pinged":"","post_modified":"2024-05-16 06:25:42","post_modified_gmt":"2024-05-16 13:25:42","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=2337132","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":2311202,"post_author":"348302","post_date":"2024-05-14 19:40:06","post_date_gmt":"2024-05-15 02:40:06","post_content":"","post_title":"Text SAM: Extracting GIS Features Using Text Prompts","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"text-sam-extracting-gis-features-using-text-prompts","to_ping":"","pinged":"","post_modified":"2024-05-16 06:44:44","post_modified_gmt":"2024-05-16 13:44:44","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=2311202","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":2975115,"post_author":"437350","post_date":"2026-07-08 13:00:33","post_date_gmt":"2026-07-08 20:00:33","post_content":"","post_title":"An Introduction to Embeddings for GIS Analysts","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"an-introduction-to-embeddings-for-gis-analysts","to_ping":"","pinged":"","post_modified":"2026-09-21 12:54:41","post_modified_gmt":"2026-09-21 19:54:41","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=2975115","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":2972133,"post_author":"9612","post_date":"2026-06-23 11:18:36","post_date_gmt":"2026-06-23 18:18:36","post_content":"","post_title":"Using Lidar Alongside Imagery to Enhance Your Reality Mapping","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"using-lidar-alongside-imagery-to-enhance-your-reality-mapping","to_ping":"","pinged":"","post_modified":"2026-06-29 04:24:30","post_modified_gmt":"2026-06-29 11:24:30","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=2972133","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"}]},"yoast_head":"\nClassify Point Clouds Using Embedding Based Image Analysis<\/title>\n<meta name=\"description\" content=\"Learn how to use imagery embeddings in ArcGIS Pro to identify features in imagery and transfer the results to classify overlapping lidar point clouds without training a custom AI mod\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Classify Point Clouds Using Embedding Based Image Analysis\" \/>\n<meta property=\"og:description\" content=\"Learn how to use imagery embeddings in ArcGIS Pro to identify features in imagery and transfer the results to classify overlapping lidar point clouds without training a custom AI mod\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis\" \/>\n<meta property=\"og:site_name\" content=\"ArcGIS Blog\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/esrigis\/\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:site\" content=\"@ESRI\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":[\"Article\",\"BlogPosting\"],\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis\"},\"author\":{\"name\":\"Chad Lopez\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/83fd9de2c0ad4b03ad1fbabafbe42b4b\"},\"headline\":\"Classify Point Clouds Using Embedding Based Image Analysis\",\"datePublished\":\"2026-10-02T17:23:10+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis\"},\"wordCount\":8,\"publisher\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#organization\"},\"keywords\":[\"deep learning models\",\"embeddings\",\"Lidar\"],\"articleSection\":[\"3D Visualization & Analytics\",\"AI\",\"Imagery & Remote Sensing\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis\",\"name\":\"Classify Point Clouds Using Embedding Based Image Analysis\",\"isPartOf\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#website\"},\"datePublished\":\"2026-10-02T17:23:10+00:00\",\"description\":\"Learn how to use imagery embeddings in ArcGIS Pro to identify features in imagery and transfer the results to classify overlapping lidar point clouds without training a custom AI mod\",\"breadcrumb\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.esri.com\/arcgis-blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Classify Point Clouds Using Embedding Based Image Analysis\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#website\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/\",\"name\":\"ArcGIS Blog\",\"description\":\"Get insider info from Esri product teams\",\"publisher\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.esri.com\/arcgis-blog\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#organization\",\"name\":\"Esri\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Esri.png\",\"contentUrl\":\"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Esri.png\",\"width\":400,\"height\":400,\"caption\":\"Esri\"},\"image\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/esrigis\/\",\"https:\/\/x.com\/ESRI\",\"https:\/\/www.linkedin.com\/company\/5311\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/83fd9de2c0ad4b03ad1fbabafbe42b4b\",\"name\":\"Chad Lopez\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2022\/07\/1590759325815-465x465.jpg\",\"contentUrl\":\"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2022\/07\/1590759325815-465x465.jpg\",\"caption\":\"Chad Lopez\"},\"description\":\"Chad Lopez works within Esri's Imagery and Remote Sensing team specializing in drone solutions. Chad has worked at Esri since 2018 and holds a GIS Professional Certification (GISP), a Part 107 Remote Pilot Certificate, and a Master of Science in GIS from the University of Redlands. Chad also teaches GIS part time at several higher education institutions in Southern California. Chad is based in Esri's Redlands, California office.\",\"sameAs\":[\"https:\/\/www.linkedin.com\/in\/chadlopez2015\/\"],\"jobTitle\":\"Solution Engineer\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/author\/clopez\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Classify Point Clouds Using Embedding Based Image Analysis","description":"Learn how to use imagery embeddings in ArcGIS Pro to identify features in imagery and transfer the results to classify overlapping lidar point clouds without training a custom AI mod","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis","og_locale":"en_US","og_type":"article","og_title":"Classify Point Clouds Using Embedding Based Image Analysis","og_description":"Learn how to use imagery embeddings in ArcGIS Pro to identify features in imagery and transfer the results to classify overlapping lidar point clouds without training a custom AI mod","og_url":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis","og_site_name":"ArcGIS Blog","article_publisher":"https:\/\/www.facebook.com\/esrigis\/","twitter_card":"summary_large_image","twitter_site":"@ESRI","twitter_misc":{"Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":["Article","BlogPosting"],"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis#article","isPartOf":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis"},"author":{"name":"Chad Lopez","@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/83fd9de2c0ad4b03ad1fbabafbe42b4b"},"headline":"Classify Point Clouds Using Embedding Based Image Analysis","datePublished":"2026-10-02T17:23:10+00:00","mainEntityOfPage":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis"},"wordCount":8,"publisher":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/#organization"},"keywords":["deep learning models","embeddings","Lidar"],"articleSection":["3D Visualization & Analytics","AI","Imagery & Remote Sensing"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis","url":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis","name":"Classify Point Clouds Using Embedding Based Image Analysis","isPartOf":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/#website"},"datePublished":"2026-10-02T17:23:10+00:00","description":"Learn how to use imagery embeddings in ArcGIS Pro to identify features in imagery and transfer the results to classify overlapping lidar point clouds without training a custom AI mod","breadcrumb":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.esri.com\/arcgis-blog\/"},{"@type":"ListItem","position":2,"name":"Classify Point Clouds Using Embedding Based Image Analysis"}]},{"@type":"WebSite","@id":"https:\/\/www.esri.com\/arcgis-blog\/#website","url":"https:\/\/www.esri.com\/arcgis-blog\/","name":"ArcGIS Blog","description":"Get insider info from Esri product teams","publisher":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.esri.com\/arcgis-blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.esri.com\/arcgis-blog\/#organization","name":"Esri","url":"https:\/\/www.esri.com\/arcgis-blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/logo\/image\/","url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Esri.png","contentUrl":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Esri.png","width":400,"height":400,"caption":"Esri"},"image":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/esrigis\/","https:\/\/x.com\/ESRI","https:\/\/www.linkedin.com\/company\/5311\/"]},{"@type":"Person","@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/83fd9de2c0ad4b03ad1fbabafbe42b4b","name":"Chad Lopez","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/image\/","url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2022\/07\/1590759325815-465x465.jpg","contentUrl":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2022\/07\/1590759325815-465x465.jpg","caption":"Chad Lopez"},"description":"Chad Lopez works within Esri's Imagery and Remote Sensing team specializing in drone solutions. Chad has worked at Esri since 2018 and holds a GIS Professional Certification (GISP), a Part 107 Remote Pilot Certificate, and a Master of Science in GIS from the University of Redlands. Chad also teaches GIS part time at several higher education institutions in Southern California. Chad is based in Esri's Redlands, California office.","sameAs":["https:\/\/www.linkedin.com\/in\/chadlopez2015\/"],"jobTitle":"Solution Engineer","url":"https:\/\/www.esri.com\/arcgis-blog\/author\/clopez"}]}},"text_date":"October 2, 2026","author_name":"Multiple Authors","author_page":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/classify-point-clouds-using-embedding-based-image-analysis","custom_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2026\/10\/Lidarblogbanner.jpg","primary_product":"ArcGIS Pro","tag_data":[{"term_id":757081,"name":"deep learning models","slug":"deep-learning-models","term_group":0,"term_taxonomy_id":757081,"taxonomy":"post_tag","description":"","parent":0,"count":4,"filter":"raw"},{"term_id":781242,"name":"embeddings","slug":"embeddings","term_group":0,"term_taxonomy_id":781242,"taxonomy":"post_tag","description":"","parent":0,"count":2,"filter":"raw"},{"term_id":24381,"name":"Lidar","slug":"lidar","term_group":0,"term_taxonomy_id":24381,"taxonomy":"post_tag","description":"","parent":0,"count":49,"filter":"raw"}],"category_data":[{"term_id":23771,"name":"3D Visualization & Analytics","slug":"3d-gis","term_group":0,"term_taxonomy_id":23771,"taxonomy":"category","description":"","parent":0,"count":725,"filter":"raw"},{"term_id":770712,"name":"AI","slug":"geoai","term_group":0,"term_taxonomy_id":770712,"taxonomy":"category","description":"","parent":0,"count":82,"filter":"raw"},{"term_id":22931,"name":"Imagery & Remote Sensing","slug":"imagery","term_group":0,"term_taxonomy_id":22931,"taxonomy":"category","description":"","parent":0,"count":812,"filter":"raw"}],"product_data":[{"term_id":36561,"name":"ArcGIS Pro","slug":"arcgis-pro","term_group":0,"term_taxonomy_id":36561,"taxonomy":"product","description":"","parent":0,"count":2174,"filter":"raw"}],"primary_product_link":"https:\/\/www.esri.com\/arcgis-blog\/?s=#&products=arcgis-pro","_links":{"self":[{"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/blog\/2983781","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/blog"}],"about":[{"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/types\/blog"}],"author":[{"embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/users\/314032"}],"replies":[{"embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/comments?post=2983781"}],"version-history":[{"count":16,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/blog\/2983781\/revisions"}],"predecessor-version":[{"id":2983929,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/blog\/2983781\/revisions\/2983929"}],"wp:attachment":[{"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/media?parent=2983781"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/categories?post=2983781"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/tags?post=2983781"},{"taxonomy":"industry","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/industry?post=2983781"},{"taxonomy":"product","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/product?post=2983781"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}