Overview Group Keypoint Detection Node

Overview Group Keypoint Detection Node

The Group Keypoint Detection Node is used to detect the keypoints such as human pose and facial landmarks with pre-trained or custom deep learning models on GPU, CPU, TPU (Google Coral) or VPU (Intel Movidius Myriad X).

Input and Output
  1. Input: Frame from a video file, IP or USB camera (or from other pre-processing node).
  2. Output: MQTT message containing the keypoint results.
  3. Supported architecture: Currently supported on amd64 devices.
Node Parameters
The following parameters are used in the Group Keypoint Detection node.

Name: Input the node name used in a specific flow.
  1. default: group keypoint detection
  2. type: string
Device: Select the target detection mode to be used. Currently available are CPU, GPU, VPU/MYRIAD, and TPU.
  1. default: CPU
  2. type: string
In case you select VPU as your target device, you will be displayed with an additional field where you can indicate how many VPU target devices you would like to run your models on, or run the edge inference on both CPU and VPU. To do that, simply enter MYRIAD,MYRIAD,CPU as an example. This means that the inference will be performed on 2x VPUs and 1x CPU.

Category: Defines the type of keypoint category to be used (e.g. Human Pose, Facial Landmark, etc.).
  1. default: Human Pose (we currently support Human Pose)
  2. type: string
Model: Select one of the most popular public models for group keypoint detection:
  1. Available models: See here
  2. default: Resnet 50
  3. type: string
Custom Model: You can link your own custom model by adding the model URL.
Detection Threshold: Refers to the threshold value for confidence score filtering.
  1. default: 0.3
  2. range: (0.0~1.0)
Show Result: Defines whether or not to draw the detected keypoints on the output frame.
  1. default: true
  2. type: boolean

    • Related Articles

    • Group Keypoint Detection: Available Models

      Available Models We continuously test, evaluate and add available off-the-shelf models to be used immediately. Currently, we have added following models to the Group Keypoint Detection Node. Available models to run on CPU resnet50 resnet101 resnet152 ...

    • Overview Fall Detection Node

      The Fall Detection Node detects and tracks the movement of people to identify if a person is falling. Input and Output Input: Group Keypoint Detection output message and stream Output: Fall detection message and stream Supported architecture: ...

    • Posture Recognition Node Overview

      The Posture Recognition Node detects and tracks the movement of people to identify a person's posture. Input, Output and Supported Architecture Input: Group Keypoint Detection output message and stream or Video Feed output stream Output: MQTT message ...

    • Overview Object Detection Node

      The Object Detection Node is used to detect several different objects off the shelf with pre-trained or custom deep learning models on GPU, CPU, VPU (Intel Movidius Myriad X) or TPU (Google Coral). Input and Output Input: Frame from a video file, IP ...

    • Overview Object Counting Node

      The Object Counting Node is used to count one or multiple objects which are previously detected by the object detection node. Input and Output Input: MQTT message (results from object detection node) Output: MQTT message containing IN / OUT results ...