Binocular Vision People Counting via 3D Coordinate Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automatic systems for detecting the number of people passing through a target area, such as auto-gates at train stations and airports, fail to accurately count individuals when they are held together, backed by another person, or when baggage is present, leading to erroneous detections and sensitivity issues, particularly with methods using pressure sensors and infrared emitters.
Innovation Solution
A number-of-people detection system employing binocular cameras and a computing circuit that captures images and analyzes them using binocular vision to determine three-dimensional world coordinate relationships, allowing for accurate counting of people by identifying human bodies and distinguishing them from baggage or individuals held together.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If pressure sensors are used on the ground to detect people passing through, then it can prevent single-person tailgating, but it cannot detect when two people are held together and has high damage rate with continuous use
Solution Approach 1:
The patent replaces mechanical pressure sensors with an optical detection system using cameras and image processing algorithms. This substitution eliminates the mechanical wear and damage issues of pressure sensors while maintaining the ability to detect human presence and prevent tailgating behavior.
Solution Approach 2:
The patent introduces an intermediary detection layer (camera system and image analysis) between the physical passage and the control system. This intermediary allows for non-contact detection of multiple people, including those held together, without direct physical interaction that causes sensor damage.
2Measurement precision
If infrared emitters and receivers are installed on two sides of the target area to detect blocked infrared rays, then it can determine how many people pass through, but it cannot detect when two people are held together or one person is backed by another, and it erroneously detects baggage as people
Solution Approach 1:
The patent transitions from two-dimensional infrared detection to three-dimensional spatial analysis using binocular vision. By calculating depth information and world coordinates, the system can distinguish between people at different positions and depths, accurately detecting when people are held together or backed by others, and differentiating people from baggage based on their spatial characteristics.
3Productivity
If an infrared emitter is hoisted at the top of the target area to use infrared reflections for distance calculation, then it can determine the number of people passing through, but it still erroneously detects baggage as people and is not sensitive to crawling situations
Solution Approach 1:
The patent merges multiple detection capabilities (binocular vision for depth, characteristic pattern recognition for identification, and coordinate system integration for spatial analysis) into a unified detection system. This combination allows the system to accurately distinguish people from baggage and detect various movement patterns including crawling, while maintaining high detection speed.
4Device complexity
If traditional detection methods are used, then the system structure is relatively simple, but the detection accuracy for complex scenarios (people held together, backed by others, crawling) is poor
Solution Approach 1:
The patent creates a universal detection system that handles multiple detection scenarios (single person, multiple people held together, people backed by others, crawling individuals, and baggage differentiation) using a single integrated binocular vision platform. This multi-functional approach achieves high detection accuracy across diverse scenarios without requiring multiple separate detection systems.
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
Effectively detects the number of people in a target area, preventing tailgating and reducing false positives, while being sensitive to various scenarios like individuals holding or being backed by others, and avoiding misjudgment of baggage as people.
Implementation Method 1
the computing circuit analyzes the captured image of the binocular camera and calculates a distance from the human body to the binocular camera by using a binocular vision method to determine a three-dimensional world coordinate relationship
Data Source
AI summary
A number-of-people detection system includes at least one binocular camera and a computing circuit. A lens of the binocular camera is configured to capture at least one image of a target area. The computing circuit is electrically connected to the binocular camera, wherein the binocular camera is adapted to transmit the captured image to the computing circuit for analysis. When the captured image of the binocular camera shows that at least one human body in the target area, the computing circuit analyzes the captured image of the binocular camera and calculates a distance from the human body to the binocular camera by using a binocular vision method to determine a three-dimensional world coordinate relationship between the human body and the target area, so as to determine a number of people located in the target area.