A substation patrol robot road scene recognition method based on depth learning

Abstract

The invention discloses a substation patrol robot road scene recognition method based on depth learning. The method includes collecting substation road scene image and constructing road scene image database, constructing convolutional coding network and training, constructing deconvolution decoding network and training based on convolutional coding network, and using test set to test model and road scene recognition application of substation patrol robot. The whole convolutional neural network constructed by the invention simultaneously gives attention to identification accuracy and efficiency, reduces network parameters and storage space by simplifying the deep high-precision convolutional neural network into a small shallow network to improve identification efficiency, and adopts a plurality of decoding network fusion modes to obtain more target information to ensure identification accuracy. The depth learning scene recognition method can obtain the dense information of the current environment of the substation inspection robot, provide more effective guidance information for robot navigation obstacle avoidance, and make the robot more adaptable to the environment.

Description

technical field [0001] The invention relates to the technical field of computer pattern recognition, in particular to a road scene recognition method for a substation inspection robot based on deep learning. Background technique [0002] With the continuous development of science and technology, the construction of smart grid characterized by "informatization, digitalization, automation, and interaction" is gradually deepening, and intelligent robots have been widely used in substations and achieved good results. For substation inspection robots, effective detection and identification of feasible roads is a prerequisite for the robot to work normally. At present, most substation inspection robots mainly use laser radar to realize robot navigation, positioning and obstacle avoidance. Although this method has high detection accuracy, it ignores the recognition and understanding of the road scene, so that the robot cannot effectively predict the environment in which it is loca...

AI Technical Summary

Problems solved by technology

However, most of the current high-precision networks such as SegNet, PSPNet, DeepLab, etc., have relatively large models and low recognition efficiency, and need to use high-performance graphics cards such as Titan Xp, Tesla V100, etc. to achieve real-time recognition; and for high-efficiency networks such as Although SegNet-basic, ENet, ShuffleNet and other networks can achieve efficient real-time recognition in general embedded applications, the recognition accuracy is relatively low, especially for small target recognition

Images