Darknet camera not found on Jetson Nano

I am trying to run darknet with CUDA with a Jetson Nano(Ubuntu 18.04) with this camera

https://www.amazon.com/IMX219-160IR-Infrared-Megapixels-Developer-XYGStudy/dp/B07TCL3S7S/ref=sr_1_4?keywords=imx219-160ir&qid=1570582755&sr=8-4

I have followed every step in this nice tutorial

https://pysource.com/2019/08/29/yolo-v3-install-and-run-yolo-on-nvidia-jetson-nano-with-gpu/

,but when running darknet with

./darknet detector demo cfg/coco.data cfg/yolov3.cfg yolov3.weights -c 0

a green screen appears where the video feed should be and the framerate info is streaming in the terminal. Am I missing a camera driver or something? Thanks

Hi,

What kind of camera do you use?
If it’s an USB camera, you will need to build OpenCV from source with GStramer support:
https://github.com/AastaNV/JEP/blob/master/script/install_opencv4.0.0_Nano.sh

By the way, it’s recommended to use our Deepstream SDK for YOLO model.
We have optimized the pipeline for Jetson platform which can give you a better performance.
https://developer.nvidia.com/deepstream-sdk

Thanks.