A Bayesian Based Deep Unrolling Algorithm for Single-Photon Lidar Systems
A Bayesian Based Deep Unrolling Algorithm for Single-Photon Lidar Systems
复制标题
DOI：
10.1109/jstsp.2022.3170228
复制
发表时间：
2022-01
影响因子：
7.5
通讯作者：
JaKeoung Koo;Abderrahim Halimi;S. Mclaughlin
中科院分区：
文献类型：
--
作者：
JaKeoung Koo;Abderrahim Halimi;S. Mclaughlin
在真实的世界应用中部署3D单光子激光雷达成像提出了包括在高噪声环境中成像的多个挑战。已经提出了几种算法来解决这些问题的基础上统计或基于学习的框架。统计方法提供了关于推断参数的丰富信息，但受到假设模型相关性结构的限制，而深度学习方法显示了最先进的性能，但有限的推断保证，阻止了它们在关键应用中的扩展使用。本文将统计贝叶斯算法展开到一种新的深度学习架构中，用于从单光子激光雷达数据进行鲁棒图像重建，即算法的迭代步骤被转换为神经网络层。由此产生的算法受益于基于统计和学习的框架的优点，提供最佳估计，提高网络的可解释性。与现有的基于学习的解决方案相比，所提出的架构需要减少数量的可训练参数，对系统脉冲响应函数的噪声和错误建模更具鲁棒性，并且提供关于估计的更丰富的信息，包括不确定性度量。合成和真实的数据的结果显示竞争力的结果相比，国家的最先进的算法的推理和计算复杂性的质量。
Deploying 3D single-photon Lidar imaging in real world applications presents multiple challenges including imaging in high noise environments. Several algorithms have been proposed to address these issues based on statistical or learning-based frameworks. Statistical methods provide rich information about the inferred parameters but are limited by the assumed model correlation structures, while deep learning methods show state-of-the-art performance but limited inference guarantees, preventing their extended use in critical applications. This paper unrolls a statistical Bayesian algorithm into a new deep learning architecture for robust image reconstruction from single-photon Lidar data, i.e. the algorithm’s iterative steps are converted into neural network layers. The resulting algorithm benefits from the advantages of both statistical and learning based frameworks, providing best estimates with improved network interpretability. Compared to existing learning-based solutions, the proposed architecture requires a reduced number of trainable parameters, is more robust to noise and mismodelling of the system impulse response function, and provides richer information about the estimates including uncertainty measures. Results on synthetic and real data show competitive results regarding the quality of the inference and computational complexity when compared to state-of-the-art algorithms.