CityPersons: A Diverse Dataset for Pedestrian Detection. 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.
Keywords for this software
References in zbMATH (referenced in 3 articles )
Showing results 1 to 3 of 3.
- Samsonov, N. A.; Gneushev, A. N.; Matveev, I. A.: Training a classifier by descriptors in the space of the Radon transform (2020)
- Sharma, Vipul; Mir, Roohie Naaz: A comprehensive and systematic look up into deep learning based object detection techniques: a review (2020)
- Holger Caesar, Varun Bankiti, Alex H. Lang, Sourabh Vora, Venice Erin Liong, Qiang Xu, Anush Krishnan, Yu Pan, Giancarlo Baldan, Oscar Beijbom: nuScenes: A multimodal dataset for autonomous driving (2019) arXiv