The 2nd International Workshop on
Physics Based Vision meets Deep Learning (PBDL)
In Conjunction with ICCV 2019, November 2, Seoul, Korea
Following the success of 1st ICCV Workshop on Physics Based Vision meets Deep Learning (PBDL2017). We propose the 2nd workshop using the same title and topics with ICCV 2019, and co-organize the Hyperspectral City Challenge.

Access the Challenge Dataset

Challenge Dataset can be downloaded from here:

Baidu: Training Set(with the code 'u5qj'), Testing Set(with the code 'krz6').

UvA: Training Set 1, Training Set 2, Testing Set.

The Dataset is for this chanllenge and research purpose only. Commercial use is not permitted.

If participants would like to use dateset in this challenge to produce academic outputs, this document must be cited:

[1]Title: Hyperspectral City V1.0 Dataset and Benchmark

Authors:

Shaodi You, Erqi Huang, Shuaizhe Liang, Yongrong Zheng, Yunxiang Li, Fan Wang, Sen Lin, Qiu Sheng, Xun Cao, Diming Zhang, Yuanjiang Li, Yu Li, Ying Fu, Boxin Shi, Feng Lu, Yinqiang Zheng, Robby T. Tan

Categories: cs.CV

Comments: 8 pages

arXiv: 1907.10270.

E-mail pbdl.ws@outlook.com if you have any technical problems.

Content of The Downloaded Package

In the dataset, you may find a folder for training data.

Train
In the training dataset folder, you will find 367 sub-folders, each of which is named with an index. In each of the folder, you will find four files, which are:

<*.hsd>, <*_cropped.png>, <label_gray.png>, <label_viz.png>

They are: 1. the hyperspectral data file, 2. The RGB visualization of the hyperspectral image, 3. Semantic labelling with the pixel values 0~9, 4. Visualization of the semantic labelling by use different RGB color. The $*$ is the filename which is the same as the folder name.

Test
In the testing dataset, you will find 68 sub-folders. The same as training dataset, each of the sub-folder is named with a file index. In each of the folder, you will find two files, which are:

<*.hsd>, <*_cropped.png>

They are: 1. the hyperspectral data file, 2. The RGB visualization of the hyperspectral image. The $*$ is the filename which is the same as the folder name.

Read Hyperspectral Cubic Dataset
In the dataset package, you will find a MATLAB file named \textit{readHSD.m}, which is the MATLAB code to read the hyperspectral data. The data format is similar as RGB images, the different is the file has 125 channels rather than 3 channels.