V-SenseDrive: A Privacy-Preserving Road Video and In-Vehicle Sensor Fusion Framework for Road Safety & Driver Behaviour Modelling

📅 2025-09-18
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Existing driver behavior datasets predominantly originate from developed countries and thus inadequately capture behavioral diversity under mixed-traffic conditions and high uncertainty prevalent in emerging economies—such as Pakistan—while also posing facial privacy risks. To address this, we introduce V-SenseDrive: the first privacy-preserving, multimodal driver behavior dataset tailored to real-world Pakistani road environments. V-SenseDrive eliminates facial video capture entirely, instead integrating forward-facing road videos with high-frequency in-vehicle sensor data (accelerometer, gyroscope, GPS), achieving millisecond-level temporal synchronization across modalities. It covers representative scenarios—including urban arterials, secondary roads, and highways—and provides fine-grained annotations for normal, aggressive, and hazardous driving behaviors. Structured in three layers—raw, processed, and semantic—it facilitates multimodal fusion modeling. V-SenseDrive fills a critical gap in driving data for heterogeneous traffic environments in developing countries, offering a scalable, privacy-compliant, behaviorally diverse, and spatiotemporally precise benchmark for ADAS development, traffic safety analysis, and insurance risk assessment.

Technology Category

Application Category

📝 Abstract
Road traffic accidents remain a major public health challenge, particularly in countries with heterogeneous road conditions, mixed traffic flow, and variable driving discipline, such as Pakistan. Reliable detection of unsafe driving behaviours is a prerequisite for improving road safety, enabling advanced driver assistance systems (ADAS), and supporting data driven decisions in insurance and fleet management. Most of existing datasets originate from the developed countries with limited representation of the behavioural diversity observed in emerging economies and the driver's face recording voilates the privacy preservation. We present V-SenseDrive, the first privacy-preserving multimodal driver behaviour dataset collected entirely within the Pakistani driving environment. V-SenseDrive combines smartphone based inertial and GPS sensor data with synchronized road facing video to record three target driving behaviours (normal, aggressive, and risky) on multiple types of roads, including urban arterials, secondary roads, and motorways. Data was gathered using a custom Android application designed to capture high frequency accelerometer, gyroscope, and GPS streams alongside continuous video, with all sources precisely time aligned to enable multimodal analysis. The focus of this work is on the data acquisition process, covering participant selection, driving scenarios, environmental considerations, and sensor video synchronization techniques. The dataset is structured into raw, processed, and semantic layers, ensuring adaptability for future research in driver behaviour classification, traffic safety analysis, and ADAS development. By representing real world driving in Pakistan, V-SenseDrive fills a critical gap in the global landscape of driver behaviour datasets and lays the groundwork for context aware intelligent transportation solutions.
Problem

Research questions and friction points this paper is trying to address.

Detecting unsafe driving behaviors in heterogeneous road conditions
Addressing privacy concerns in driver behavior data collection
Creating multimodal datasets for emerging economies' driving environments
Innovation

Methods, ideas, or system contributions that make the work stand out.

Privacy-preserving multimodal dataset combining smartphone sensors and video
Synchronized inertial, GPS and road-facing video data collection
Structured raw, processed and semantic layers for driver behavior analysis
🔎 Similar Papers
No similar papers found.
M
Muhammad Naveed
School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST), Islamabad, Pakistan
Nazia Perwaiz
Nazia Perwaiz
National University of Sciences & Technology, Islamabad, Pakistan
Computer VisionDeep LearningPerson Re-IdentificationSurveillance
S
Sidra Sultana
School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST), Islamabad, Pakistan
M
Mohaira Ahmad
School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST), Islamabad, Pakistan
Muhammad Moazam Fraz
Muhammad Moazam Fraz
Professor, National University of Sciences and Technology
Computer VisionVideo AnalyticsPrecision AgricultureMedical Image Analysis