Robust Detection of Anomalous Driving Behavior

Matousek, Matthias; Yassin, Mahmoud; Al-Momani, Ala'a; Heijden, Rens W. van der; Kargl, Frank

doi:10.1109/vtcspring.2018.8417777

Cited by 28 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They detect the invasion of centerlines based on road image data and centralized ML models. Matousek et al [14] analyze an LuST-based simulated dataset to detect driving behavior. Their approach handles the overlapping behaviors.…”

Section: B Anomalous Driving Detectionmentioning

confidence: 99%

CAD3: Edge-facilitated Real-time Collaborative Abnormal Driving Distributed Detection

Alhilal

Braud

Sut

et al. 2021

2021 IEEE 41st International Conference on Distributed Computing Systems (ICDCS)

View full text Add to dashboard Cite

Speeding, slowing down, and sudden acceleration are the leading causes of fatal accidents on highways. Anomalous driving behavior detection can improve road safety by informing drivers who are in the vicinity of dangerous vehicles. However, detecting abnormal driving behavior at the city-scale in a centralized fashion results in considerable network and computation load, that would significantly restrict the scalability of the system. In this paper, we propose CAD3, a distributed collaborative system for road-aware and driver-aware anomaly driving detection. CAD3 considers a decentralized deployment of edge computation nodes on the roadside and combines collaborative and context-aware computation with low-latency communication to detect and inform nearby drivers of unsafe behaviors of other vehicles in real-time. Adjacent edge nodes collaborate to improve the detection of abnormal driving behavior at the city-scale. We evaluate CAD3 with a physical testbed implementation. We emulate realistic driving scenarios from a real driving data set of 3,000 vehicles, 214,000 trips, and 18 million trajectories of private cars in Shenzhen, China. At the microscopic (road) level, CAD3 significantly improves the accuracy of detection and lowers the number of potential accidents caused by false negatives up to four times and 24 times as compared to distributed standalone and centralized models, respectively. CAD3 can scale up to 256 vehicles connected to a single node while keeping the end-to-end latency under 50 ms and a required bandwidth below 5 mbps. At the mesoscopic (driver-trip) level, CAD3 performs stable and accurate detection over time, owing to local RSU interaction. With a dense deployment of edge nodes, CAD3 can scale up to the size of Shenzhen, a megalopolis of 12 million inhabitant with over 2 million concurrent vehicles at peak hours.

show abstract

Section: B Anomalous Driving Detectionmentioning

confidence: 99%

CAD3: Edge-facilitated Real-time Collaborative Abnormal Driving Distributed Detection

Alhilal

Braud

Sut

et al. 2021

2021 IEEE 41st International Conference on Distributed Computing Systems (ICDCS)

View full text Add to dashboard Cite

show abstract

“…These approaches compare the behavior of vehicles and mark outliers. For instance, in [8], three ML algorithms, namely Support Vector Machine (SVM), Isolation Forest (iForest), and K-Nearest Neighbors (K-NN), are used to detect outlier drivers. Also, the authors of [9] present a reckless driver detection framework which uses vehicular collaboration to collect data and then apply support vector machine (SVM) and decision-tree models to measure every vehicle's driving performance.…”

Section: Related Workmentioning

confidence: 99%

“…Therefore, a huge dataset of normal patterns is required, which is not easy to acquire. Other solutions rely on finding outliers in traffic flows [8], [9]. These approaches are based on two assumptions.…”

Section: Introductionmentioning

confidence: 99%

DeepFlow: Abnormal Traffic Flow Detection Using Siamese Networks

Sabour¹,

Rao²,

Ghaderi³

2021

Preprint

View full text Add to dashboard Cite

Nowadays, many cities are equipped with surveillance systems and traffic control centers to monitor vehicular traffic for road safety and efficiency. The monitoring process is mostly done manually which is inefficient and expensive. In recent years, several data-driven solutions have been proposed in the literature to automatically analyze traffic flow data using machine learning techniques. However, existing solutions require large and comprehensive datasets for training which are not readily available, thus limiting their application. In this paper, we develop a traffic anomaly detection system, referred to as DeepFlow, based on Siamese neural networks, which are suitable in scenarios where only small datasets are available for training. Our model can detect abnormal traffic flows by analyzing the trajectory data collected from the vehicles in a fleet. To evaluate DeepFlow, we use realistic vehicular traffic simulations in SUMO. Our results show that DeepFlow detects abnormal traffic patterns with an F1 score of 78%, while outperforming other existing approaches including: Dynamic Time Warping (DTW), Global Alignment Kernels (GAK), and iForest.

show abstract

“…Abnormal driving behaviours, such as aggressive driving are a significant factor in fatal accidents. Matousek et al [222] analyse an offline large simulated data set based on LuST [223] to detect abnormal driving activity (extremely aggressive or passive driving behaviours). Chen et al [205] analyse sensory data using an offline training and online detection approach to develop real-time abnormal driving behaviours identification and detection system.…”

Section: Real-time Context-aware Abnormal Driving Activity Detectionmentioning

confidence: 99%

Distributed Vehicular Computing at the Dawn of 5G: a Survey

Alhilal

Braud

Hui³

2020

Preprint

View full text Add to dashboard Cite

Recent advances in information technology have revolutionized the automotive industry, paving the way for next-generation smart and connected vehicles. Connected vehicles can collaborate to deliver novel services and applications. These services and applications require 1) massive volumes of data that perceive ambient environments, 2) ultrareliable and low-latency communication networks, 3) realtime data processing which provides decision support under application-specific constraints. Addressing such constraints introduces significant challenges with current communication and computation technologies. Coincidentally, the fifth generation of cellular networks (5G) was developed to respond to communication challenges by providing an infrastructure for low-latency, high-reliability, and high bandwidth communication. At the core of this infrastructure, edge computing allows data offloading and computation at the edge of the network, ensuring low-latency and context-awareness, and pushing the utilization efficiency of 5G to its limit. In this paper, we aim at providing a comprehensive overview of the state of research on vehicular computing in the emerging age of 5G. After reviewing the main vehicular applications requirements and challenges, we follow a bottom-up approach, starting with the promising technologies for vehicular communications, all the way up to Artificial Intelligence (AI) solutions. We explore the various architectures for vehicular computing, including centralized Cloud Computing, Vehicular Cloud Computing, and Vehicular Edge computing, and investigate the potential data analytics technologies and their integration on top of the vehicular computing architectures. We finally discuss several future research directions and applications for vehicular computation systems.

show abstract

Robust Detection of Anomalous Driving Behavior

Cited by 28 publications

References 8 publications

CAD3: Edge-facilitated Real-time Collaborative Abnormal Driving Distributed Detection

CAD3: Edge-facilitated Real-time Collaborative Abnormal Driving Distributed Detection

DeepFlow: Abnormal Traffic Flow Detection Using Siamese Networks

Distributed Vehicular Computing at the Dawn of 5G: a Survey

Contact Info

Product

Resources

About