Abstract
Abstract. Today, cameras mounted in vehicles are used to observe the driver as well as the objects around a vehicle. In this article, an outline of a concept for image based recognition of dynamic traffic situations is shown. A dynamic traffic situation will be described by road users and their intentions. Images will be taken by a vehicle fleet and aggregated on a server. On these images, new strategies for machine learning will be applied iteratively when new data has arrived on the server. The results of the learning process will be models describing the traffic situation and will be transmitted back to the recording vehicles. The recognition will be performed as a standalone function in the vehicles and will use the received models. It can be expected, that this method can make the detection and classification of objects around the vehicles more reliable. In addition, the prediction of their actions for the next seconds should be possible. As one example how this concept is used, a method to recognize the illumination situation of a traffic scene is described. This allows to handle different appearances of objects depending on the illumination of the scene. Different illumination classes will be defined to distinguish different illumination situations. Intensity based features are extracted from the images and used by a classifier to assign an image to an illumination class. This method is being tested for a real data set of daytime and nighttime images. It can be shown, that the illumination class can be classified correctly for more than 80% of the images.
Highlights
Today, recognizing the position of objects around a vehicle is an important task for advanced driver assistance systems
That the quality of the recognition of dynamic traffic situations will be improved with the proposed concept
The decision between dangerous and non-dangerous traffic situations for a vehicle by using the recognition for dynamic traffic situations should be taken as example
Summary
Today, recognizing the position of objects around a vehicle is an important task for advanced driver assistance systems. Before the detector can be used, an underlying model and the corresponding parameters must be determined These values can be learned in a training step by evaluating a large set of training samples. To be able to use the object detector with a suitable parameter set, it is necessary to recognize the typical illumination situation before. To avoid accidents, it is advisable, to detect the objects around a vehicle, the driver of the recording vehicle should be considered. Depending on the grade of attention, a driver assistance system can take different measures like showing an optical warning message to increase the situation awareness of the driver or do an automated braking to avoid a collision
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
