Ullrich Scheunert

A new approach for lane departure identification

This paper introduces a lane-departure identification (LDI) system of vehicles on a road with lane marks. The system perceives the LD by means of an artificial vision relying on an ad hoc approach like a boundary pixel extractor (BPE) to make up the robustness of machine vision. For the LDI,lane-related information composed of the direction and the position of lane boundaries in images is extracted. Then using the two parameters, it is determined whether or not a vehicle deviates from its lane. Except for the two parameters, the proposed system does not use any information such as lane width, a curvature,time to lane crossing, offset between the center of a lane and the center axis of a car body and other vehicle-related data. Besides, a camera calibration, any coordinate transformation, and a road model are not required. The system was demonstrated under various situations of changing illumination, in various road types without speed limits showing a quite good performance.

Multi-modal detection and parameter-based tracking of road borders with a laser scanner

This paper treats an important problem concerning driver assistance systems: the detection and tracking of road borders. The detection of the road boarders are created from the signals of a laser scanner system. Two different information can be taken from the laser signal: range and reflectivity. The range signal delivers the road edges at the basis of single scans. In opposite to that, to detect edges in the reflectivity, the reflectivity signals are arranged as images and a special image processing algorithm is developed. The fusion and tracking of this information is performed using an Extended Kalman filter where a circular curve is used as movement model.

Multi sensor based tracking of pedestrians: a survey of suitable movement models

This article presents a multi sensor approach for driver assistance systems: the detection and tracking of pedestrians in a road environment. A multi sensor system consisting of a far infrared camera and a laser scanning device is used for the detection and precise localization of pedestrians. Kalman filter based data fusion handles the combination of the sensor information of the infrared camera and of the laser scanner. Arranging a set of Kalman filters in parallel, a multi sensor/multi target tracking system was created. The usage of suitable movement models has a great influence on the performance of the tracking system. Several types of models are discussed focussing on the typical behavior of pedestrians in road environments. The multi sensor/multi target tracking system is installed on a test vehicle to obtain practical results which is discussed in this article too.

A new approach for tracking lanes by fusing image measurements with map data

This paper presents a multi sensor approach for tracking the road borders and lanes in highway scenarios. It is based on extended Kalman filtering and estimates the parameters of circle segments. In addition to a greyscale camera, our approach uses digital map information in combination with GPS, yaw and velocity measurements. The solution combines the localization task with the task of fusing white lines in the image with data from maps. Therefore, the state space contains movement parameters as well as the parameters of more than one circle segment. Simulations show that the algorithm is also very successful in situations when the vehicle makes rapid lane changes or the white lines in front of the car are temporarily not visible, because they are hidden by another object. Also in situations when the highway goes over the top of a hill, a precise estimation of the road course in front of the car is not possible. Simulated and real tests show the improvement reached by the approach. Results are compared with others which are known from the literature.

Free space determination for parking slots using a 3D PMD sensor

We present an approach for parking slot detection using a 3D Range camera of PMD type. This sensor allows referring to a large number of spatial point measurements detailed representing cuts of the observed scene. The focus of this paper is on the feature extraction out of the PMD data as well as the fusion of the features defining the free space of a parking slot. The feature extraction includes reliable and exact curb detection and robust obstacle detection. The approach for the optimal feature extraction is based on the usage of an occupancy grid in combination with a feature conform definition of detection channels.

Applying multi level processing for robust geometric lane feature extraction

Lane feature extraction is a function which is needed for example for autonomous driving and driver assistance systems. For example Lane Departure Warning and Lane Keeping rely on information provided by a lane estimation algorithm. One important step of the lane estimation procedure is the extraction of measurements or detections which can be used to estimate the shape of the road or lane. These detections are generated by white lane markers or the road border itself. Additionally traffic rules can be derived if a system is able to distinguish for example between solid and dashed lane marks as well as between the different types of lane marks itself (length, thickness). Every state estimation filter needs a properly defined model and reliable measurements to work correctly. This paper presents an approach to extract reliable lane mark measurements using multi level feature extraction [1] and classification. Geometric features will be generated for lane mark candidates and used for the distinction between true and false lane mark detections.

Multi sensor fusion for object detection using generalized feature models

This paper presents a multi sensor tmck- ing system and introduces the use of new generalized feature models. To detect and recognize objects as self- contained parts of the real world with two or more sen- sors of the same or of several types requires on the one hand fusion methods suitable for combining the data coming from the set of sensors in an optimal man- ner. This is realized by a sensor fusion principle on the basis of a Kalman filter. On the other hand it is necessary to model objects under the assumption that seveml sensors observe them. Therefore, we propose a new generalized 3D model which is suitable for this case. The paper presents a system for the detection and tracking of cars in road environments as an example. This system works with two sensors: a laser scanner and an infrared camera.

Early and Multi Level Fusion for Reliable Automotive Safety Systems

The fusion of data from different sensorial sources is today the most promising method to increase robustness and reliability of environmental perception. The project ProFusion2 pushes the sensor data fusion for automotive applications in the field of driver assistance systems. ProFusion2 was created to enhance fusion techniques and algorithms beyond the current state-of-the-art. It is a horizontal subproject in the Integrated Project PReVENT (funded by the EC). The paper presents two approaches concerning the detection of vehicles in road environments. An early fusion and a multi level fusion processing strategy are described. The common framework for the representation of the environment model and the representation of perception results is introduced. The key feature of this framework is the storing and representation of all data involved in one perception memory in a common data structure and the holistic accessibility.

ProFusion2 — towards a Modular, Robust and Reliable Fusion Architecture for Automotive Environment Perception

This publication focuses on a modular architecture for sensor data fusion regarding to research work of common interest related to sensors and sensor data fusion. This architecture will be based on an extended environment model and representation, consisting of a set of common data structures for sensor, object and situation refinement data and algorithms as well as the corresponding models. The aim of such research is to contribute to a measurable enhancement of the output performance provided by multi-sensor systems in terms of actual availability, reliability, accuracy and precision of the perception results. In this connection, investigations towards fusion concepts and paradigms, such as ‘redundant’ and ‘complementary’, as well as ‘early’ and track-based sensor data fusion approaches, are conducted, in order to significantly enhance the overall performance of the perception system.

Multi Level Fusion with Fuzzy Operators using Confidence

The paper presents a methodology for using fuzzy operators for the hierarchical fusion of processing results in a multi sensor data processing system. Tracking and fusion of intermediate results is performed in several levels of processing (signal level, several feature levels, object level). To produce higher level hypotheses on the basis of lower level components, grouping rules using certain assignment decisions are used. In this paper this is seen as a classification procedure that is step by step testing and assigning components to a higher level feature or object. For these classifications a suitable combination of a fuzzy operator for fusion and membership functions for classification is proposed to meet the requirements of the hierarchical classification and the necessity to include confidence values for that. Especially the dependencies between the n-fold one-dimensional classification and the n-dimensional classification is addressed. We use a straightforward example to demonstrate the concept of the multi level fusion and classification procedure