Sin título

Página 1

Goal: Develop a cost-effective and accurate vehicle speed estimation system using monocular video data.

Why It's Important: This approach addresses the limitations of traditional hardware-based systems like LiDAR and GPS, which are costly and not easily scalable.

Research Problem:

Limitations of Traditional Methods:

High costs and complexity of deployment.

Reliance on expensive hardware like LiDAR, GPS, and radar.

Proposed Solution: A software-based approach using video data and machine learning, providing a scalable alternative.

Methodologies:

Methodology 1: YOLOv3 and Optical Flow

Components Used:

YOLOv3: For real-time vehicle detection.

DeepSORT: For tracking detected vehicles across frames.

Pyramidal Lucas-Kanade Optical Flow: To calculate speed using pixel displacement and virtual intrusion lines.

Performance Metrics:

Achieved a Mean Absolute Error (MAE) of 3.38 km/h.

Mean Square Error (MSE) also minimized.

Methodology 2: Deep Homography Transformation Network

Components Used:

Deep Homography Transformation: Converts monocular views to bird's-eye perspectives for better accuracy.

YOLOv4: Enhances vehicle detection capabilities.

CSPDarkNet53: Used for feature extraction to handle occlusion issues.

Performance Improvements:

MSE reduction from 14.02 to 6.56 on datasets like BrnoCompSpeed and AIC18.

Integration of Methods:

Combined Framework: Leverages both methodologies for improved accuracy and performance.

Benefits:

Real-time traffic monitoring.

Reduced reliance on expensive hardware.

Enhanced safety and efficiency in ITS applications.

Key Advantages:

Cost-Effectiveness: Eliminates the need for high-cost hardware.

Scalability: Easily deployable across different environments and infrastructure.

Accuracy: High precision in speed estimation using state-of-the-art computer vision and deep learning techniques.

Versatility: Applicable in various ITS applications, from traffic management to autonomous vehicle systems.

Results and Validation:

Datasets Used: Validated on a dataset of 813 vehicles, BrnoCompSpeed, and AIC18.

Error Metrics: Achieved low MAE and MSE, indicating high accuracy.

Comparison: Outperformed existing state-of-the-art methods in speed estimation accuracy.

Challenges and Solutions:

Occlusion Issues: Addressed using bird's-eye transformation and advanced detection networks.

Complexity of Tracking: Utilized DeepSORT for robust tracking across frames.

Environmental Factors: Adaptability to various lighting and weather conditions through data augmentation and robust model training.

Future Work and Applications:

Potential Enhancements: Explore further integration of additional data sources (e.g., IoT devices) to improve accuracy.

Applications: Extend to smart city initiatives, traffic violation enforcement, and support for autonomous vehicles.

Scalability: Plan for larger scale deployment and real-world testing in diverse traffic scenarios.

Conclusion:

Summary: The proposed solution offers a novel, scalable approach to vehicle speed estimation using monocular video data, advancing the field of intelligent transportation systems.

Impact: Promises to significantly improve traffic safety and management while reducing costs and complexity associated with traditional methods.

Página 2