Model
—
PeopleSemSegNet AMRSemantic segmentation of persons in an image.
Use the NGC CLI to download:
Copied!
| Field | Response |
|---|---|
| Intended Application(s) & Domain(s): | Detecting persons. |
| Model Type: | Object Detection |
| Intended Users: | Developers working in robotics applications to help autonomous machines navigate floor space. |
| Output: | Semantic Segmentation Mask, Category Label(s), Confidence Score(s) |
| Describe how the model works: | Detects one or more “person” object within an image and returns a semantic segmentation mask. |
| Technical Limitations: | Model accuracy may be reduced in low-light, low contrast lighting conditions, with warped images, objects positioning relatively close to or far away from the camera frame (smaller than 20x20 pixels), and with objects occluded (less than 40% of the object is visible) or truncated. |
| Verified to have met prescribed NVIDIA standards: | Yes |
| Performance Metrics: | Accuracy, Intersection over Union(IoU), Precision, Recall |
| Potential Known Risks: | Not recommended for life-critical use cases |
| Licensing: | https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/ |