The dynamic-static dual-branch deep neural network for urban speeding hotspot identification using street view image data
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.Identifying urban speeding hotspots is crucial for traffic safety. A new Dual-Branch Contextual Dynamic-Static Feature Fusion Network accurately identifies these areas by analyzing static and dynamic visual data, achieving 99.4% accuracy.
Area Of Science
- Computer Vision
- Traffic Safety Engineering
- Urban Planning
Background
- Driver perception and judgment are influenced by road environment visuals, leading to speeding.
- Identifying urban speeding hotspots can significantly enhance traffic safety and prevent incidents.
Purpose Of The Study
- To develop an accurate method for identifying urban speeding hotspots.
- To leverage both static and dynamic visual information for improved hotspot detection.
Main Methods
- Proposed a Dual-Branch Contextual Dynamic-Static Feature Fusion Network (DCDSFF-Net).
- Static branch: Multi-scale Contextual Feature Aggregation Network for global features.
- Dynamic branch: Multi-view Dynamic Feature Fusion Network for scene sequence analysis.
- Fusion structure to correlate and integrate static and dynamic features.
Main Results
- The DCDSFF-Net achieved an overall recognition accuracy of 99.4% for speeding hotspots.
- Ablation studies confirmed that fusing dynamic and static features outperformed individual branches.
- The model demonstrated superior performance compared to existing deep learning models.
- LayerCAM and GradCAM-Plus effectively extracted speeding frequency features from static and dynamic scenes, respectively.
Conclusions
- The proposed DCDSFF-Net effectively identifies urban speeding hotspots by integrating multi-modal visual data.
- Fusion of static and dynamic features is critical for accurate speeding hotspot identification.
- Visual features associated with speeding frequency are concentrated in specific environmental elements like buildings, greenery, and transition zones.
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
Related Concept Videos
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Geographic Information Systems (GIS) rely on two core types of data: spatial data and attribute data.Spatial DataSpatial data defines the physical location of features within a coordinate system, typically expressed in terms of latitude and longitude. It provides precise positioning for elements like roads, rivers, or buildings.Attribute DataAttribute data complements spatial data by adding descriptive information about these features. For example, a road's spatial data includes its start and...