Data underlying the publication: Addressing Camera Sensors Faults in Vision-Based Navigation: Simulation and Dataset Development

The present dataset is designed to be used in training and testing of AI algorithms for the detection of failures in space camera sensors. It contains simulated images generated from the camera sensor of a sample vehicle for Small Solar System Bodies exploration. The images depict various simulated faults as described in the related publication, and are accompanied by labelling masks, which can be used for both classification and segmentation tasks.The dataset is intended to support the development of AI applications that can be implemented onboard to improve the reliability of vision-based navigation systems. We encourage the research community to utilise this dataset and enhance it through further advancements.本数据集专为训练与测试用于探测太空相机传感器故障的人工智能算法而设计。其包含源自小太阳系天体探测样例航天器相机传感器的仿真图像。这些图像呈现了相关出版物中记载的各类仿真故障，并附带标注掩码（labelling masks），可同时适配分类与分割任务。本数据集旨在支持可部署于航天器机载端的人工智能应用开发，以提升基于视觉的导航系统的可靠性。我们诚挚呼吁学术界使用本数据集，并通过后续技术演进对其进行优化完善。