The CAMO_UOW dataset is used for camouflaged foreground detection (background subtraction). It contains 10 (high resolution) videos captured in real scenes including both in-door and out-door cases. In each video, one or two persons appear in the scene wearing clothes in the similar colour as the background. Ground truth foreground masks are manually labelled for all the frames and provided in the dataset. More details can be found in the following papers.
Please cite the following papers if you use the dataset.
S. Li, D. Florencio, Y. Zhao, C. Cook, W. Li, "Foreground detection in camouflaged scenes", IEEE International Conference on Image Processing, ICIP 2017, Beijing, China, September 2017.
S. Li, D. Florencio, W. Li, Y. Zhao, C. Cook, "A Fusion Framework for camouflaged moving foreground detection in the wavelet domain", IEEE Transactions on Image Processing, (to appear) 2018.