Vision-based underwater robot target autonomous identification method

• Main Authors: HAN YI, ZENG JUNBAO, QIU TIANYOU, LI YIPING, XU GAOPENG
• Format: Patent
• Language: Chinese; English
• Published: 09.08.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention relates to the technical field of underwater robot target identification, and provides a method for autonomously identifying an underwater specific target by an underwater robot. The method comprises the following steps: firstly, carrying out comprehensive image enhancement and preprocessing, carrying out red channel compensation and histogram equalization enhancement processing on an image acquired by an underwater robot camera in advance, and reducing the influence of factors such as blurring and contrast reduction caused by scattering in an environment on an original image; secondly, a composite structure of a parallel convolutional layer is adopted to accelerate extraction of feature data in the picture, and a BN layer is added behind a pooling layer to perform batch normalization to improve the generalization ability of the model; and finally, channel pruning is carried out based on LASSO regression to remove a part of unimportant pruning units, and the network is retrained, so that the com