DeepAI
Log In Sign Up

The Cityscapes Dataset for Semantic Urban Scene Understanding

04/06/2016
by   Marius Cordts, et al.
0

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; 20000 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.

READ FULL TEXT

page 15

page 16

page 21

page 25

page 26

page 27

page 28

page 29

11/10/2015

Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer

Semantic annotations are vital for training models for object recognitio...
07/12/2020

SkyScapes – Fine-Grained Semantic Understanding of Aerial Scenes

Understanding the complex urban infrastructure with centimeter-level acc...
09/10/2018

PedX: Benchmark Dataset for Metric 3D Pose Estimation of Pedestrians in Complex Urban Intersections

This paper presents a novel dataset titled PedX, a large-scale multimoda...
03/29/2022

Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation

Large-scale training data with high-quality annotations is critical for ...
02/12/2019

A system for generating complex physically accurate sensor images for automotive applications

We describe an open-source simulator that creates sensor irradiance and ...
03/11/2022

Peng Cheng Object Detection Benchmark for Smart City

Object detection is an algorithm that recognizes and locates the objects...
02/04/2022

StandardSim: A Synthetic Dataset For Retail Environments

Autonomous checkout systems rely on visual and sensory inputs to carry o...

Code Repositories

SMSnet

Model-evaluator of Publication : "SMSnet: Semantic Motion Segmentation using Deep Convolutional Neural Networks"


view repo