Autonomous vehicles and robots require increasingly more robustness and reliability to meet the demands of modern tasks. These requirements specially apply to cameras onboard such vehicles because they are the predominant sensors to acquire information about the environment and support actions. Cameras must maintain proper functionality and take automatic countermeasures if necessary. However, few works examine the practical use of a general condition monitoring approach for cameras and designs countermeasures in the context of an envisaged high-level application. We propose a generic and interpretable self-health-maintenance framework for cameras based on data- and physically-grounded models. To this end, we determine two reliable, real-time capable estimators for typical image effects of a camera in poor condition (blur, noise phenomena and most common combinations) by comparing traditional and retrained machine learning-based approaches in extensive experiments. Furthermore, we demonstrate on a real-world ground vehicle how one can adjust the camera parameters to achieve optimal whole-system capability based on experimental (non-linear and non-monotonic) input-output performance curves, using object detection, motion blur and sensor noise as examples. Our framework not only provides a practical ready-to-use solution to evaluate and maintain the health of cameras, but can also serve as a basis for extensions to tackle more sophisticated problems that combine additional data sources (e.g., sensor or environment parameters) empirically in order to attain fully reliable and robust machines.

翻译：自主车辆和机器人需具备日益增强的鲁棒性与可靠性以应对现代任务需求。这些要求尤其适用于车载相机，因其作为获取环境信息并支撑行为决策的主要传感器，必须保持正常运行状态，并在必要时采取自动应对措施。然而，现有研究鲜少从实际应用角度探讨相机通用状态监测方法，亦未结合高层级应用场景设计相应应对策略。本文提出一种基于数据驱动与物理模型的通用可解释相机自健康维护框架。为达成此目标，我们通过传统方法与基于重训练机器学习方法的广泛实验对比，确定了两种适用于实时场景的可靠估计器，用于检测相机低照状态下的典型图像效应（模糊、噪声现象及常见组合）。此外，以目标检测、运动模糊和传感器噪声为例，基于实验获得的非线性非单调输入-输出性能曲线，我们在真实地面车辆上展示了如何调整相机参数以实现系统整体最优性能。本框架不仅提供了即用型相机健康评估与维护的实践方案，还可作为扩展基础，通过实证结合多源数据（如传感器参数或环境参数），解决更复杂问题，最终实现完全可靠与鲁棒的机器系统。