Monitoring alarm method and system

Abstract

The invention provides a monitoring alarm method and device. The method comprises the following steps: acquiring image data of a workshop site through a monitoring node; recognizing a human body in the image data, and capturing a plurality of key nodes of the human body; constructing a limb line based on a plurality of key nodes of the human body, and calculating an intrusion proportion of the limb line in an early warning surface generated based on the image data; and in response to the condition that the intrusion proportion of the limb line in the early warning surface is greater than or equal to a preset threshold value, enabling the monitoring node to give an alarm and uploading related image data to a monitoring center. The method and the device have the beneficial effects that the monitoring method and the device for image recognition and human body posture prediction are provided, auxiliary monitoring by speculating the human body posture under the condition of low image definition is supported, speculation under an offline condition is supported, the investment of monitoring personnel is reduced, and the workshop network arrangement cost is decreased.

Description

technical field [0001] The invention relates to the technical field of monitoring, in particular to a monitoring and alarming method and system. Background technique [0002] With the continuous deepening of the concept of safe production, the production workshops and production lines of the enterprise are equipped with operation monitoring, and are equipped with special personnel for monitoring and exception handling. However, there are many problems in the existing workshop monitoring methods, the main problems include: [0003] 1) Unlike the process manufacturing-oriented chemical and paper industries that can achieve purification and dust-free workshops, it is difficult to achieve dust-free workshops in large-scale equipment manufacturing plants and bridge manufacturing plants oriented to discrete manufacturing, especially in workshops involving steel structure processing. In the processing technology of large-scale equipment manufacturing plants, there are often proces...

AI Technical Summary

Problems solved by technology

In the processing technology of large-scale equipment manufacturing plants, there are often processes such as high-temperature cutting and argon arc welding, which will generate a lot of exhaust gas. However, due to the large volume of processed parts and temporary stacking and stacking of raw materials and semi-finished products in large-scale equipment manufacturing workshops, the exhaust gas is not easy to flow. It dissipates in a short time, reducing the visibility of the workshop. In addition, the work clothes in the workshop are mostly dark blue, gray, black and other dark tones, and the boundaries with other environmental factors such as equipment and steel are unclear. It is even more difficult to distinguish and distinguish from the monitoring images.

[0004] 2) For the early warning of object intrusion, the alarm is generally triggered according to the area ratio of the intrusion area and the forbidden area (warning surface). However, this method often causes false alarms

For example, if a flying insect is flying close to the camera, due to the perspective phenomenon of near-large and far-small, the area of ​​the flying insect will be doubled, and the proportion will reach the preset value, which will lead to false triggering of the monitoring alarm, thereby giving the monitoring personnel It will cause additional review work, and on the other hand, a large amount of storage space will be wasted due to the retention of false alarm warnings

[0005] 3) After the deployment of the monitoring system is completed, due to the solidification of the monitoring system, it is difficult to upgrade, increase or decrease, migrate, and introduce new functional equipment.

Images