The USyd Campus Dataset

Vision and lidar are complementary sensors that are incorporated into many applications of intelligent transportation systems. These sensors have been used to great effect in research related to perception, navigation and deep-learning applications. Despite this success, the validation of algorithm robustness has recently been recognised as a major challenge for the massive deployment of these new technologies. It is well known that algorithms and models trained or tested with a particular dataset tend not to generalise well for other scenarios. For certain applications, autonomous vehicles in particular, algorithm failures can lead to potentially catastrophic consequences. To minimise this risk, it is essential to evaluate the robustness and reliability of algorithms before deploying them in real life applications. This paper presents a long-term, large-scale dataset collected over the period of 1.5 years on a weekly basis over the University of Sydney campus and surrounds. The USyd Campus Dataset has been designed to aid in the development, validation and testing of algorithm robustness under a wide variety of conditions. It includes multiple sensor modalities and covers various environmental conditions as well as diverse changes to illumination, scene structure, and pedestrian/vehicle traffic volumes. The dataset also includes a semantic segmentation dataset with different illumination conditions and camera perspectives, and a ‘Road’ class image dataset which is automatically generated using lidar. To facilitate the dataset use by researchers and practitioners, we also provide a set of development tools for the analysis and visualisation of the dataset.