YORU Your Optimal Recognition Utility

Step5. Closed-loop experiments

Condition

Using the Drosophila mating model created earlier, I will explain an experimental setup that operates an LED in response to Drosophila mating. The LED is controlled by the Arduino’s TTL (Transistor-Transistor Logic) signal.

  1. Edit a condition YAML file.

condition YAML file template

  name: fly_copulation_project   # Experimental name.  
    export: /Path/to/result/directory/   # Output folder for videos and experiment information.  
    export_name: fly_copulation_real_time_analysis   # Specifying the file name of the output video.   
    
  model:  
   yolo_detection: False   # If you want to start YORU's inference immediately after starting YORU's real-time process, set this to True.  
   yolo_model_path: Path to YORU model   # Specify the YORU model (.pt file).  
   Trigger: False  
  
  capture_style:  
   stream_MSS: False   # When using the screen capture function, set to True.  
    
  trigger:  
   trigger_threshold_configuration: 0.3   # Confidence threshold when detecting YORU.  
   trigger_class: copulation   # Which action class to trigger.  
      
   Arduino_COM: “COM3”   # COM to which Arduino is connected.  
   trigger_pin: 13   # Specifying pin numbers for outputting TTL signals with Arduino.  
   trigger_style: standard_arduino   # Select which trigger plugin to use.  
     
  hardware:  
   use_camera: True   # Specify whether to use the camera.  
   camera_id: 0   # Specifying the camera ID.  
   camera_width: 640   # Specify the width (px) of images captured by the camera.  
   camera_height: 480   # Specifying the height (px) of images captured by the camera.  
   camera_scale: 1   # If you want to change the scale of the camera image, change this setting.  
   camera_fps: 30   # Specifying camera fps.  
   camera_imshow: False   # When set to True, the opencv window opens.

  1. Write the “Standard Firmata” program, located within the Example programs section of the Arduino IDE, to the Arduino.

  2. Connect a camera and Arduiono to a PC.

  3. Select the condition YAML file in YORU start page.

  4. Run “Real-time Process”.

  5. Operate Real-time Process GUI.

i. Check the “YORU detection” box to start YORU’s real-time analysis. Frames analyzed by YORU will be displayed on the right.

ii. By checking the “Trigger condition” box, you can start the YORU trigger. In this case, when “copulation” is detected, a TTL signal is output on Arduino pin 13.

iii. Save videos by checking the “Streaming data”.


Previous