Novel Collision Warning System using Neural Networks

  title={Novel Collision Warning System using Neural Networks},
  author={Beomseong Kim and Baehoon Choi and Jhonghyun An and Jae Pil Hwang and Euntai Kim},
  journal={Journal of The Korean Institute of Intelligent Systems},
Abstract Recently, there are many researches on active safety system of intelligent vehicle. To reduce the probability of collision caused by driver's inattention and mistakes, the active safety system gives warning or controls the vehicle toward avoiding collision. For the purpose, it is necessary to recognize and analyze circumstances around. In this paper, we will treat the problem about collision risk assessment. In general, it is difficult to calculate the collision risk before it happens… 

Figures and Tables from this paper

Real-Time Rear-End Collision-Warning System Using a Multilayer Perceptron Neural Network
  • Donghoun Lee, H. Yeo
  • Computer Science
    IEEE Transactions on Intelligent Transportation Systems
  • 2016
This paper proposes multilayer perceptron neural-network-based rear-end collision warning algorithm (MCWA) to develop a real-time CWS without any influence of human PRTs and demonstrates that the proposed algorithm outperforms other previous algorithms for predicting the potential rear- end collision by detecting severe deceleration in advance.
A study on the rear-end collision warning system by considering different perception-reaction time using multi-layer perceptron neural network
Multi-layer perceptron neural network based rear-end collision warning algorithm (MCWA) is developed and evaluated through a comparison between the conventional algorithms such as Time To Collision (TTC) and Stopping Distance Algorithm (SDA), demonstrating that the proposed algorithm outperforms other traditional algorithms for detecting and predicting the rear- end collision risks.
Vehicle forward collision warning algorithm based on road friction
Real-Time Feed-Forward Neural Network-Based Forward Collision Warning System Under Cloud Communication Environment
These findings suggest that the advanced F2N2 model can be an effective alternative for uprating the performance of the RCWS, particularly under a large delay with low MPR.
Study on V2V communication based Lateral Collision Risk
In this study, a minimum distance for collision avoidance is proposed to avoid collision with vehicles on the other lane when the host vehicle laterally moves while driving using vehicle-to-vehicle
Study on Collision Risk during V2V-based Lane Changes using Minimum Collision Avoidance Distance
This paper proposes a system to determine the minimum collision avoidance distance with vehicles in other lanes during lane change when vehicle-to-vehicle (V2V) communication is established between
Development of V2I2V Communication-based Collision Prevention Support Service Using Artificial Neural Network
The C-ITS, Artificial Neural Network-based Collision Warning Service, and ACWS(ACWS) are competing against each other in the world of artificial intelligence.


Intelligent collision risk assessment based on Neural Network Ensemble
This paper proposes to apply Neural Network Ensemble to the collision risk assessment system, and proposes to separate the input data and training each network with different data set to reduce the computation load with small error.
Collision Risk Assessment for Pedestrians' Safety Using Neural Network
A new collision risk assessment system for pedestrians’s safety by applying Monte Carlo Simulation but also Neural Networks in this problem to estimate the collision probability at each positions and velocities with high speed and low error rate.
Prediction of Centerlane Violation for vehicle in opposite direction using Fuzzy Logic and Interacting Multiple Model
A novel prediction method using IMM algorithm and fuzzy logic to increase accuracy and get rid of false positive is proposed and verified by the computer simulation that shows stable prediction result and fewer number of false alarm.
Recursive Probabilistic Approach to Collision Risk Assessment for Pedestrians` Safety
A collision risk assesment system that estimates the information of pedestrian and compute the collision probability using Monte Carlo Simulations and neural network and updates the collision risk using time histor y which is called belief.
Use of Fuzzy technique for Calculating Degree of Collision Risk in Obstacle Avoidance of Unmanned Underwater Vehicles
This paper introduces a technique for calculating the degree of collision risk used in collision avoidance system of AUVs, and a method to obtain TCPA and DCPA for 3-dimension.
Extreme learning machine: a new learning scheme of feedforward neural networks
  • G. Huang, Q. Zhu, C. Siew
  • Computer Science
    2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)
  • 2004
A new learning algorithm called extreme learning machine (ELM) for single-hidden layer feedforward neural networks (SLFNs) which randomly chooses the input weights and analytically determines the output weights of SLFNs is proposed.
A general regression neural network
  • D. Specht
  • Computer Science
    IEEE Trans. Neural Networks
  • 1991
The general regression neural network (GRNN) is a one-pass learning algorithm with a highly parallel structure that provides smooth transitions from one observed value to another.
A tutorial on support vector regression
This tutorial gives an overview of the basic ideas underlying Support Vector (SV) machines for function estimation, and includes a summary of currently used algorithms for training SV machines, covering both the quadratic programming part and advanced methods for dealing with large datasets.
Onboard Sensor-Based Collision Risk Assessment to Improve Pedestrians' Safety
A novel approach to assessing the risk of collision with a pedestrian based on the scenario and the behavior of the pedestrian is developed, based on extensive offline Monte Carlo simulations.
Extreme learning machine : a new learning scheme of feedforward neural networks Collision risk assessment for pedestrians ' safety using neural network
  • Journal of Institute of Control , robotics and Systems