Instance Segmentation (Colored and Depth Image)

The main function of this step is to obtain the list of the masks of the object by object detection and recognition of deep learning. It usually applies when we need to recognize and segment the object. The combination is as Figure 1 shown.

Figure 1. Procedure of instance segmentation(colored and depth image)

The step scale_image_in_2d_roi would process the colored and depth image and output the scaled ROI to the step Instance Segmentation. The list of the masks would be calculated by object detection and recognition of deep learning and then be fed into step Recover Scaled Images in 2D ROI. This step could restore the scaled ROI and finally output the ist of the masks.

Since we add some depth information in this step, the detecting ability should be higher than Instance Segmentation (Colored Image).