基于稀疏先验的度量尺度单目深度估计用于水下机器人
Metrically Scaled Monocular Depth Estimation through Sparse Priors for Underwater Robots
AI总结：
本研究提出一种融合稀疏深度先验的深度学习模型，解决了移动水下航行器单目图像实时稠密深度估计中的尺度模糊问题，在FLSea等数据集上显著提升了预测精度并实现了嵌入式系统实时部署。
摘要：
在本研究中，我们解决了移动水下航行器基于单目图像的实时稠密深度估计问题。我们构建了一个深度学习模型，该模型融合了来自三角化特征的稀疏深度测量值，以改善深度预测并解决尺度模糊问题。为了允许任意稀疏度的先验输入，我们应用了稠密参数化方法。我们的模型扩展了近期基于单目图像深度估计的最先进方法，使用高效的编码器-解码器主干网络和现代轻量级 transformer 优化阶段来编码全局上下文。该网络以监督方式在朝前看水下数据集 FLSea 上进行训练。在该数据集上的评估结果表明，通过融合稀疏特征先验，深度预测精度得到了显著提升。此外，无需任何重新训练，我们的方法在我们使用潜水员操作的相机装置收集的朝下看数据集上实现了相似的深度预测精度，该数据集是在进行珊瑚礁调查时收集的。该方法实现了实时性能，在笔记本电脑 GPU 上以 160 FPS 运行，在单核 CPU 上以 7 FPS 运行，适合直接部署在嵌入式系统上。本工作的实现已在 https://github.com/ebnerluca/uw_depth 公开。
英文摘要：
In this work, we address the problem of real-time dense depth estimation from monocular images for mobile underwater vehicles. We formulate a deep learning model that fuses sparse depth measurements from triangulated features to improve the depth predictions and solve the problem of scale ambiguity. To allow prior inputs of arbitrary sparsity, we apply a dense parameterization method. Our model extends recent state-of-the-art approaches to monocular image based depth estimation, using an efficient encoder-decoder backbone and modern lightweight transformer optimization stage to encode global context. The network is trained in a supervised fashion on the forward-looking underwater dataset, FLSea. Evaluation results on this dataset demonstrate significant improvement in depth prediction accuracy by the fusion of the sparse feature priors. In addition, without any retraining, our method achieves similar depth prediction accuracy on a downward looking dataset we collected with a diver operated camera rig, conducting a survey of a coral reef. The method achieves real-time performance, running at 160 FPS on a laptop GPU and 7 FPS on a single CPU core and is suitable for direct deployment on embedded systems. The implementation of this work is made publicly available at https://github.com/ebnerluca/uw_depth.
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。
