Air traffic controller fatigue detection method, device and system based on cluster analysis
A technology for air traffic and fatigue detection, applied in instruments, alarms, etc., can solve the problems of comprehensiveness, lack of comprehensiveness, less quantitative research, and less engineering applications, and achieves strong practicability and operability, and a high degree of recognition. , easy-to-build effects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0033] figure 1 It is a system structure diagram of the present invention. The fatigue detection system integrating face and voice provided by the present invention includes a real-time audio and video full data collection platform for control seats, a controller fatigue detection database integrating face recognition and land-air call voice analysis, and a controller fatigue detection system. Indicator detection module, controller fatigue alarm module: Based on the historical statistical results in the controller fatigue detection database integrated with facial recognition and ground-air call voice analysis, the cluster analysis method is used to construct controller work status files, and the controller fatigue indicators The controller fatigue indicator detection data in the detection module is classified and comprehensively detected, and if the similarity exceeds the threshold range, an alarm is triggered.
Embodiment 2
[0035] A kind of integrated face and voice air traffic controller fatigue detection method, it is characterized in that, comprising the following steps:
[0036] Step 1: Receive the control seat video monitoring data and land-air call data obtained by the real-time audio and video full data collection device. The process of receiving the control seat video monitoring data is to collect video information in real time, perform noise reduction and filtering processing, and extract Characteristic value; the process of receiving the land-air call data is to use a cable to connect the voice signal from the distribution frame to the voice processor, and when the sound signal is detected in the system audio channel, start recording; when the audio channel is detected If there is no sound for 3 seconds, stop recording, that is to say, one recording is completed. The next time a sound signal is detected, the recording will be repeated. If there is no sound signal in the audio channel, no...
Embodiment 3
[0041]An air traffic controller fatigue detection method that integrates face and voice, detects the fatigue degree of the controller through 8 fatigue indicators, specifically includes: calculating and counting the facial expression characteristics of the controller through the video surveillance data of the control seat, so as to analyze Obtain the statistical data of PERCLOS value, average eye-closing time and yawning frequency, and analyze and analyze the land and air call data collected and processed by the real-time audio and video full data collection platform of the control seat: channel occupancy rate, number of calls, average audio frequency , the average sound intensity, and the occurrence rate of key words in land and air calls in the sector.
[0042] Among them, the PERCLOS value detection uses the ratio of the eye closure time to 60 seconds. The PERCLOS value was calculated using the P80 measurement method (the proportion of time when the area of the eyelid cov...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com