Semantically Aware UAV Landing Site Assessment from Remote Sensing Imagery via Multimodal Large Language Models

TL;DR

This paper introduces a novel framework combining remote sensing imagery and multimodal large language models to assess UAV emergency landing sites, focusing on semantic risks beyond geometric features, validated by a new benchmark dataset.

Contribution

The paper presents a new multimodal approach for UAV landing site assessment that integrates semantic segmentation and language reasoning, outperforming traditional geometric methods.

Findings

Significantly improved risk detection accuracy over geometric baselines

Ability to generate human-like, interpretable justifications

Validated on the newly constructed ELSS benchmark dataset

Abstract

Safe UAV emergency landing requires more than just identifying flat terrain; it demands understanding complex semantic risks (e.g., crowds, temporary structures) invisible to traditional geometric sensors. In this paper, we propose a novel framework leveraging Remote Sensing (RS) imagery and Multimodal Large Language Models (MLLMs) for global context-aware landing site assessment. Unlike local geometric methods, our approach employs a coarse-to-fine pipeline: first, a lightweight semantic segmentation module efficiently pre-screens candidate areas; second, a vision-language reasoning agent fuses visual features with Point-of-Interest (POI) data to detect subtle hazards. To validate this approach, we construct and release the Emergency Landing Site Selection (ELSS) benchmark. Experiments demonstrate that our framework significantly outperforms geometric baselines in risk identification accuracy. Furthermore, qualitative results confirm its ability to generate human-like, interpretable justifications, enhancing trust in automated decision-making. The benchmark dataset is publicly accessible at https://anonymous.4open.science/r/ELSS-dataset-43D7.