openmv对物体进行色块识别，但是想脱离PC对识别过程进行录制，类似在IDE中帧缓冲区的录制效果

我通过openmv和esp32进行串口通信，但是将openmv IDE的程序停止运行后，esp32依然会接收到串口数据

import sensor, image, time
from pyb import UART

sensor.reset() # Initialize the camera sensor.
sensor.set_pixformat(sensor.RGB565) # use RGB565.
sensor.set_framesize(sensor.QQVGA) # use QQVGA for speed.
sensor.skip_frames(10) # Let new settings take affect.
sensor.set_auto_whitebal(False) # turn this off.
clock = time.clock() # Tracks FPS.

roi_threshold  = (55, 100, -5, 127, -25, 127)
uart = UART(3, 115200)

def find_max(blobs):
    max_size=0
    for blob in blobs:
        if blob[2]*blob[3] > max_size:
            max_blob=blob
            max_size = blob[2]*blob[3]
    return max_blob

while(True):
     clock.tick() # Track elapsed milliseconds between snapshots().
     img = sensor.snapshot() # Take a picture and return the image.
     blobs = img.find_blobs([roi_threshold])
     if blobs:
         max_blob=find_max(blobs)
         if max_blob.cx()<70:
             flag=0
         elif max_blob.cx()>90:
             flag=1
         else:
             flag=2
         output_str="%d" %flag
         uart.write(str(flag))
         img.draw_rectangle(max_blob.rect())
         img.draw_cross(max_blob.cx(), max_blob.cy())
         output_string="[%d,%d]" % (max_blob.cx(),max_blob.cy()) #方式1
         print('you send:',output_str)
     else:
         print('not found!')

#include <ESP32Servo.h>
volatile int degree;
volatile int step;
Servo servo_23;

char flag;

void setup() {

 Serial2.begin(115200);
 Serial.begin(115200);
 servo_23.attach(13,500,2500);
 
}



void loop() { 
if (Serial2.available()>0)
  {
    flag=Serial2.read();
    if (flag=='1')
    {
      Serial.println(1);
      servo_23.write(60);
           
     }
     if (flag=='0')
     {
      Serial.println(0);
      servo_23.write(120);
       
     }
     if (flag=='2')
     {
      Serial.println(2);
      servo_23.write(90);
      
     }
     
   }
 

}