Qingdao University of Technology

Xiaohan Zhang

Wenbin Zhang

The disclosure relates to a grabbing detection method based on an RP-ResNet. The method comprises: inputting an image of a target; pre-processing data; performing data processing by an RP-ResNet model; and finally, generating a grabbing block diagram of a target to be grabbed. On the basis of a model ResNet 50, a region proposal network is used in the 30th layer of a network, fuzzy positioning is performed on the positions of grabbing points, feature information of high and low layers is fully fused to strengthen the utilization of information of low layers, and the 40th layer of the network is added to an SENet structure, thereby further increasing the detection accuracy of a grabbing points. By a grabbing detection framework based on ResNet-50, a residual network, a region proposal idea and SENet are combined, thereby ensuring rapid and accurate target detection.

Growing community of inventors

Qingdao, China

Xiaohan Zhang