ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIAKit SDK - Windows (PB25h1)NVIDIAKit SDK - Linux (PB25h1)NVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
—
PeopleSemSegNet AMR
Model
—
PeopleSemSegNet AMR

Semantic segmentation of persons in an image.

This model is backed by NVIDIA's Plus Plus (++) Promise
to learn more about the quality of the datasets used to train this model.
FieldResponse
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/