Guardrail crossing detection method combining deep neural network and block chain

Abstract

The invention discloses a guardrail crossing detection method combining a deep neural network and a block chain. The method comprises the following steps: building a guardrail crossing detection deepneural network, enabling the input of the network to be an acquired monitoring area image, enabling the output result of the network to be the detection result of whether someone crosses a fence or not, wherein the network comprises a personnel key point detection encoder, a personnel key point detection decoder, a key point regression unit and a post-processing unit; and loading parameters required by the trained guardrail crossing detection deep neural network on the server cluster, configuring a guardrail crossing detection deep neural network inference block chain private chain for each guardrail crossing detection deep neural network inference request, and executing guardrail crossing detection inference. By utilizing the method, the detection precision, the detection efficiency and the safety and confidentiality in the data processing and transmission process are improved in construction site limited area personnel crossing monitoring.

Description

technical field [0001] The invention relates to the technical fields of artificial intelligence, block chain, CIM, and smart construction site, in particular to a guardrail crossing detection method combined with deep neural network and block chain. Background technique [0002] With the rapid development of my country's social economy and science and technology, the traditional detection and management methods based on human resources in the construction site have shown many limitations, such as the high cost of personnel detection and management, and the low efficiency of detection and management. , The accuracy of detection is not high, it is easily affected by subjective factors, and the lack of human resources leads to problems such as ineffective management. [0003] The construction site has a certain degree of danger. If outsiders enter the restricted area of ​​the construction site by climbing over the guardrail, failure to enter will affect the construction progres...

AI Technical Summary

Problems solved by technology

However, relying on manpower for real-time supervision is too costly and inefficient, and will be affected by the subjective factors of supervisors

Moreover, the current detection of various risk factors on the construction site usually only returns abnormal results, and the result feedback is single

In addition, the system used for computing, information is easily leaked, and the security performance is low

[0004] Therefore, the existing guardrail overturning detection technology has the problems of low detection accuracy and detection efficiency, single result feedback, and low safety performance in the process of data processing and transmission.

Images