Prototype-Based Low Altitude UAV Semantic Segmentation

2026-04-01

AI Summary

This work addresses the challenges of semantic segmentation for low-altitude UAV imagery, which include large scale variations, complex object boundaries, and limited computational resources on edge devices. The authors propose PBSeg, an efficient prototype-based segmentation framework featuring a novel Prototype-Based Cross-Attention (PBCA) mechanism that significantly reduces computational complexity by exploiting feature redundancy. To simultaneously preserve fine details and enhance semantic understanding, PBSeg integrates deformable convolutions with a context-aware modulation module. Evaluated on the UAVid and UDD6 datasets, the method achieves mIoU scores of 71.86% and 80.92%, respectively, demonstrating both high accuracy and substantially improved inference efficiency, making it well-suited for deployment on resource-constrained UAV platforms.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Learning on the Edge & Model Compression
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Semantic segmentation of low-altitude UAV imagery presents unique challenges due to extreme scale variations, complex object boundaries, and limited computational resources on edge devices. Existing transformer-based segmentation methods achieve remarkable performance but incur high computational overhead, while lightweight approaches struggle to capture fine-grained details in high-resolution aerial scenes. To address these limitations, we propose PBSeg, an efficient prototype-based segmentation framework tailored for UAV applications. PBSeg introduces a novel prototype-based cross-attention (PBCA) that exploits feature redundancy to reduce computational complexity while maintaining segmentation quality. The framework incorporates an efficient multi-scale feature extraction module that combines deformable convolutions (DConv) with context-aware modulation (CAM) to capture both local details and global semantics. Experiments on two challenging UAV datasets demonstrate the effectiveness of the proposed approach. PBSeg achieves 71.86\% mIoU on UAVid and 80.92\% mIoU on UDD6, establishing competitive performance while maintaining computational efficiency. Code is available at https://github.com/zhangda1018/PBSeg.

Problem

• semantic segmentation
• low-altitude UAV
• computational efficiency
• scale variation
• edge devices

Innovation

• prototype-based segmentation
• cross-attention
• deformable convolution
• context-aware modulation
• UAV semantic segmentation