Flight support node intelligent recognition system

Abstract

The invention discloses a flight support node intelligent recognition system. The system is composed of a streaming media processing platform, a YOLOv3 + AddNN algorithm platform, a message queue, a node intelligent recognition system, a database and a WEB system display platform. Firstly, a to-be-identified video is collected into a storage server; then, the video stream is transmitted to a streaming media platform; video playing, slicing and picture cutting are carried out through real-time transcoding; transmitting the video stream to a YOLOv < 3 + > AddNN algorithm platform; and the algorithm platform uses an improved deep neural network recognition framework to identify the annotation data set and put a result into a message queue, then the node intelligent recognition system completes node pushing and database storage by subscribing the queue, and finally the WEB system display platform accesses the nodes in the database to perform front-end page display. According to the invention, collection and recognition of data of each guarantee node in airport process management and control can be accurately completed, the labor cost is reduced, missing report and delay of data are avoided, and reliable reference is provided for efficient management of airports.

Description

technical field [0001] The invention relates to the field of pattern recognition, in particular to an intelligent recognition system for flight guarantee nodes. Background technique [0002] Under the favorable conditions of economic globalization and strong support from national policies, the aviation industry has become one of the fastest growing industries in my country in recent years. The continuous expansion of flight transportation has put forward higher requirements for the ground support service system. As an important component of the ground service production operation support system, the airport process control is mainly used to manage and monitor the flight support process. Process management and control combined with configurable daily support and processing plans can update the flight operation status in real time according to flight dynamics, operation support conditions and resource conditions. At present, the airport process control has the following main...

AI Technical Summary

Problems solved by technology

[0005] 3. There is a large error between the support time node information of the ground service operation feedback and the actual work link operation time, and the real-time and reliability are low. Once an accident occurs in the support link, it is difficult to trace the root cause of the accident;

[0006] 4. The on-duty record of specific personnel during the peak flight period is likely to cause fatigue, reduce work efficiency, be prone to subjective errors, and consume a lot of labor costs;

[0007] 5. At present, the scalability, operation friendliness and actual operation of the process control system are poor, and the visualization effect cannot be achieved. To ensure the query of operation information, a large amount of recorded data information query is required, and the workload is huge

Images