On-board Traffic Density Estimation Using Sensor Binning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating traffic density around a vehicle are either inaccurate, slow, or require costly infrastructure and wireless communication, failing to provide real-time, specific traffic conditions necessary for automotive systems.
Innovation Solution
An electronic controller in a host vehicle uses on-board sensors to detect and bin nearby vehicles into lanes, calculating traffic density based on the ratio of vehicle count to detected distances, allowing for real-time traffic density estimation without external infrastructure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If cell phone tracking or automated counting techniques are used to estimate traffic density, then traffic density information can be obtained, but the update rate is slow and the information is not specific to the immediate area around any particular vehicle
Solution Approach 1:
The host vehicle performs traffic density estimation itself using its own onboard sensors, eliminating the need for external infrastructure. The vehicle independently detects, tracks, and processes nearby vehicles to calculate real-time traffic density specific to its immediate surroundings, achieving both high precision and fast update rates.
Solution Approach 2:
The patent replaces centralized automated counting systems with distributed onboard sensor systems. Each vehicle independently performs detection and estimation using its own sensors, transforming the system from centralized processing to distributed autonomous measurement, thereby improving both update rate and location-specific accuracy.
2Measurement precision
If Vehicle-to-Infrastructure systems are used to characterize traffic density, then traffic density information can be obtained, but the cost of implementing hardware on both vehicles and roadside is high
Solution Approach 1:
The patent extracts the traffic density estimation function from external infrastructure and relocates it entirely to the host vehicle. By removing the infrastructure component and performing all detection, tracking, and calculation onboard, the system eliminates costly roadside hardware while maintaining estimation accuracy.
Solution Approach 2:
Instead of relying on centralized infrastructure, each vehicle creates its own local copy of the traffic monitoring system using onboard sensors. This distributed approach replaces expensive centralized infrastructure with affordable onboard systems that independently perform detection and estimation.
3Loss of information
If wireless communication is required to access traffic density information, then centralized traffic information can be obtained, but the system requires infrastructure and wireless communication capabilities
Solution Approach 1:
The host vehicle independently gathers and processes traffic information using its own sensors, eliminating the need for wireless communication with external systems. The vehicle self-sufficiently performs detection, tracking, and density calculation, reducing system complexity while ensuring information availability.
4Ease of manufacture
If drivers visually characterize traffic density, then no infrastructure is needed, but the accuracy is reduced and it is subject to human limitations
Solution Approach 1:
The patent replaces human visual estimation with automated onboard sensor systems. Sensors objectively detect and track vehicles, eliminating human limitations while maintaining system simplicity. The automated processing provides precise, consistent measurements without requiring complex infrastructure.
Data Source
AI summary
Traffic density is estimated around a host vehicle moving on a roadway. An object detection system remotely senses and identifies the positions of nearby vehicles. A controller a) predicts a path of a host lane being driven by the host vehicle, b) bins the nearby vehicles into a plurality of lanes including the host lane and one or more adjacent lanes flanking the predicted path, c) determines a host lane distance in response to a position of a farthest vehicle that is binned to the host lane, d) determines an adjacent lane distance in response to a difference between a closest position in an adjacent lane that is within the field of view and a position of a farthest vehicle binned to the adjacent lane, and e) indicates a traffic density in response to a ratio between a count of the binned vehicles and a sum of the distances.