Skip to main content
. 2019 Oct 16;19(20):4484. doi: 10.3390/s19204484

Table 3.

Description of the complete dataset used to train our model. Columns represent the category of the images, the number of complete images used, the size of each image and the resultant number of 64×64 patches used to train the algorithm.

Category Images Size Total Patches
Blizzard (BW) 195 1216 × 704 40,755
Skating (BW) 177 1216 × 704 36,993
Snowfall (BW) 192 1216 × 704 40,128
Canoe (DBG) 210 640 × 384 12,600
Sofa (IOM) 1 150 320 × 192 6750

1 Only used for metrics evaluation.