ChatGPT as a mapping assistant: A novel method to enrich maps with generative AI and content derived from street-level photographs
This addresses mapping efficiency for geographic information systems, but it is incremental as it applies existing AI models to new data without modifying them.
This paper tackles the problem of inefficient collaborative mapping by using generative AI to suggest tags for OpenStreetMap from street-level photographs, achieving accuracy improvements of up to 29% with detailed descriptions and up to 20% with prompt engineering and context.
This paper explores the concept of leveraging generative AI as a mapping assistant for enhancing the efficiency of collaborative mapping. We present results of an experiment that combines multiple sources of volunteered geographic information (VGI) and large language models (LLMs). Three analysts described the content of crowdsourced Mapillary street-level photographs taken along roads in a small test area in Miami, Florida. GPT-3.5-turbo was instructed to suggest the most appropriate tagging for each road in OpenStreetMap (OSM). The study also explores the utilization of BLIP-2, a state-of-the-art multimodal pre-training method as an artificial analyst of street-level photographs in addition to human analysts. Results demonstrate two ways to effectively increase the accuracy of mapping suggestions without modifying the underlying AI models: by (1) providing a more detailed description of source photographs, and (2) combining prompt engineering with additional context (e.g. location and objects detected along a road). The first approach increases the suggestion accuracy by up to 29%, and the second one by up to 20%.