Edge-Optimized Multimodal Learning for UAV Video Understanding via BLIP-2

TL;DR

This paper introduces a lightweight multimodal platform based on BLIP-2, integrated with YOLO models, enabling real-time UAV video understanding with minimal resource use and no task-specific fine-tuning.

Contribution

It presents a novel integration of BLIP-2 with YOLO models, along with a content-aware frame sampling and prompt optimization for efficient UAV video analysis.

Findings

Achieved real-time object detection and segmentation on UAV videos.

Enhanced visual-attention understanding and reasoning capabilities.

Maintained high accuracy with minimal computational resources.

Abstract

The demand for real-time visual understanding and interaction in complex scenarios is increasingly critical for unmanned aerial vehicles. However, a significant challenge arises from the contradiction between the high computational cost of large Vision language models and the limited computing resources available on UAV edge devices. To address this challenge, this paper proposes a lightweight multimodal task platform based on BLIP-2, integrated with YOLO-World and YOLOv8-Seg models. This integration extends the multi-task capabilities of BLIP-2 for UAV applications with minimal adaptation and without requiring task-specific fine-tuning on drone data. Firstly, the deep integration of BLIP-2 with YOLO models enables it to leverage the precise perceptual results of YOLO for fundamental tasks like object detection and instance segmentation, thereby facilitating deeper visual-attention understanding and reasoning. Secondly, a content-aware key frame sampling mechanism based on K-Means clustering is designed, which incorporates intelligent frame selection and temporal feature concatenation. This equips the lightweight BLIP-2 architecture with the capability to handle video-level interactive tasks effectively. Thirdly, a unified prompt optimization scheme for multi-task adaptation is implemented. This scheme strategically injects structured event logs from the YOLO models as contextual information into BLIP-2's input. Combined with output constraints designed to filter out technical details, this approach effectively guides the model to generate accurate and contextually relevant outputs for various tasks.