Supernovae

> Actually , it does not need a vehicle just use the detect ocr script but the trained model that they shared is not the best , if you train...

> When it is possible, sys_time does timesync between FCU and OBC. So mavlink messages with timestamp fields will be relatively close to FCU's time. You can also use ntpd_driver...

> I do not know why, but sys_time reports that RTT is too high to operate correctly. okay, but according to you, are[ these steps](https://discuss.cubepilot.org/t/indoor-autonomous-flight-with-cube-ros-and-aruco-board-ongoing/351/7) correct? and since I am...

Hi, @vooon I tried using the GUIDED mode but still the results are not appropriate. and as far as I saw the typemask scheme for this message is same for...

Hi @vooon, Thanks for the response, when using PX4: I am trying to use the [Fast-panner](https://github.com/mzahana/px4_fast_planner), it works well with the PX4 since it has mavros_controllers which make sure that...

edit this function based on the co ordinates you require https://github.com/theAIGuysCode/yolov4-custom-functions/blob/8f2c922a54d9ee0878efd3dffa42ce6e7bd3ae34/core/utils.py#L216 i think this is called to draw over images

https://github.com/TheophileBuy/LicensePlateRecognition refer this

close the issue if it is solved @iabesadze

is it okay if you use darknet instead of tensorflow? if yes you can use https://github.com/AlexeyAB/darknet ./darknet detector test cfg/coco.data cfg/yolov4.cfg yolov4.weights -ext_output -dont_show -out result.json < filelist.txt > result.txt...

refer this https://github.com/hunglc007/tensorflow-yolov4-tflite/issues/241