一种用于实时单目视觉里程计的基于注意力的深度学习架构：在无GPS无人机导航中的应用
An Attention-Based Deep Learning Architecture for Real-Time Monocular Visual Odometry: Applications to GPS-free Drone Navigation
AI总结：
本文提出一种结合CNN、LSTM与多头注意力模块的实时单目视觉里程计深度学习架构，用于无GPS无人机导航，相比传统RNN模型收敛更快且显著降低了轨迹误差。
摘要：
无人机在工业、医疗、研究、灾害救援、国防和安全等领域的应用日益广泛。在无GPS环境中的导航等技术挑战阻碍了其进一步普及。视觉里程计的研究正在不断推进，有望解决无GPS导航问题。传统的视觉里程计方法采用基于几何的流程，虽然流行，但常受误差累积和高计算需求的困扰。近期利用深度神经网络的研究已展现出性能提升，解决了这些缺陷。深度视觉里程计通常采用卷积神经网络和循环神经网络等序列建模网络来解析场景并从视频序列中推导视觉里程计。本文提出了一种用于无人机的新型实时单目视觉里程计模型，采用带有自注意力模块的深度神经架构。它利用连续视频帧估计无人机上相机的自运动。推理工具处理实时视频流，采用深度学习估计无人机的轨迹。该架构结合了用于图像特征提取的CNN，以及带有多头注意力模块用于视频序列建模的长短期记忆网络。在两个视觉里程计数据集上进行测试，该模型比先前的RNN模型收敛速度快48%，平均平移漂移减少了22%，平均平移绝对轨迹误差改善了12%，展示了对噪声的更强鲁棒性。
英文摘要：
Drones are increasingly used in fields like industry, medicine, research, disaster relief, defense, and security. Technical challenges, such as navigation in GPS-denied environments, hinder further adoption. Research in visual odometry is advancing, potentially solving GPS-free navigation issues. Traditional visual odometry methods use geometry-based pipelines which, while popular, often suffer from error accumulation and high computational demands. Recent studies utilizing deep neural networks (DNNs) have shown improved performance, addressing these drawbacks. Deep visual odometry typically employs convolutional neural networks (CNNs) and sequence modeling networks like recurrent neural networks (RNNs) to interpret scenes and deduce visual odometry from video sequences. This paper presents a novel real-time monocular visual odometry model for drones, using a deep neural architecture with a self-attention module. It estimates the ego-motion of a camera on a drone, using consecutive video frames. An inference utility processes the live video feed, employing deep learning to estimate the drone's trajectory. The architecture combines a CNN for image feature extraction and a long short-term memory (LSTM) network with a multi-head attention module for video sequence modeling. Tested on two visual odometry datasets, this model converged 48% faster than a previous RNN model and showed a 22% reduction in mean translational drift and a 12% improvement in mean translational absolute trajectory error, demonstrating enhanced robustness to noise.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
