Multiple View and Varying Illumination Dataset
Lincoln Field Dataset
Multiple View and Varying Illumination Dataset - Download
You may download it and use it freely for research purposes with acknowledgement.
This dataset was collected to evaluate multiple view change detection algorithms under greatly varying illumination. Thousands of pictures were taken at a Brown University quadrangle, the Lincoln Field, three times a day and three times a week for 6 months, between April and November, 2006. The Lincoln Field dataset is challenging for background subtraction algorithms due to varying viewing angles, occlusions and illumination changes.
The scene was observed by roughly 6 viewpoints and its geometry is composed of a low curvature ground (grass and concrete), buildings, trees, bushes and lampposts. Dynamic foreground objects include vehicles, trash cans, people, objects etc.
Many illumination changes are observed due to Sun's position, clouds, overcast weather and rain. These phenomenon affects the shadows location, relative intensity and also color.
Over one hundred accurate differential GPS measurements are provided for the scene and can be used for image registration. Nearly 900 images are calibrated. Ground truth masks for 24 images are provided for performance tests.For more information see the README file.
|
|
Lincoln Field Dataset Calibrated |
Lincoln Field Dataset Unprocessed |
|
| Undistorted images | Original images | ||
| 870 images | 3742 images | ||
| Calibrated cameras | No estimated cameras | ||
 |
|