Target identification method based on deep learning network and hot-line robot

Abstract

The invention provides a target identification method based on a deep learning network and a hot-line robot. Weights and offsets on each layer in a convolution neural network are initialized; two-dimensional image data is input for convolution to obtain C1-layer data; the maximum pooling treatment is performed for the C1-layer data to reduce the magnitude of the data to obtain S2-layer data; the convolution is performed for the S2-layer data to obtain C3-layer data; the maximum pooling treatment is performed for the C3-layer data to further reduce the magnitude of the data to obtain S4-layer data; the convolution is performed for the S4-layer data to obtain C5-layer data; the C5-layer data serves as input to totally connect with a H6 layer, and an output layer is totally connected with the H6 layer to output learning results of target characteristics; and the weights and the offsets are finely adjusted by applying a back propagation algorithm to finish the network learning. The method is high in target identification rate and excellent in robustness under complicated background.

Description

Technical field [0001] The invention relates to the field of target recognition of live working robots, in particular to a target recognition method based on a deep learning network and a live working robot. Background technique [0002] The introduction of live working robots into the power industry instead of manual power maintenance and repair work can effectively avoid the occurrence of casualties during live work, and can greatly improve the efficiency of the power industry. At present, live working robots mainly adopt the remote operation method of the master-slave manipulator. The operator uses the master manipulator to remotely control the slave manipulator, and their personal safety is guaranteed to a certain extent. But it has the following shortcomings: 1. The operator is required to have a high degree of technical proficiency, which means strict and professional training for the operator, consumes manpower and material resources, and is not efficient. 2. The manual m...

AI Technical Summary

Problems solved by technology

But it has the following disadvantages: 1. The operator is required to have a high degree of technical proficiency, which means that the operator must be trained strictly and professionally, which consumes manpower and material resources, and the efficiency is not high.

2. Manual master-slave operation steps are cumbersome and slow

3. The fault tolerance rate in the operation process is low, which may damage the robotic arm and even affect the progress of the operation

These methods are highly data-dependent, and the accuracy of recognition is often not high when the object is in a complex background.

Images