The Cityscapes Dataset for Semantic Urban Scene Understanding

Abstract

Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning. For semantic urban scene understanding, however, no current dataset adequately captures the complexity of real-world urban scenes. To address this, we introduce Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling. Cityscapes is comprised of a large, diverse set of stereo video sequences recorded in streets from 50 different cities. 5000 of these images have high quality pixel-level annotations; 20 000 additional images have coarse annotations to enable methods that leverage large volumes of weakly-labeled data. Crucially, our effort exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity. Our accompanying empirical study provides an in-depth analysis of the dataset characteristics, as well as a performance evaluation of several state-of-the-art approaches based on our benchmark.

Automatic Discovery and Geotagging of Objects from Street View Imagery

“…The image segmentation pipeline for traffic lights is trained on data from two publicly available datasets with pixel-level annotations: Mapillary Vistas [45] and Cityscapes [46]. We crop/resize the images to match the standard GSV image size of 640 × 640.…”

“…We then train our FCNN to detect all tall poles-utilities and lampposts-by combining public datasets Mapillary Vistas [45] and Cityscapes [46] with the dataset prepared in the previous step. The inclusion of public datasets allows us to dramatically increase robustness with respect to background objects, which are largely underrepresented in the dataset prepared above with outlines of poles.…”

Processing of Crawled Urban Imagery for Building Use Classification

“…Likewise, the CITYSCAPES dataset provided by (Cordts et al, 2016) contains scenes from 50 cities with corresponding semantic pixelwise annotations for each frame, obtained by a windshieldmounted stereo camera system. For these datasets, GPS information of the car's trajectory is available.…”

Quantifying Urban Surroundings Using Deep Learning Techniques: A New Proposal

“…The author of PSPNet has made training weights and the architecture of the model available for use in research purposes. The PSPNet architecture is trained on Pascal VOC [41], Cityscapes [42], and ADE20K [43] datasets. These datasets have been widely used and researched in studies related to street view segmentation.…”