The paper at hand outlines design considerations for a data fusion system of an ADAS and describes a novel methodology to support the development process until series deployment including a glance at virtual validation. Furthermore, the novel hybrid development approach is classified with respect to state-of-the-art methodologies. The table below summarizes the conclusions and indicates the advantages of the hybrid approach.
Download the paper (PDF, 990 KB)
A Hybrid Approach for ADAS Data Fusion Algorithm Development - From High-Level Prototypes to ECUs.
Multi-Sensor Data Fusion for Checking Plausibility of V2V Communications by Vision-based Multiple-Object Tracking.
In this paper a vision-based multi-object tracking system for checking the plausibility of V2V communication is presented. The plausibility check is implemented in a prototype and based on a state-of-the-art multiple-object tracking algorithm.
Download the paper (PDF, 1500 KB)
Probabilistic Multipath Mitigation for GNSS-based Vehicle Localization in Urban Areas
Reliable and accurate positioning is a core requirement for many automotive applications. In this paper, a Bayesian satellite-based localization algorithm for vehicles is presented. It will be shown that the proposed algorithm autonomously excludes suspicious observations and decreases the positioning error down to 50 percent even when using low-cost single frequency receivers.
Download the paper (PDF, 757 KB)
Rapid Prototyping of ADAS und ITS Applications on the Example of a Vision-based Vehicle Tracking System
In this paper, an innovative design methodology for advanced driver assistance systems and data fusion applications is presented which exploits state-of-the-art software tools in order to accelerate the prototyping, the system design, and the parameterization. The benefits of this methodology are demonstrated on the example of a camera-based vehicle tracking system. In particular, it is shown how this approach facilitates the rapid comparison of different probabilistic tracking algorithms.
Download the paper (PDF, 408 KB)