Passenger Conveyor Monitoring System Using Depth Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Passenger conveying devices, such as escalators and moving walks, face safety hazards due to unaccompanied vulnerable individuals, overcrowding, and sudden events, necessitating effective monitoring systems to prevent accidents and improve user safety.
Innovation Solution
A monitoring system utilizing imaging and depth sensing sensors to acquire data frames, process them through background modeling, foreground detection, feature extraction, and state judgment modules to identify abnormal conditions, such as unattended vulnerable individuals or overcrowding, and trigger warnings or safety measures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If imaging sensors and depth sensing sensors are used to monitor the passenger conveying device, then safety hazard detection capability is improved, but device complexity increases
Solution Approach 1:
The monitoring system is divided into multiple functional modules: data acquisition module (imaging sensors and depth sensing sensors), data processing module (background modeling, foreground detection, feature extraction), and state judgment module. Each module handles specific tasks independently, making the complex system manageable and maintainable while achieving comprehensive safety monitoring.
Solution Approach 2:
The monitoring system integrates multiple sensing capabilities (imaging and depth sensing) into a single unified platform that can detect various types of safety hazards including abnormal populations, dangerous actions, and overcrowding conditions. This multi-functional approach improves reliability without proportionally increasing complexity.
2Measurement precision
If a great amount of data from sensors is processed for comprehensive safety monitoring, then judgment accuracy is improved, but data processing time increases
Solution Approach 1:
The system extracts only the essential features from the sensor data that are relevant to safety hazard detection. The feature extraction module identifies key characteristics such as population type, action patterns, and crowd density metrics, discarding redundant information. This maintains judgment accuracy while significantly reducing processing time.
Solution Approach 2:
The system performs background modeling during normal operation to establish a baseline of typical conditions. When monitoring for abnormalities, the system compares current data against this pre-established background model, allowing for faster real-time detection without requiring complete re-analysis of all historical data.
3Measurement precision
If background modeling and foreground detection are performed on all sensor data, then abnormal population identification accuracy is improved, but computational load increases
Solution Approach 1:
The system applies different processing strategies to different regions of the monitoring area. Background modeling and foreground detection are focused on areas where abnormal populations are most likely to occur or where safety risks are highest, rather than uniformly processing all sensor data. This reduces computational load while maintaining identification accuracy in critical zones.
Data Source
AI summary
A monitoring system and a monitoring method for a passenger conveying device, and the passenger conveying device. The monitoring system comprises an imaging sensor and/or a depth sensing sensor for sensing a monitoring area of the passenger conveying device to acquire data frames; and a processing device for performing data processing on the data frames to monitor whether the monitoring area is abnormal, and configured to comprise: a background acquisition module for acquiring a background model based on data frames sensed when the monitoring area is in a normal state; a foreground detection module for comparing data frames sensed in real time with the background model to obtain a foreground object; a foreground feature extraction module for extracting a corresponding foreground object markup feature from the foreground object; and a state judgment module for judging whether the foreground object belongs to an abnormal population.