People Detection

Overview

People Detection node detects people in an input image using a built-in PeopleNet model and returns bounding boxes with optional overlays.

Compared with General Object Detection filtered to person, this node is specialized for people. Feed detections into Tracker, Gender and Age Detection, or zone counters as needed.

Input

Input Image

image required

The image frame to analyze. Connect this to a camera or upstream image output.

People Detection Model

string required advanced

Built-in model used for people detection. The pruned model is smaller and faster but less accurate, and can be used with NVIDIA GPU only.

Values:

• ONNV_PEOPLENET (default) — PeopleNet
• ONNV_PEOPLENET_PRUNE — PeopleNet (Pruned)

Confidence threshold

number required advanced

Minimum confidence score to keep a detection. See Confidence Threshold for tuning guidance.

Range: 0.0 to 1.0
Default: 0.3

Overlap threshold

number required advanced

NMS overlap threshold (higher allows more overlap). See Overlap threshold for tuning guidance.

Range: 0.0 to 1.0
Default: 0.2

Use TensorRT if available

boolean required advanced

Enable TensorRT inference backend when available. Can improve throughput on NVIDIA GPUs.

Default: false

Overlay results

boolean required advanced

Whether to draw detections on the output frame. See Overlay Results.

Default: true

Output

Overlay Image

image

Frame with detected people overlays.

Detected Count

integer

Number of people detected in the current frame.

Detected Objects

array

Array of detection objects with:

• Bounding Box (bbox): [x, y, width, height]
• Label
• Confidence