Interesting project! I have a UnitV2 (and the older UnitV) as well but only little experience with. My approach would be the following: To recognise only a few well known vehicles you can classify the image of the whole plate including car front (and drivers face) instead of the individual numbers/letters on it. This can be done with the V-training or with the online classifier function. For recognising single numbers/letters you can try to classify individual numbers/letters and then "read" the x-coordinates of the returned boundary boxes in ascending order to convert into string and then compare to a list/database.

I would like to know this too, BUMP!

SOLVED IT! Here, You can use this, hope it helps out! UNITV2 WEB RESULT RESPONSE

@viquaheeg520 I have a number of cameras that have caught fire whilst operating on charge. The ESP32 has cracked and literally let the smoke out. Not sure if that is related but clearly I can't risk using the 30 or so units we bought.

I reboot with terminal and try LaneLine Tracker setting. but I had same problem... I try it: Power on and start UnitV2 . Click gear icon and select "Switch to notebook mode". Open Jupyter main page. Click "New" and select "Terminal". type "reboot" and open camera stream page. Click little switch and there color change black to light blue. Select "LaneLine Tracker" on Browser GUI. Change L_max text box value 0 to 30 . Click “update” button. Line tracking process is stopped. but camera stream keep running. Maybe, I think my unitV2 need initialize firmware. Where is unitv2 initialize procedure?

@m5stack This is a very big issue, The M5Stack team needs to get this working, and the wifi access point!

A new version of the firmware is comming soon ... https://community.m5stack.com/topic/3321/unit-v2-connection