The images in this dataset are of actual road scenes captured while unmanned vehicle driving.
If this dataset is provided for research purposes, please see License section below.
Currently the dataset contains 6000 infrared images, visible light images and raw depth maps.
------------------------------------------
infrared images | 6000 | 7.40M
visible light images | 6000 | 396K
raw depth maps | 6000 | 1.11M
------------------------------------------
The raw images in Snow-road dataset are the resolution of 768×576.
We crop the 6000 infrared images, visible light images to the resolution of 256×512 for depth estimation in infrared images and visible light images. Next, the depth map that display on Example are generated by classifying the raw depth map into 32 levels in the logarithmic space.We use the generated depth maps as training and testing labels.
- To preprocess the raw depth map:
python preprocess.py
If you want to use the formatted images,you can load the preprocessed data(.h5 file) in testData
Start with importing package:
import h5py
import matplotlib.pyplot as plt- To load a dataset:
def read_hdf5(file_name):
with h5py.File(file_name, 'r') as f:
images = np.asarray(f['images'])
depths = np.asarray(f['depths'])
infrareds = np.asarray(f['infrareds'])
return images,depths,infrareds
images,depths,infrareds=read_hdf5('test_snow_data.h5')- To display the image of a dataset:
i, j = 0,4
imageTest = images[i:j]
plt.imshow(imageTest[0],cmap='jet')I provide this dataset for research purposes, please follow Citing.
For removal of copyrighted content, please contact me on GitHub.
If you use this dataset in academic work, please cite as follows:
@misc{Yuqi,
title={A dataset of Snow-road},
url={https://github.com/humdingers/Depth-imaget},
author={Yuqi, Li},
year={2019},
publisher = {GitHub},
journal = {GitHub repository}
}