Paper Reading AI Learner

DroneKey: Drone 3D Pose Estimation in Image Sequences using Gated Key-representation and Pose-adaptive Learning

2025-08-25 07:40:31
Seo-Bin Hwang, Yeong-Jun Cho

Abstract

Estimating the 3D pose of a drone is important for anti-drone systems, but existing methods struggle with the unique challenges of drone keypoint detection. Drone propellers serve as keypoints but are difficult to detect due to their high visual similarity and diversity of poses. To address these challenges, we propose DroneKey, a framework that combines a 2D keypoint detector and a 3D pose estimator specifically designed for drones. In the keypoint detection stage, we extract two key-representations (intermediate and compact) from each transformer encoder layer and optimally combine them using a gated sum. We also introduce a pose-adaptive Mahalanobis distance in the loss function to ensure stable keypoint predictions across extreme poses. We built new datasets of drone 2D keypoints and 3D pose to train and evaluate our method, which have been publicly released. Experiments show that our method achieves an AP of 99.68% (OKS) in keypoint detection, outperforming existing methods. Ablation studies confirm that the pose-adaptive Mahalanobis loss function improves keypoint prediction stability and accuracy. Additionally, improvements in the encoder design enable real-time processing at 44 FPS. For 3D pose estimation, our method achieved an MAE-angle of 10.62°, an RMSE of 0.221m, and an MAE-absolute of 0.076m, demonstrating high accuracy and reliability. The code and dataset are available at this https URL.

Abstract (translated)

估算无人机的3D姿态对于反无人机系统至关重要,但现有的方法在处理无人机关键点检测的独特挑战时遇到了困难。无人机螺旋桨作为关键点,但由于其视觉相似性和姿势多样性的原因,它们难以被准确识别出来。为了解决这些挑战,我们提出了DroneKey框架,该框架结合了专门针对无人机设计的2D关键点检测器和3D姿态估计器。 在关键点检测阶段,我们从每个Transformer编码层中提取两种关键表示(中间和紧凑型),并通过门控求和来优化地将它们结合起来。此外,我们在损失函数中引入了一种姿势自适应Mahalanobis距离,以确保极端姿态下的稳定的关键点预测。 为了训练和评估我们的方法,我们建立并公开发布了一系列无人机2D关键点及3D姿态的新数据集。实验结果表明,在关键点检测方面(OKS标准),我们的方法达到了99.68%的AP值,超过了现有技术的表现。消融研究证实了姿势自适应Mahalanobis损失函数在提高关键点预测稳定性和准确性方面的有效性。 此外,编码器设计的改进使得实时处理能力达到了每秒44帧。对于3D姿态估计,我们的方法实现了10.62°的MAE角度误差、0.221m的RMSE以及0.076m的MAE绝对值误差,展示了其高准确性和可靠性。 代码和数据集可以在以下链接获取:[提供链接]

URL

https://arxiv.org/abs/2508.17746

PDF

https://arxiv.org/pdf/2508.17746.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot