This is a simple, small C++ implementation of Selective Search [1, 2] that can be easily integrated into your projects.
For initial segmentation, this implementation uses Efficient Graph-Based Image Segmentation [3].
- Visual Studio 2013 / GCC 4.8 / Clang 3.2 or later
- This implementation relies on C++11 features.
- OpenCV (2.4.9-)
You can test this implementation as:
% ./test
To include it in your project, you just need to:
#include "selective_search.hpp"
...
// Get object proposals
auto proposals = ss::selectiveSearch( img, scale, sigma, minSize, smallest, largest, distorted );
MIT
[1] J. R. R. Uijlings et al., "Selective Search for Object Recognition", IJCV, 2013
[2] K. E. A. van de Sande et al., "Segmentation As Selective Search for Object Recognition", ICCV, 2011
[3] P. Felzenszwalb et al., "Efficient Graph-Based Image Segmentation", IJCV, 2004