I would like to use realsense L515 to perform some operations on the mask data and find the depth and size3 of the objects detected. However when I run eval.py with the --video argument, I only get the infrared frame and the detections arent good. DoI just have to pass the video 0 as parameter for the relsense or is there a special way where I have to dig deeper into the code? I want to calculate the size of the object using depth frame data and the mask coordinates.
I would like to use realsense L515 to perform some operations on the mask data and find the depth and size3 of the objects detected. However when I run eval.py with the --video argument, I only get the infrared frame and the detections arent good. DoI just have to pass the video 0 as parameter for the relsense or is there a special way where I have to dig deeper into the code? I want to calculate the size of the object using depth frame data and the mask coordinates.