search

leggedrobotics / darknet_ros

YOLO ROS: Real-Time Object Detection for ROS
BSD 3-Clause "New" or "Revised" License
2.19k stars 1.18k forks source link

Colours are wrong in image widow. #320

Closed elpidiovaldez closed 3 years ago

elpidiovaldez commented 3 years ago

It looks like an RGB/BGR issue is causing colours to be displayed incorrectly in the OpenCV window. I see a similar issue #43 is marked as closed, but it still appears to be a problem. I can't tell if this affects the image data (which could lower the recognition accuracy), or just the displayed image.

tomlankhorst commented 3 years ago

Please provide your OS, the commit hash that you're working on, and any other info that might be helpful.

tomlankhorst commented 3 years ago

Will likely be solved by #321 please continue discussion there.

Wuxinxiaoshifu commented 2 years ago

I also meet this problem! when i training,the picture's format is rgb8. when i test the weights that i trained using bag,the colors of pictures in windows(yolo_v4) is different from my training pictures. i also changed BGR8 to RGB8 in YoloObjectDetector.CPP, but the colors in window(yolo_v4) didn't change! how did you handled this problem?

elpidiovaldez commented 2 years ago

I have not fixed it. I have not tried anything beyond searching the internet, because not a serious issue for me right now.

On Wed, Oct 13, 2021 at 4:34 AM Wuxinxiaoshifu @.***> wrote:

I also meet this problem! when i training,the picture's format is rgb8. when i test the weights that i trained using bag,the colors of pictures in windows(yolo_v4) is different from my training pictures. i also changed BGR8 to RGB8 in YoloObjectDetector.CPP, but the colors in window(yolo_v4) didn't change! how did you handled this problem?

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/leggedrobotics/darknet_ros/issues/320#issuecomment-941885625, or unsubscribe https://github.com/notifications/unsubscribe-auth/AICYPYQBTFPDZWMFPQNXIOTUGT435ANCNFSM44QE7DTA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.