Leveraging YOLO-World and GPT-4V LMMs for Zero-Shot Person Detection and Action Recognition in Drone Imagery

TL;DR

This paper investigates the use of zero-shot Large Multimodal Models, YOLO-World and GPT-4V, for person detection and action recognition in drone imagery, highlighting their potential and limitations in aerial perception tasks.

Contribution

It is the first study to evaluate LMMs like YOLO-World and GPT-4V for drone-based perception, demonstrating their capabilities and challenges in zero-shot person detection and scene understanding.

Findings

YOLO-World shows good detection performance.

GPT-4V effectively filters region proposals and describes scenes.

GPT-4V has limited accuracy in classifying actions.

Abstract

In this article, we explore the potential of zero-shot Large Multimodal Models (LMMs) in the domain of drone perception. We focus on person detection and action recognition tasks and evaluate two prominent LMMs, namely YOLO-World and GPT-4V(ision) using a publicly available dataset captured from aerial views. Traditional deep learning approaches rely heavily on large and high-quality training datasets. However, in certain robotic settings, acquiring such datasets can be resource-intensive or impractical within a reasonable timeframe. The flexibility of prompt-based Large Multimodal Models (LMMs) and their exceptional generalization capabilities have the potential to revolutionize robotics applications in these scenarios. Our findings suggest that YOLO-World demonstrates good detection performance. GPT-4V struggles with accurately classifying action classes but delivers promising results in filtering out unwanted region proposals and in providing a general description of the scenery. This research represents an initial step in leveraging LMMs for drone perception and establishes a foundation for future investigations in this area.