Constructor safety shoe wearing detection method combining block chain and DNN

Abstract

The invention discloses a constructor safety shoe wearing detection method combining a block chain and a DNN. The method comprises the following steps: constructing a constructor safety shoe wearing detection deep neural network; setting a key point matching unit for performing position matching on the key points of the construction personnel and the key points of the safety shoes to obtain a safety shoe wearing detection result; loading parameters required by the trained constructor safety shoe wearing detection deep neural network and parameters required by the key point matching unit on theterminal cluster and the server cluster; and for each constructor safety shoe wearing detection deep neural network inference request, generating a constructor safety shoe wearing detection block chain private chain, and executing network inference. According to the invention, in construction site safety monitoring, safety shoe wearing detection precision, detection efficiency and safety and confidentiality in a data processing and transmission process are improved.

Description

Technical field [0001] The invention relates to the technical fields of artificial intelligence, blockchain, CIM, and smart construction sites, and specifically relates to a detection method for safety shoes worn by construction workers that combines blockchain and DNN. Background technique [0002] With the rapid development of social economy and science and technology in our country, the traditional detection and management methods based on human resources in the construction site have appeared many limitations, such as the high cost of inspection and management by personnel, and the low efficiency of detection and management. , The accuracy of detection is not high and it is easily affected by subjective factors, and the lack of human resources leads to problems such as ineffective management. There are many safety problems in the construction site, such as the irregular wearing of workers’ safety equipment and the fall of safety equipment during the construction process. Howe...

AI Technical Summary

Problems solved by technology

[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 poor management

There are many safety problems in the construction site, such as irregular wearing of safety equipment for workers, falling off of safety equipment during construction, etc. However, the cost of real-time supervision by manpower is too high and the efficiency is low, which will be subject to subjective factors of supervisors and objective factors such as environment and occlusion. factors

[0003] Some studies use target recognition to detect whether construction workers are wearing safety devices. However, the method of using target recognition can only get the results of whether there are corresponding safety devices in the image, without further matching, and the detection accuracy is low. Robustness poor

Moreover, the current safety inspections for construction personnel usually only return abnormal results, and the result feedback is single

Moreover, the server clusters used for computing are easy to leak information and have low security performance

[0004] Therefore, the existing construction personnel safety shoes wearing 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