Single Camera Queue Detection via World Coordinate Height Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for acquiring queuing information require multiple video cameras per queue region, increasing costs and operational complexity, especially when dealing with multiple queue regions.

Innovation Solution

A method and apparatus that utilize a single video camera to acquire queuing information by determining the location and height of pixel points in a world coordinate system, identifying human bodies, and calculating their behavior states to count queuing individuals, thereby reducing the need for multiple cameras and simplifying the process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If multiple video cameras are deployed per queue region, then queuing information can be acquired with higher reliability, but device complexity and cost increase

Engineering Contradiction:
Improvequeuing information acquisition reliabilityVSAvoidcamera deployment complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

A single video camera is designed to perform multiple functions: capturing video images of entire queue areas, identifying human body characteristics, determining behavior states (queuing vs. non-queuing), and counting queuing individuals. This multi-functional approach replaces the need for multiple specialized cameras per queue region, reducing device complexity while maintaining information acquisition reliability

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent introduces height dimension analysis by determining the location and height of pixel points in a world coordinate system. This vertical dimension enables the system to distinguish queuing behavior from non-queuing behavior by analyzing body posture and position relative to the ground, allowing accurate queuing detection with a single camera

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Measurement precision

If multiple video cameras are deployed per queue region, then measurement precision of queuing information is improved, but operational complexity increases

Engineering Contradiction:
Improvequeuing information precisionVSAvoidsystem operation simplicity
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system automatically performs the complete queuing information acquisition process without manual intervention. The video camera captures images, the processor identifies human bodies, determines behavior states through coordinate system transformation and height analysis, and automatically counts queuing individuals. This self-service automation maintains high measurement precision while significantly simplifying operational complexity

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent transforms image coordinate system data into world coordinate system data with height information, changing the parameter representation from 2D image coordinates to 3D spatial coordinates. This parameter transformation enables precise determination of body height and posture, improving measurement precision while the automated processing maintains operational simplicity

Inventive Principle:
Principle #35Parameter changes

3Device complexity

If a single video camera is used for the entire area, then device cost and complexity are reduced, but the ability to distinguish queuing behavior from non-queuing behavior becomes more difficult

Engineering Contradiction:
Improvecamera system complexityVSAvoidbehavior state detection difficulty
Core Design Contradiction:
Device complexityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent introduces height dimension analysis by determining the location and height of pixel points in a world coordinate system. This vertical dimension enables the system to distinguish queuing behavior from non-queuing behavior by analyzing body posture and position relative to the ground, allowing accurate queuing detection with a single camera

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent replaces complex mechanical multi-camera systems with a computational approach using a single camera. By transforming image coordinates to world coordinates and analyzing height parameters, the system substitutes physical camera multiplication with mathematical processing to achieve the same behavioral detection capability

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

Data Source

PatentEP3594848B1Queue information acquisition method, device and computer readable storage medium
Publication Date: 2024.07.17 HANGZHOU HIKVISION DIGITAL TECHNOLOGY CO LTD
  • EP3594848B1 patent drawingFigure 1-1~1-2
  • EP3594848B1 patent drawingFigure 2-1
  • EP3594848B1 patent drawingFigure 2-2~3

AI summary

The present application provides a method and apparatus for acquiring queuing information, and a computer-readable storage medium thereof, pertaining to the technical field of video surveillance. The method includes: acquiring a location and a height of each pixel point in a first video image in a world coordinate system, wherein the first video image is a video image captured by a video camera at a queue area; determining a behavior state of each human body at the area based on the location and the height of each pixel point; and acquiring queuing information based on the behavior state of each human body at the area at a current time. The apparatus includes a first acquiring module, a first determining module and a second acquiring module. The present application may reduce the cost.