Traffic Counting System Using Video Regions of Interest

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional traffic counting methods are prone to errors, lack accuracy, and are not comprehensive due to reliance on human labor, which is expensive and inefficient, and existing automated methods like light sensors and turnstiles have limitations such as sensitivity to environmental changes and inability to differentiate object types or determine directions accurately.

Innovation Solution

A computer vision-based system using video cameras to identify regions of interest, analyze image data over time, and count moving objects while determining their directions, reducing the need for extensive network bandwidth and infrastructure by performing calculations locally within the imaging device.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual traffic counting is used, then labor costs are high and accuracy is low, but implementation complexity is low

Engineering Contradiction:

Improvetraffic counting accuracyVSAvoidsystem implementation complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces manual mechanical counting with an automated computer vision system that uses cameras and image processing algorithms to detect and count vehicles, eliminating human labor errors and providing continuous accurate monitoring

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-service by automatically processing images through local algorithms without requiring external intervention or complex infrastructure, enabling autonomous traffic counting with minimal setup

Inventive Principle:

Principle #25Self-service

2Extent of automation

If automated traffic counting devices like light sensors are used, then automation level increases, but measurement precision deteriorates due to environmental sensitivity

Engineering Contradiction:

Improveautomation levelVSAvoidtraffic counting accuracy

Core Design Contradiction:

Extent of automationVSMeasurement precision

Solution Approach 1:

The patent replaces light sensors and turnstiles with computer vision technology that uses image processing to identify and track vehicles, providing robust automation that is not sensitive to environmental changes like lighting conditions

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system changes the detection parameter from light intensity (which is environmentally sensitive) to visual pattern recognition through image analysis, enabling stable and accurate vehicle detection across varying environmental conditions

Inventive Principle:

Principle #35Parameter changes

3Extent of automation

If existing automated methods are used, then automation increases, but ability to differentiate object types and determine directions is lost

Engineering Contradiction:

Improveautomation levelVSAvoidobject type differentiation and direction data

Core Design Contradiction:

Extent of automationVSLoss of information

Solution Approach 1:

The patent segments the traffic monitoring function into multiple analysis components: vehicle detection, type classification (bus, truck, car, motorcycle), and direction determination, allowing the system to automatically provide comprehensive traffic information including object differentiation and movement direction

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS10248870B2Traffic-counting system and method thereof

Publication Date: 2019.04.02 KAMI VISION INC

AI summary

Traffic-counting methods and apparatus are disclosed. The methods may include, in a view of traffic comprising moving objects, identifying first and second regions of interest (ROIs). The methods may also include obtaining first and second image data respectively representing the first and second ROIs. The methods may also include analyzing the first and second image data over time. The methods may further include, based on the analyses of the first and second image data, counting the moving objects and determining moving directions of the moving objects.