Semantic segmentation assigns a semantic category to each pixel in the input image, that is, it identifies pixels as part of an object, say, a car, a road, a tree, a horse, etc. Libsegmentation is a segmentation library that can be used in ADAS applications. It offers simple interfaces for a developer to deploy segmentation tasks on a Xilinx® FPGA.
The following is an example of semantic segmentation, where "blue-gray" denotes the sky, "green" denotes trees, "red" denotes people, "dark blue" denotes cars, "plum" denotes the road, and "gray" denotes structures.
Figure 1. Semantic Segmentation Example
The following table lists the semantic segmentation models supported by the Vitis AI library.
| No | Model Name | Framework |
|---|---|---|
| 1 | fpn | Caffe |
| 2 | FPN-resnet18_Endov | |
| 3 | semantic_seg_citys_tf2 | TensorFlow |
| 4 | mobilenet_v2_cityscapes_tf | |
| 5 |
SemanticFPN_cityscapes_pt |
PyTorch |
| 6 | ENet_cityscapes_pt | |
| 7 | unet_chaos-CT_pt | |
| 8 | SemanticFPN_Mobilenetv2_pt |