I am using a realsense l515 lidar camera. I have darknet built into my jetson. I want to find out the size of apples using these two. I am new at computer vision and would like to know how to use the depth frame along with darknet to find the dimensions of the apple from the frame. I was told to create a mask of the apple and then create a 3d bounding box to find it. I am unclear how to go about this?