Fix pink tint on Jetson Nano wide angle camera

Jonathan Tse
2 min readJul 11, 2019

Update: If you are using newer Jetson software, note that you might need to use a newer isp profile. I haven’t verified it yet so please give it a shot and let me know.

Thanks Ville Saukkonen for mentioning this to me.

A lot of people are very interested in Nvidia recently announced Jetson Nano and JetBot. In many use cases including the JetBot and Donkey Car, we would want to use a wide angle camera. One of the recommended camera module for Jetson Nano is a Raspiberry Pi v2 camera module. This camera come with a standard camera lens which is not a wide angle lens. To convert this camera to a wide angel lens, you would need to buy a wide angle lens and replace it.

A Raspiberry pi camera module v2 and a wide angle lens module

Alternatively, you could also choose a IMX219 compatible wide angle camera. If you are using it for Donkey car, I would recommend you to get this option because it fits better into the new cage.

The pink tint

However, no matter which camera you choose, all of them exhibit a red or pink tint on the outer area of the image like below:

This pink or red tint is disturbing because it would interfere with the CV algorithm. Until recently, someone on the Nvidia forum has released a tuning profile for the wide angle camera and I confirm it works on the IMX219 compatible wide angle camera.

Here is how you could use the fix:

Download the tuning profile for Jetson 4.2:

wget https://www.waveshare.com/w/upload/e/eb/Camera_overrides.tar.gz
tar zxvf Camera_overrides.tar.gz

For JP4.4 or above, you might want to try this isp profile:

wget https://www.dropbox.com/s/u80hr1o8n9hqeaj/camera_overrides.isp?dl=0

Copy it to the directory

sudo cp camera_overrides.isp /var/nvidia/nvcam/settings/
sudo chmod 664 /var/nvidia/nvcam/settings/camera_overrides.isp
sudo chown root:root /var/nvidia/nvcam/settings/camera_overrides.isp

The result

The red tint is gone (left) after the profile is applied

Fantastic, the pink or red haze is gone!

--

--

Jonathan Tse

Love Self-driving technology and machine learning. Community leader in DIYRobocar Hong Kong.