Urban Traffic Velocity Estimation via Multi-Source Crowd Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional urban traffic velocity estimation methods rely on limited traffic sensors, resulting in coarse-grained data coverage, especially in suburbs, making it difficult to achieve fine-grained large-scale traffic velocity estimation.
Innovation Solution
An urban traffic velocity estimation method utilizing multi-source crowd sensing data, including roadside pedestrian data and road navigation data, which involves data preprocessing, missing data filling, self-view velocity aggregation, and multi-view velocity fusion using a multi-layer perceptron to achieve 100% coverage and accurate estimation without additional device installation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional traffic sensors are used for velocity estimation, then measurement precision is improved, but spatial coverage area is limited
Solution Approach 1:
The patent combines multiple data sources including mobile navigation data, roadside pedestrian data from WIFI scanning, and historical velocity data to compensate for the limited coverage of traditional sensors. By merging these diverse data streams, the system achieves both high measurement precision and comprehensive spatial coverage across the entire road network.
Solution Approach 2:
The patent makes existing mobile devices and WIFI infrastructure serve multiple functions: mobile phones used for navigation also provide velocity data, and pedestrian mobile phones used for scanning WIFI signals also contribute to traffic velocity estimation. This multi-functionality expands coverage without deploying dedicated traffic sensors on every road section.
2Area of stationary object
If mobile navigation data is used for velocity estimation, then spatial coverage is improved, but data uniformity deteriorates due to hot spot concentration
Solution Approach 1:
The patent applies different data sources and processing strategies to different spatial locations. In hot spots with abundant navigation data, it uses navigation data primarily, while in suburbs with sparse navigation data, it relies more on roadside pedestrian data from WIFI scanning. This localized adaptation ensures uniform data distribution across all areas.
Solution Approach 2:
The patent introduces roadside pedestrian data as an intermediary source to bridge the gap in coverage. Pedestrian mobile phones scanning WIFI signals provide location and velocity information in areas where navigation data is scarce, acting as a mediator to balance the uneven data distribution caused by hot spot concentration.
3Area of stationary object
If roadside pedestrian data from WIFI scanning is used, then spatial coverage is improved, but device complexity increases due to data filtering requirements
Solution Approach 1:
The patent extracts only the necessary velocity and location information from WIFI scanning data, separating it from other irrelevant information. By extracting only the relevant features (pedestrian location, movement velocity, and timestamp), the system reduces processing complexity while maintaining comprehensive coverage.
Solution Approach 2:
The patent uses the existing mobile phone and WIFI infrastructure that pedestrians already carry and use, rather than deploying additional specialized devices. This copying of existing ubiquitous technology expands coverage while avoiding the complexity of new device deployment and maintenance.
4Measurement precision
If multi-source data fusion is implemented, then measurement precision is improved, but computational complexity increases
Solution Approach 1:
The patent segments the data fusion process into distinct modules: data collection from multiple sources, data cleaning and filtering, velocity calculation, data fusion using MLP, and result validation. This segmentation allows each module to be optimized independently, improving precision while managing computational complexity through modular processing.
Solution Approach 2:
The patent employs a multi-layer perceptron (MLP) neural network to automatically learn and adjust the optimal weighting parameters for fusing different data sources. By using parameter changes through neural network training, the system achieves high measurement precision while the learned parameters efficiently manage computational complexity during inference.
Data Source
AI summary
The present invention discloses an urban traffic velocity estimation method based on multi-source crowd sensing data. This method, based on roadside pedestrian data and road navigation data collected by smart phones, obtains a final estimated velocity through the steps of missing data filling, self-view velocity aggregation and multi-view velocity fusion. This fine-grained large-scale urban traffic velocity estimation method can achieve velocity estimation on all types of roads, including suburban road sections and paths, instead of just focusing on main roads in a city center. According to the present invention, based on data driving, the urban traffic velocity estimation method does not need to install additional devices on roads, and is low in cost and high in universality. Compared with the prior art, the urban traffic velocity estimation method has higher practicability, theoretical property and applicability, and is of great significance for improving traffic management and planning.