Vision-Based Speed Detection for Passenger Conveyors

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing passenger conveyor speed monitoring systems are cumbersome and labor-intensive, requiring manual data acquisition from complex and costly sensors, which can lead to inaccurate readings and increased risk of operational accidents due to speed anomalies like reverse running or sudden braking.

Innovation Solution

A speed detection system utilizing imaging and/or depth sensing sensors to capture sequence frames, processing them with optical flow estimation, calibration, and time calculation modules to determine speed information, reducing the need for manual data acquisition and enhancing operational safety.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a speed sensor is mounted in the passenger conveyor to monitor speed, then speed monitoring capability is improved, but device complexity and cost increase

Engineering Contradiction:
Improvespeed monitoring capabilityVSAvoidstructure complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces mechanical speed sensors with a vision-based measurement system using imaging sensors and optical flow algorithms. The system captures images of the passenger conveyor and uses computer vision to calculate speed, eliminating the need for physical sensors mounted on the conveyor structure.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates a virtual model of the passenger conveyor by capturing its visual appearance through imaging sensors. Instead of directly measuring physical parameters with sensors, the system creates image copies and analyzes them through optical flow to derive speed information.

Inventive Principle:
Principle #26Copying

2Reliability

If a speed sensor is mounted in the passenger conveyor, then speed monitoring is enabled, but maintenance time and labor cost increase

Engineering Contradiction:
Improvespeed monitoring capabilityVSAvoidmaintenance time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces manual sensor installation and calibration with an automated vision-based system. The imaging sensors and processing apparatus automatically capture images and compute speed through optical flow algorithms, eliminating time-consuming manual setup and calibration procedures.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-calibration and automatic speed calculation without requiring manual intervention. The processing apparatus automatically processes images, calculates optical flow, and derives speed information, reducing maintenance labor requirements.

Inventive Principle:
Principle #25Self-service

3Ease of operation

If manual data acquisition is used during maintenance testing, then speed information can be obtained, but measurement precision and accuracy decrease

Engineering Contradiction:
Improvedata acquisition simplicityVSAvoidspeed measurement accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent replaces manual reading and recording of speed sensor data with automated image capture and computer vision processing. The system automatically captures sequential images, calculates optical flow vectors, and derives precise speed measurements, eliminating human error in data collection.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system continuously captures images and calculates speed in real-time through continuous optical flow processing. This continuous automated measurement provides more data points and smoother speed profiles compared to discrete manual readings, improving measurement precision.

Inventive Principle:
Principle #20Continuity of useful action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This system enables efficient and accurate monitoring of passenger conveyor speeds, reducing labor and hardware costs while preventing accidents by automatically detecting speed anomalies and providing real-time monitoring.

Implementation Method 1

an imaging sensor and/or a depth sensing sensor configured to sense at least one part of the passenger conveyor to acquire sequence frames

Methodology Applied
Scientific EffectLight reflection: Reflection

Implementation Method 2

an optical flow estimation module configured to calculate, based on an optical flow method, a shift of a corresponding feature point between any adjacent frames in the sequence frames in frame coordinates

Methodology Applied
Scientific EffectOptical flow:

Data Source

PatentEP3279131B1Speed detection system and method for a passenger conveyor
Publication Date: 2020.07.15 OTIS ELEVATOR CO
  • EP3279131B1 patent drawingFigure 1
  • EP3279131B1 patent drawingFigure 2
  • EP3279131B1 patent drawingFigure 3

AI summary

The present invention relates to the field of passenger conveyor technologies, and provides a speed detection system of a passenger conveyor and a speed detection method thereof. In the speed detection system and the speed detection method of the present invention, an imaging sensor and/or a depth sensing sensor (3101, 310n) are/is used to sense at least one part of the passenger conveyor (900) to acquire sequence frames, and the sequence frames are analyzed by a processing apparatus (100) to obtain at least speed information about steps of the passenger conveyor (900).