detectPoses

warning

The document is a continuation of the previous document, if you have landed directly on this page then, Please read from page Get started.

What is detectPoses component ?

detectPoses component is used to detect pose of a person in input image.

• Description : detectPoses() takes an input as image in base64 string format and returns the points(x,y) with probability for that point.Check Input and output parameters for details.
• Parameters :
  • Input(Via STDIN) : A JSON String with following parameters:
    • Parameter1 : Image (.jpg/.png) in base64 format
  • Output(Via STDOUT) : A JSON string with following contents
    • For each detected point
      • x,y co-ordinates
      • probability being point
    • int responseID

List of detectPoses features in shunya stack

1. Get human pose data.

Using detectPoses

Requirements to use detectPoses

1. Shunya OS installed (supported Arm devices) or Shunya OS docker container (X86 based windows/linux devices)
2. Shunya AI installed in Shunya OS.

Steps to use detectPoses

1. Set input image location.
2. Get human pose data

note

Run the steps given below inside Shunya OS installed (supported Arm devices) or Shunya OS docker container (X86 based windows/linux devices) terminals.

Lets take an example use case: Say we need to

1. Detect pose of person in an image.
2. Get JSON output of detected pose data.

Steps are

Step 1: Set location of the input image for pose estimation

1. Start with an ready to use template for detecting pose from image.

   git clone https://gitlab.iotiot.in/shunya/products/shunya-ai-examples.git
   cd shunya-ai-examples/indiv-components

2. Open the examples in a text editor and modify as per your usecase.

   • For CPP you will find the examples in the folder cpp-examples/pose-estimation/detectPoses
   • Open the file detect_poses.cpp
   • Modify the line to set the location of the input image

   /* Modify the location of the image to your input image */
   cv::Mat inputImage = cv::imread("../images/pose.jpeg"); 

   • For Python you will find the examples in the folder python-examples/pose-estimation/detectPoses
   • Open the file detect_poses.py
   • Modify the line to set the location of the input image

   # Modify the location of the image to your input image
   img = cv2.imread("images/pose.jpeg") 

Step 2: Get human pose data.

1. Once you are done editing, save and run the code, by running

   mkdir build && cd build
   cmake ../
   make 
   ./detectPosesCpp

   python3 detect_poses.py

2. Running the codes will print the JSON output on the terminal (to STDOUT).

   For Example:

   • Lets say the input image is

     

   • Input JSON is

     {
         "inputImage": "4h32e898473urmcrkd947ryuemcc3x21j98k09754ycmx1k030i1d98754yn==",
     }

   • Then the JSON output is

     {
          "Image":"/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAIBAQEBAQIBAQECAgICAgQDAgICAgUEBAMEBgUG",
          "DetectedposesJSON":[
          {
              "Point0":{
                   "Landmarks":{
                         "x":112.5,
                         "y":21.09375
                   },
                   "Prob":0.979064404964447
                  
              },
              "Point1":{
                   "Landmarks": {
                         "x":117.1875,
                         "y":17.578125
                   },
                   "Prob":0.9587295651435852
              },
              .....
          }
     }

Understand this component with an example (ready to use code)

• This is an example for pose-estimation and here we will be using 2 components: detectPoses and drawPoses

• Check this ready to use example in c++ and python

• Download the code

  git clone https://gitlab.iotiot.in/shunya/products/shunya-ai-examples.git
  cd shunya-ai-examples/cpp-examples/pose-estimation

  ```shell git clone https://gitlab.iotiot.in/shunya/products/shunya-ai-examples.git cd shunya-ai-examples/python-examples/pose-estimation ```

• In this folder there is a file, pose_detect.cpp or pose_detect.py

• detectbjects Components used

  subprocess::popen detectPoses("/usr/bin/detectPoses", {});

  ```shell detectPoses = Popen(['/usr/bin/detectPoses'], stdout=PIPE, stdin=PIPE) ```

• drawPoses component used

  subprocess::popen drawPoses("/usr/bin/drawPoses", {});

  ```shell drawPoses = Popen(['/usr/bin/drawPoses'], stdout=PIPE, stdin=PIPE) ```

• Run code by yourself

  mkdir build && cd build
  cmake .. && make
  ./poseEstimateCpp

  ```shell python3 pose_estimate.py ```
  - You will get a new image stored in system.

Facing errors with the component?