Cooperative multi sensor network for traffic safety applications at intersections

Abstract

To significantly reduce injury and fatal accidents smart intersections equipped with sensors and communication infrastructure have been proposed. In this publication a novel multi sensor network to perceive the intersection environment is presented. Based on an intensive analysis of accident scenarios in Germany the system was designed to address 75 % of all severe and lethal accidents. 14 laserscanners, 10 cameras, signal phase tapping and an I2V communication unit have been installed at a public intersection in Aschaffenburg, Germany. By using computer based field of view modelling the sensor positions are carefully selected to avoid occlusions. Thus, the infrastructure perception system provides a bird's eye view. Our experiments show that spatial and temporal alignment of sensor data is achieved. We also demonstrate that a part of the sensor network, a calibrated stereo system, allows 3D coordinates in the field of view region of the cameras to be determined with an accuracy of 30 mm.

FPGA-Based Real-Time Pedestrian Detection on High-Resolution Images

“…The results together with the input image are transferred by a PCIe Core 2 using DMA to a PC for further processing. Further information about the system setup and its components can be found in [8,11]. Table 1 lists the resources for the scaling, HOG and SVM modules for one processing pipeline at scale 1 (unscaled Full-HD input image).…”

“…More and more applications ask for high resolution cameras to cover a wide field of view and resolve far distant objects. We concentrate on infrastructure based traffic assistance systems, which address pedestrian perception aiming at an improvement of road safety [8,12] , but the concepts presented in this paper are applicable to most other applications, too.…”

Inter-vehicle information-fusion with shared perception information

“…The IPS is described in [9] and [10]. The ego-vehicle is equipped with a laserscanner-video fusion system.…”

Road user tracking at intersections using a multiple-model PHD filter

“…With that, the Ko-PER vehicles which are able to receive the intersection broadcast can fuse the dynamic model of the intersection into their environment representation. For further details refer to [6]. On the other hand, the reference data of the vehicles which is recorded using a real-time kinematic global positioning system (RTK-GPS) with inertial measurement unit can be used to evaluate the intersection perception.…”

“…3D model of the public test side in Aschaffenburg[6] and sketch of the intersection including the mounting positions of the sensors.…”