graviti logo产品公开数据集关于我们
Demo演示登录
866
0
28
KITTI-Sceneflow
概要
讨论
代码
活动
33c7fecb-8ce2-11eb-b816-506b4b419b4c
16c3966·
Jun 28, 2021 12:03 AM
·1Commits

Overview

The sceneflow 2015 benchmark consists of 200 training scenes and 200 test scenes (4 color images per scene, saved in loss less png format). It comprises dynamic scenes for which the ground truth has been established in a semi-automatic process. Our evaluation server computes the percentage of bad pixels averaged over all ground truth pixels of all 200 test images. For this benchmark, we consider a pixel to be correctly estimated if the disparity or flow end-point error is <3px or <5% (for scene flow this criterion needs to be fulfilled for both disparity maps and the flow map). We require that all methods use the same parameter set for all test pairs. Our development kit provides details about the data format as well as MATLAB / C++ utility functions for reading and writing disparity maps and flow fields. More details can be found in Object Scene Flow for Autonomous Vehicles (CVPR 2015).

Data Collection

We equipped a standard station wagon with two high-resolution color and grayscale video cameras. Accurate ground truth is provided by a Velodyne laser scanner and a GPS localization system. Our datsets are captured by driving around the mid-size city of Karlsruhe, in rural areas and on highways. Up to 15 cars and 30 pedestrians are visible per image.

img

Citation

Please use the following citation when referencing the dataset:

@ARTICLE{Menze2018JPRS,
  author = {Moritz Menze and Christian Heipke and Andreas Geiger},
  title = {Object Scene Flow},
  journal = {ISPRS Journal of Photogrammetry and Remote Sensing (JPRS)},
  year = {2018}
}
@INPROCEEDINGS{Menze2015ISA,
  author = {Moritz Menze and Christian Heipke and Andreas Geiger},
  title = {Joint 3D Estimation of Vehicles and Scene Flow},
  booktitle = {ISPRS Workshop on Image Sequence Analysis (ISA)},
  year = {2015}
}
🎉感谢Hello Dataset的贡献
数据集信息
应用场景暂无
标注类型暂无
任务类型暂无
LicenseCC BY-NC-SA 3.0
更新时间2020-12-31 17:27:50
数据概要
数据格式暂无
数据数量1.6K
已标注数量0
文件大小18MB
版权归属方
Max Planck Institute for Intellgent Systems
标注方
未知
了解更多和支持
立即开始构建AI
免费开始联系我们