/ELSED

ELSED: Enhanced Line SEgment Drawing

Primary LanguageJupyter NotebookApache License 2.0Apache-2.0

Graffter Banner

ELSED: Enhanced Line SEgment Drawing

Open in Colab arXiv Project Page

This repository contains the source code of ELSED: Enhanced Line SEgment Drawing the fastest line segment detector in the literature. It is ideal for resource-limited devices like drones of smartphones. Visit the Project Webpage to try it online!

Graffter header image

Dependencies

The code depends on OpenCV (tested with version 4.1.1).

To install OpenCV ... In Ubuntu 18.04 compile it from sources with the following instructions:
# Install dependencies (Ubuntu 18.04)
sudo apt-get install -y build-essential cmake git libgtk2.0-dev pkg-config libavcodec-dev libavformat-dev libswscale-dev
# Download source code
git clone https://github.com/opencv/opencv.git --branch 4.1.1 --depth 1
# Create build directory
cd opencv && mkdir build && cd build
# Generate makefiles, compile and install
cmake -D CMAKE_BUILD_TYPE=RELEASE -D CMAKE_INSTALL_PREFIX=/usr/local ..
make -j
sudo make install

Compile and Run

The code contains a demo detecting large and short line segments in one image. The code can be compiled with Cmake:

mkdir build && cd build
cmake .. && make
./elsed_main

The result for the provided image should be:

******************************************************
******************* ELSED main demo ******************
******************************************************
ELSED detected: 305 (large) segments
ELSED detected: 391 (short) segments

Cite

@article{suarez2022elsed,
      title={ELSED: Enhanced Line SEgment Drawing}, 
      author={Iago Suárez and José M. Buenaposada and Luis Baumela},
      journal = {Pattern Recognition},
      volume = {127},
      pages = {108619},
      year = {2022},
      issn = {0031-3203},
      doi = {https://doi.org/10.1016/j.patcog.2022.108619},
      url = {https://www.sciencedirect.com/science/article/pii/S0031320322001005}
}