[The 3rd Xuantie Cup RISC-V Application Innovation Competition] LicheePi 4A+ portable mobile endoscope hardware construction completed
[Copy link]
邀请:@okhxyyo
@lightxixi
参与回复
I finally finished the hardware part after a month of delay, and I want to share it with you.
- Hardware parts
At first, I planned to use Android 13 to install the open source USB camera software to achieve this. Later, I saw other friends saying that Android's compatibility needs to be improved and there will be certain problems when burning the image. So after a simple attempt failed, I decisively used the debain image to do it. Stability and ease of use are the first priority.
I upgraded according to the official method. There is one thing I need to pay attention to when burning the image , which is the relative file path relationship between your batch processing, exe and img. There will be problems if you use an absolute path here, so a relative path will be fine.
During the upgrade process, a bunch of oks will appear. Remember not to turn off the power during this period.
After burning, it booted up smoothly. I also modified the official plastic box. It was just a simple window, ironing and cutting with a blade. Please refer to another post .
If the official can make this box before it comes out, I would feel much more comfortable. It’s so fussy when I make it myself.
The solution is 70% complete, and the remaining 30% is the image recognition part. I plan to deploy a small yolo for image recognition to identify the close-range images captured by the endoscope. Still in progress
Currently, the USB-camera is used for image display. The image quality of the endoscope is not very good, but the whole process can be run smoothly.
2. Interesting and innovative
Overall, the fun lies in its portability, plug-and-play, and suitability for a variety of scenarios. Of course, the USB-endoscope itself can be plug-and-play with a mobile phone, and the board plus the display is several times larger than the mobile phone. However, few mobile apps have recognition functions, so using a computing board with a built-in GPU to create an intelligent recognition endoscope is very useful in special medical and process scenarios.
I saw the poster personally reaching into the ear and seeing the dirt inside. It feels similar to cleaning the ears outside. If you look inside and gently wipe it with an ear pick and a cotton swab, it will basically be done.
Minors are prohibited from attempting dangerous actions.
3.Technology Exploration
To be continued, save for later
4. Demonstration Video
I'll first post a demonstration video of the overall hardware, and please be gentle with your criticism.
111
|