Probabilistic Analysis of Dynamic Scenes and Collision Risks Assessment to Improve Driving Safety

TLDR

Urban driving scenes are analyzed and interpreted to understand dynamic traffic environments. The study aims to assess collision risks for the ego‑vehicle. We integrated Bayesian Occupancy Filter‑based sensor fusion of visual, telemetric, and inertial data on a Lexus car and simulator, using Hidden Markov Models and Gaussian processes to estimate stochastic collision risks and enable parallel computation. Tests confirm the approach is relevant and feasible for enhancing driving safety.

Abstract

The article deals with the analysis and interpretation of dynamic scenes typical of urban driving. The key objective is to assess risks of collision for the ego-vehicle. We describe our concept and methods, which we have integrated and tested on our experimental platform on a Lexus car and a driving simulator. The on-board sensors deliver visual, telemetric and inertial data for environment monitoring. The sensor fusion uses our Bayesian Occupancy Filter for a spatio-temporal grid representation of the traffic scene. The underlying probabilistic approach is capable of dealing with uncertainties when modeling the environment as well as detecting and tracking dynamic objects. The collision risks are estimated as stochastic variables and are predicted for a short period ahead with the use of Hidden Markov Models and Gaussian processes. The software implementation takes advantage of our methods, which allow for parallel computation. Our tests have proven the relevance and feasibility of our approach for improving the safety of car driving.