PulseAugur
EN
LIVE 22:00:19

AWS and Vexcel enable natural language search for aerial imagery

AWS has partnered with Vexcel Group Inc. to develop a system that makes vast libraries of aerial imagery searchable using natural language. This solution leverages multimodal AI, specifically Amazon Nova Multimodal Embeddings, and vector search capabilities on AWS services like Amazon Bedrock and Amazon OpenSearch Serverless. The approach eliminates the need for manual inspection or training custom computer vision models for each specific search query, transforming Vexcel's extensive aerial data into a product called Vexcel Intelligence. AI

IMPACT Enables more efficient querying and analysis of large-scale geospatial data for various industries.

RANK_REASON This describes a product built on existing AI capabilities and cloud infrastructure, rather than a novel AI model release or research breakthrough.

Read on AWS Machine Learning Blog →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

AWS and Vexcel enable natural language search for aerial imagery

COVERAGE [1]

  1. AWS Machine Learning Blog TIER_1 English(EN) · Gilbert V Lepadatu ·

    Embed the world: Multimodal AI for searchable aerial imagery at scale

    In this post, we walk through the problem space, our architecture on Amazon Bedrock and Amazon OpenSearch Serverless, the evaluation methodology we built on OpenStreetMap ground truth, four experiments that compared embedding models, fusion strategies, captioning, and search meth…