From a0f930bc2abdfba356817846b4190c31a1098624 Mon Sep 17 00:00:00 2001 From: Takayuki Tozawa Date: Thu, 19 Aug 2021 11:23:13 +0900 Subject: [PATCH] Fixed typo. --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index b9979f6..8ab3e0a 100644 --- a/README.md +++ b/README.md @@ -2,14 +2,14 @@ ## Overview -According to [the census by R&A](https://www.randa.org/~/media/Files/DownloadsAndPublications/Golf-around-the-world-2017.ashx), there are more than 30,000 golf courses all over the world. They are good targets for research of automatic object detection due to their specific shape, world-wide distibution and common size. **MUSIC** for GC (**G**olf **C**ourse) is the dataset to support the global survey of golf courses based on satellite imagery. +According to [the census by R&A](https://www.randa.org/~/media/Files/DownloadsAndPublications/Golf-around-the-world-2017.ashx), there are more than 30,000 golf courses all over the world. They are good targets for research of automatic object detection due to their specific shape, world-wide distribution and common size. **MUSIC** for GC (**G**olf **C**ourse) is the dataset to support the global survey of golf courses based on satellite imagery. First, we have created several KML files for polygons which cover all the golf courses in Japan. Next, [Landsat-8](https://landsat.usgs.gov/landsat-8) multiband images of these target areas were cropped into a 16 × 16 grids. These patch images are classified as “positives” if the golf course cover more than 20% of the total areas, while patches with no golf course are classified as “negatives”. The rest with the intermediate coverage (0~20%) were neither “positives” and “negatives”. ![fig:MUSIC4GC image example](https://github.com/gistairc/MUSIC4GC/blob/master/fig0.png "Original polygons in a Landsat-8 scene") -You can download the **MUSIC** for GC dataset from [here](http://data.airc.aist.go.jp/MUSIC4GC/MUSIC4GC.zip) (375MB). More detailed exaplanations can be found in the following papers. +You can download the **MUSIC** for GC dataset from [here](http://data.airc.aist.go.jp/MUSIC4GC/MUSIC4GC.zip) (375MB). More detailed explanations can be found in the following papers. [1] *Uehara, K., H. Sakanashi, H. Nosato, M. Murakawa, H. Miyamoto, and R. Nakamura, “Object Detection of Satellite Images Using Multi-Channel Higher-order Local Autocorrelation”, IEEE International Conference on Systems, Man and Cybernetics doi:10.1109/SMC.2017.8122799* ([paper](http://arxiv.org/abs/1707.09099))