[Retracted] A Secure and Efficient Multi-Object Grasping Detection Approach for Robotic Arms

Figure 9

The first line is the result of the grasp detection of the original image, and the lines below are the results under the compression ratio of 16.29%, 4.07%, 0.99%, 0.5%, 0.13%, 0.05%, 0.04%, and 0.03%. From top to bottom, the loss of pictures due to compression gradually increases, which slowly affects the bounding box results of grasp detection.