People Counting Verification via Position Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for verifying the accuracy of people counting systems are prone to human error, especially when multiple individuals pass through a site simultaneously, making it difficult to determine if the accumulated number of persons is incorrect.
Innovation Solution
A verification method and system that displays a people counting video showing entry and exit boundaries and the accumulated number of persons, allowing users to determine if individuals have crossed these boundaries by comparing their initial and current positions, with an input device to modify the count when inaccuracies are detected.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a person manually counts persons by pressing a counter at the site, then the counting result can be obtained, but the person cannot keep attention without distraction for a long span of time, resulting in counting mistakes
Solution Approach 1:
The verification process is segmented into automated detection (computer vision system tracking persons) and selective manual verification (user only verifies when system detects boundary crossings). This division allows the system to maintain high accuracy while reducing the time burden on manual verifiers, as they only need to confirm specific events rather than continuously monitor and count all persons.
Solution Approach 2:
The system introduces an intermediary automated detection mechanism that monitors person movement and identifies boundary crossings. This intermediary filters and pre-processes the verification task, presenting only relevant cases to the user for confirmation, thereby maintaining accuracy while significantly reducing the time and attention required from manual verifiers.
2Measurement precision
If a person counts persons simultaneously passing through a site, then the counting result can be obtained, but it is very difficult to verify whether the number of persons counted is incorrect
Solution Approach 1:
The system implements feedback by displaying the user's verification results and allowing them to confirm or correct the automated counting. The system provides visual feedback showing which persons triggered boundary crossings and presents the accumulated count for verification. This feedback loop enables users to easily verify counts even during simultaneous passage, as they can see the specific events being counted and make corrections if needed.
Solution Approach 2:
The system creates a visual copy or representation of the persons and their movement paths, displaying them on the interface with their trajectories and boundary crossing points. This visual copy allows users to verify the counting without directly observing and counting live persons, making the verification process much easier while maintaining accuracy.
3Measurement precision
If the user verifies each person passing across the boundary manually, then the accuracy can be ensured, but the input frequency is high and the process becomes complex
Solution Approach 1:
The verification process is segmented into automated detection (computer vision system tracking persons) and selective manual verification (user only verifies when system detects boundary crossings). This division allows the system to maintain high accuracy while reducing the time burden on manual verifiers, as they only need to confirm specific events rather than continuously monitor and count all persons.
Solution Approach 2:
The automated detection system performs self-service by automatically tracking persons, identifying boundary crossings, and presenting verification requests to the user. This self-service capability reduces the complexity of the verification process, as the system handles the complex tracking and detection tasks autonomously, requiring user input only for confirmation of pre-processed events.
Data Source
AI summary
A verification method for people counting includes steps of displaying a people counting video by a display device, wherein the people counting video shows an entry and exit boundary and an accumulated number of persons; when at least one person exists in the people counting video, displaying an initial position and a current position of each of the at least one person by the display device; determining whether each of the at least one person passes across the entry and exit boundary according to the initial position and the current position of each of the at least one person by a user, so as to determine whether the accumulated number of persons is incorrect; and when the user determines that the accumulated number of persons is incorrect, receiving a modified number of persons from the user by an input device.