This paper presents a non-intrusive approach for monitoring driver drowsiness, based on driver and driving data fusion. The Percentage of Eye Closure (PERCLOS) is used to estimate the driver's state. The PERCLOS is computed on real time using a stereo vision-based system. The driving information used is the lateral position, the steering wheel angle and the heading error provided by the CAN bus. These three signals have been studied in the time and frequency domain. A multilayer perceptron neural network has been trained to fetch an optimal performance score. This system was installed in a naturalistic driving simulator. For evaluation purposes, several experiments were designed by psychologists and carried out with professional drivers. As ground truth, subjective experts' manual annotation of the driver video sequences and driving signals was used. A detection rate of 70% using individual indicators was raised up to 94% with the combination of indicators. An explanation about these results and some conclusion are presented.

Driver Assistance Systems have achieved a high level of maturity in the latest years. As an example of that, sophisticated pedestrian protection systems are already available in a number of commercial vehicles from several OEMs. However, accurate pedestrian path prediction is needed in order to go a step further in terms of safety and reliability, since it can make the difference between effective and non-effective intervention. In this paper, we consider the three-dimensional pedestrian body language in order to perform path prediction in a probabilistic framework. For this purpose, the different body parts and joints are detected using stereo vision. We propose the use of GPDM (Gaussian Process Dynamical Models) for reducing the high dimensionality of the input feature vector (composed by joints and displacement vectors) in the 3D pose space and for learning the pedestrian dynamics in a latent space. Experimental results show that accurate path prediction can be achieved at a time horizon of ≈ 0.8 s.

No abstract

Pedestrian protection systems are being included by many automobile manufacturers in their commercial vehicles. However, improving the accuracy of these systems is imperative since the difference between an effective and a noneffective intervention can depend only on a few centimeters or on a fraction of a second. In this paper, we describe a method to carry out the prediction of pedestrian locations and pose and to classify intentions up to 1 s ahead in time applying Balanced Gaussian Process Dynamical Models (B-GPDM) and naïve-Bayes classifiers. These classifiers are combined in order to increase the action classification precision. The system provides accurate path predictions with mean errors of 24.4 cm, for walking trajectories, 26.67 cm, for stopping trajectories and 37.36 cm for starting trajectories, at a time horizon of 1 second.

No abstract