CityPersons: A Diverse Dataset for Pedestrian Detection
This work addresses pedestrian detection for autonomous driving by providing a dataset that enhances generalization across benchmarks, though it is incremental as it builds on existing methods and datasets.
The authors tackled pedestrian detection by introducing CityPersons, a diverse dataset built on Cityscapes, and adapted FasterRCNN to achieve state-of-the-art results on Caltech, with improvements in handling occlusion and small-scale cases.
Convnets have enabled significant progress in pedestrian detection recently, but there are still open questions regarding suitable architectures and training data. We revisit CNN design and point out key adaptations, enabling plain FasterRCNN to obtain state-of-the-art results on the Caltech dataset. To achieve further improvement from more and better data, we introduce CityPersons, a new set of person annotations on top of the Cityscapes dataset. The diversity of CityPersons allows us for the first time to train one single CNN model that generalizes well over multiple benchmarks. Moreover, with additional training with CityPersons, we obtain top results using FasterRCNN on Caltech, improving especially for more difficult cases (heavy occlusion and small scale) and providing higher localization quality.