Forward collision avoidance systems considering driver's driving behavior recognized by Gaussian Mixture Model

Su, Chen; Deng, Weiwen; Sun, Hao; Wu, Jian; Sun, Bohua

doi:10.1109/ivs.2017.7995773

Cited by 22 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The false warning rate is the ratio of the number of false warnings to the total number of warnings. The false warning rate was calculated as follows: 19) where N M represents the number of vehicle collisions occurring after the collision warning.…”

Section: ) the Collision Warning Simulation Testmentioning

confidence: 99%

See 1 more Smart Citation

A Forward Collision Warning System Using Driving Intention Recognition of the Front Vehicle and V2V Communication

Yang

Wan²,

2020

IEEE Access

View full text Add to dashboard Cite

A forward collision warning (FCW) system is important for avoiding rear-end collisions. When the front vehicle slows down or the risk of rear-end collision increases, the FCW system sends a warning. However, if the warning is provided too late, the following vehicle may not have enough time to stop or slow down smoothly. Here, we propose a new FCW system that detects the driving intention of the front vehicle to provide earlier warning than previously used systems. The proposed FCW system consists of three steps. First, the driving intention of the front vehicle is determined by the driving intention recognition module. Second, the driving intention and other driving parameters of the front vehicle are transmitted to the following vehicle using vehicle-to-vehicle (V2V) communication. Finally, this information and the driving parameters of the following vehicle are used to determine the potential collision risk by the FCW module located in the second vehicle. To evaluate the proposed system, we conducted a simulation test based on PreScan (commercial software provided by TASS international) and actual road tests in various driving scenarios. The simulation test results demonstrated that the correct warning rate of the proposed system was 97.67%, which was 6.34% higher than that of the system with a fixed time-to-collision (TTC) threshold. The real vehicle test results showed that the proposed system was able to provide earlier warnings than the TTC-based system. The timely warning rate, i.e., the ratio of the number of warnings at the beginning of braking to the total number of warnings was 93.33%. The proposed system proved effective for providing early warning to the following vehicle under different driving conditions of the front vehicle. INDEX TERMS Collision warning, driving intention, hidden Markov model, V2V communication.

show abstract

Section: ) the Collision Warning Simulation Testmentioning

confidence: 99%

“…Wang et al [18] developed an adaptive longitudinal driving assistance system that adapted to the driver's habits. Su et al [19] proposed an FCW system based on a Gaussian mixture model to recognize the driver's driving behavior. Iranmanesh et al [20] designed an adaptive FCW framework based on detecting driver distraction.…”

Section: Introductionmentioning

confidence: 99%

A Forward Collision Warning System Using Driving Intention Recognition of the Front Vehicle and V2V Communication

Yang

Wan²,

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This adaptation reduces the false warning rate if the driver behavior changes. Other tunings for the warning threshold have been addressed, by using GPS data [28], drivers' expected response decelerations (ERDs) [44], and drivers' longitudinal braking behavior using GMM [37].…”

Section: Personalized Forward Collision Warningmentioning

confidence: 99%

“…First, unlike [25], we avoid designing offline thresholds and focus on the problem of continuous adaptation to the driver behavior. Unlike the other work on online adaptation [25,37,44], we do not restrict our algorithm to particular parametric models. Instead, we use an entirely data-driven approach to adapt to the human behavior.…”

Section: Personalized Forward Collision Warningmentioning

confidence: 99%

Sentio

Elmalaki

Tsai

Srivastava

2018

Proceedings of the 16th ACM Conference on Embedded Networked Sensor Systems

View full text Add to dashboard Cite

Thanks to the adoption of more sensors in the automotive industry, context-aware Advanced Driver Assistance Systems (ADAS) become possible. On one side, a common thread in ADAS applications is to focus entirely on the context of the vehicle and its surrounding vehicles leaving the human (driver) context out of consideration. On the other side, and due to the increasing sensing capabilities in mobile phones and wearable technologies, monitoring complex human context becomes feasible which paves the way to develop driver-in-the-loop context-aware ADAS that provide personalized driving experience. In this paper, we propose Sentio 1 ; a Reinforcement Learning based algorithm to enhance the Forward Collision Warning (FCW) system leading to Driver-in-the-Loop FCW system. Since the human driving preference is unknown a priori, varies between different drivers, and moreover, varies across time for the same driver, the proposed Sentio algorithm needs to take into account all these variabilities which are not handled by the standard reinforcement learning algorithms. We verified the proposed algorithm against several human drivers. Our evaluation, across distracted human drivers, shows a significant enhancement in driver experience-compared to standard FCW systems-reflected by an increase in the driver safety by 94.28%, an improvement in the driving experience by 20.97%, a decrease in the false negatives from 55.90% down to 3.26%, while adding less than 130 ms runtime execution overhead. CCS CONCEPTS • Human-centered computing → Human computer interaction (HCI); Ubiquitous computing; • Computing methodologies → Reinforcement learning;

show abstract

“…Many techniques have been proposed for better environment perception and decision making. Some typical applications for important ADAS modules include lane change detection (LCD), forward collision warning (FCW), and overtaking vehicle identification (OVI) [ 3 , 4 , 5 ]. LCD is to provide the vehicle in-lane position or lane departure information by the identification of road markings.…”

Section: Introductionmentioning

confidence: 99%

A Vision-Based Driver Assistance System with Forward Collision and Overtaking Detection

Lin

Dai

et al. 2020

Sensors

View full text Add to dashboard Cite

One major concern in the development of intelligent vehicles is to improve the driving safety. It is also an essential issue for future autonomous driving and intelligent transportation. In this paper, we present a vision-based system for driving assistance. A front and a rear on-board camera are adopted for visual sensing and environment perception. The purpose is to avoid potential traffic accidents due to forward collision and vehicle overtaking, and assist the drivers or self-driving cars to perform safe lane change operations. The proposed techniques consist of lane change detection, forward collision warning, and overtaking vehicle identification. A new cumulative density function (CDF)-based symmetry verification method is proposed for the detection of front vehicles. The motion cue obtained from optical flow is used for overtaking detection. It is further combined with a convolutional neural network to remove repetitive patterns for more accurate overtaking vehicle identification. Our approach is able to adapt to a variety of highway and urban scenarios under different illumination conditions. The experiments and performance evaluation carried out on real scene images have demonstrated the effectiveness of the proposed techniques.

show abstract

Forward collision avoidance systems considering driver's driving behavior recognized by Gaussian Mixture Model

Cited by 22 publications

References 8 publications

A Forward Collision Warning System Using Driving Intention Recognition of the Front Vehicle and V2V Communication

A Forward Collision Warning System Using Driving Intention Recognition of the Front Vehicle and V2V Communication

Sentio

A Vision-Based Driver Assistance System with Forward Collision and Overtaking Detection

Contact Info

Product

Resources

About