Overview Image Classification Node

Overview Image Classification Node

The Image Classification Node is used to classify an image into several categories, using pre-trained or custom deep learning models on GPU, CPU, TPU and VPU.

Input and Output
  1. Input: Frame from a video file, IP or USB camera.
  2. Output: MQTT message containing the classification results.
  3. Supported architecture: Currently supported on amd64 devices.
Node Parameters
The following parameters are used in the Image Classification node.

Name: Input the node name used in a specific flow.
  1. default: image-classification
  2. type: string
Device: Select the target device mode to be used. Currently available are GPU, CPU, TPU or VPU.
  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.

Model Name: Select one of the most popular public models for image classification.
  1. Available models: See here
  2. type: string
Custom Model: You can link your own custom model by adding the model URL.
Detection Labels: Select the target object(s) to classified. A single or multiple objects can be selected.
  1. default: none
  2. type: string
Detection Score Threshold: Refers to the threshold value for confidence score filtering.
  1. default: 0.5
  2. range: (0.0~1.0)
Top Counts: Refers to the number of output classes sorted by its confidence score.
  1. default: 20
Custom Model: You can link your own custom model by adding the model URL.

    • Related Articles

    • Image Classification: 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 Image Classification Node. Available models to run on CPU mobilenet resnet50 vgg19 ...
    • Overview Object Flow Node

      The Object Flow Node detects and tracks people from an input video stream to compose a heatmap and to calculate the average dwell time. Input and Output Input: Object Detection mqtt result message, ROI section definition, Object Counting result ...
    • Overview Region of Interest (ROI) Node

      The Region of Interest (ROI) node allows to filter a portion of an image that you want to perform some other operation on. ROI can be set for each camera stream and is therefore device specific. While the ROI node needs to be added to your flow, it ...
    • 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 ...