ฉบับไทย

This project was intended for displaying camera feed and inference results of FOMO object detection model by Edge Impulse to TFT screen. The Hardware were provided by Wireless Solution Asia. To run this project users must obtain a model from Edge Impulse.

- Before using this repository please obtain a model from FOMO and set up TFT and camera properly before running this project

• Arduino IDE, preferably the latest ones, but older versions will still do the job.
• ESP32-S3 is preferable but older version will do just fine.
• ST7789 or any TFT screens.
• OV2640 camera or any OV series.

• FOMO_object_detect_TFT.ino - Containes Arduino codes displaying camera feed and FOMO results to TFT screens.

1. Download the zip file and extract it to Arduino directory.




2. Open Fomo_object_detect_TFT.ino, under tools change your Board to "ESP32S3 Dev Module" and PSRAM to "OPI PSRAM".





3. Add the zip folder of the trained model obtained from Edge Impulse to Arduino IDE.







4. Connect pin no.1 of the Esp32 to a push button.

• User can change resolution of the camera when the push button is pressed. The avaiable resolution is as follow.
  
  
• 96 X 96
  
  
  
  
  
• QQVGA 160 X 120
  
  
  
  
  
• 176 X 144
  
  
  
  
  
• 240 X 176
  
  
  
  
  
• 240 X 240
  
  
  
  
  
• 320 X 240
  
  
  
  
  

Thanks to WIRELESS SOLUTION ASIA CO.,LTD for providing AIOT board to support this project. Also thanks to Bodmer / TFT_eSPI for the TFT libraries. Scripted used for Esp32 FOMO object detection inferencing were provided by Edge Impulse.