Feature Detection Classes
Model BSHRK-W-BFD-11 is trained to detect the footprint of buildings. BSHRK-W-BFD-11 is capable of detecting buildings from aerial image input and producing a high-quality probability heatmap of buildings. The image can then be vectorized for an accurate representation of building footprints.
Model BSHRK-W-VGD-21 is trained to detect vegetation coverage. BSHRK-W-VGD-21 is capable of detecting vegetation coverage from aerial image input and producing a high-quality probability heatmap of vegetation coverage. The results are provided with 3 channels each with 0-255 value heatmap. The three channels represent low/no vegetation coverage, medium-height vegetation, and high vegetation.
Blackshark.ai’s OrCA model BSHRK-W-CLD-88 is trained to detect the presence of clouds from input images and output a binary pixel mask indicating cloud coverage.
Blackshark.ai’s Orca model BSHRK-W-BHD-19 can estimate the height of buildings from input images and output detected heights by category (1, 2-5, 6-10, etc.) for each vectorized building footprint.
Model BSHRK-W-RDD-09 is trained to detect roads. BSHRK-W-RDD-09 is capable of detecting roads from aerial image input and output a high-quality map of road coverage as a binary pixel mask.
Blackshark.ai’s Orca model BSHRK-W-RCD-19 is trained to detect the roof color of buildings from input images and output color masks for each building footprint polygon indicating the detected roof color.