Leveraging YOLO-World and GPT-4V LMMs for Zero-Shot Person Detection and Action Recognition in Drone Imagery
This addresses the problem of resource-intensive data acquisition for drone perception in robotics, though it is an incremental step in applying existing LMMs to a new domain.
The paper tackled person detection and action recognition in drone imagery using zero-shot large multimodal models (LMMs), finding that YOLO-World showed good detection performance while GPT-4V struggled with action classification but aided in filtering and scene description.
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.