Skip to content

Commit

Permalink
updated README with link to paper
Browse files Browse the repository at this point in the history
  • Loading branch information
jingdao committed Dec 19, 2019
1 parent 1ff0156 commit f93ca0a
Show file tree
Hide file tree
Showing 2 changed files with 33 additions and 1 deletion.
30 changes: 29 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
@@ -1,9 +1,37 @@
# CNN-based Person Detection using Infrared Images for Night-time Intrusion Warning Systems

Supplemental material for the **Sensors** journal submission *CNN-based Person Detection using Infrared Images for Night-time Intrusion Warning Systems*.
Supplemental material for the **Sensors** journal paper *CNN-based Person Detection using Infrared Images for Night-time Intrusion Warning Systems*.
The paper can be accessed through the following [link](https://www.mdpi.com/1424-8220/20/1/34).
If you find this code or data useful, please cite our paper as follows:

```
Park, J.; Chen, J.; Cho, Y.K.; Kang, D.Y.; Son, B.J. CNN-Based Person Detection Using Infrared Images for Night-Time Intrusion Warning Systems. Sensors 2020, 20, 34.
```

```
@Article{s20010034,
AUTHOR = {Park, Jisoo and Chen, Jingdao and Cho, Yong K. and Kang, Dae Y. and Son, Byung J.},
TITLE = {CNN-Based Person Detection Using Infrared Images for Night-Time Intrusion Warning Systems},
JOURNAL = {Sensors},
VOLUME = {20},
YEAR = {2019},
NUMBER = {1},
ARTICLE-NUMBER = {34},
URL = {https://www.mdpi.com/1424-8220/20/1/34},
ISSN = {1424-8220},
ABSTRACT = {Night-time surveillance is important for safety and security purposes. For this reason, several studies have attempted to automatically detect people intruding into restricted areas by using i$
DOI = {10.3390/s20010034}
}
```

## Data preparation

To download the *university* dataset, use this Dropbox [link](https://www.dropbox.com/s/3n4y112uhsonx8a/university_data.zip?dl=1) or run the following script:

```
./download_data.sh
```

To prepare a new dataset, first create a subfolder under the "dataset" folder (e.g. dataset/myfolder).
Copy the image files to this subfolder using the naming scheme 1.png 2.png 3.png ... etc.
Next, create a file "params.txt" in the subfolder with a single line containing the values \[xOffset\] \[yOffset\] \[cropSize\].
Expand Down
4 changes: 4 additions & 0 deletions download_data.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
#!/bin/bash

wget -O university_data.zip https://www.dropbox.com/s/3n4y112uhsonx8a/university_data.zip?dl=1
unzip university_data.zip -d dataset/university

0 comments on commit f93ca0a

Please sign in to comment.