This paper puts forward two useful methods for self-adaptation of the mutation distribution - the concepts of derandomization and cumulation. Principle shortcomings of the concept of mutative strategy parameter control and two levels of derandomization are reviewed. Basic demands on the self-adaptation of arbitrary (normal) mutation distributions are developed. Applying arbitrary, normal mutation distributions is equivalent to applying a general, linear problem encoding. The underlying objective of mutative strategy parameter control is roughly to favor previously selected mutation steps in the future. If this objective is pursued rigorously, a completely derandomized self-adaptation scheme results, which adapts arbitrary normal mutation distributions. This scheme, called covariance matrix adaptation (CMA), meets the previously stated demands. It can still be considerably improved by cumulation - utilizing an evolution path rather than single search steps. Simulations on various test functions reveal local and global search properties of the evolution strategy with and without covariance matrix adaptation. Their performances are comparable only on perfectly scaled functions. On badly scaled, non-separable functions usually a speed up factor of several orders of magnitude is observed. On moderately mis-scaled functions a speed up factor of three to ten can be expected.

/pdf/completely-derandomized-self-adaptation-in-evolution-4berz8v4fr.pdf

Completely Derandomized Self-Adaptation in Evolution Strategies

Developing on-board automotive driver assistance systems aiming to alert drivers about driving environments, and possible collision with other vehicles has attracted a lot of attention lately. In these systems, robust and reliable vehicle detection is a critical step. This paper presents a review of recent vision-based on-road vehicle detection systems. Our focus is on systems where the camera is mounted on the vehicle rather than being fixed such as in traffic/driveway monitoring systems. First, we discuss the problem of on-road vehicle detection using optical sensors followed by a brief review of intelligent vehicle research worldwide. Then, we discuss active and passive sensors to set the stage for vision-based vehicle detection. Methods aiming to quickly hypothesize the location of vehicles in an image as well as to verify the hypothesized locations are reviewed next. Integrating detection with tracking is also reviewed to illustrate the benefits of exploiting temporal continuity for vehicle detection. Finally, we present a critical overview of the methods discussed, we assess their potential for future deployment, and we present directions for future research.

/pdf/on-road-vehicle-detection-a-review-4iw469j6iz.pdf

On-road vehicle detection: a review

A forward-facing vision system for a vehicle includes a forward-facing camera disposed in a windshield electronics module attached at a windshield of the vehicle and viewing through the windshield. A control includes a processor that, responsive to processing of captured image data, detects taillights of leading vehicles during nighttime conditions and, responsive to processing of captured image data, detects lane markers on a road being traveled by the vehicle. The control, responsive to lane marker detection and a determination that the vehicle is drifting out of a traffic lane, may control a steering system of the vehicle to mitigate such drifting, with the steering system manually controllable by a driver of the vehicle irrespective of control by the control. The processor, based at least in part on detection of lane markers via processing of captured image data, determines curvature of the road being traveled by the vehicle.

Vision system for vehicle

Neural networks

A vehicular vision system includes a camera having a lens and a CMOS photosensor array having a plurality of photosensor elements. The camera is disposed at an interior portion of a vehicle equipped with the vehicular vision system. The camera one of (i) views exterior of the equipped vehicle through the windshield of the equipped vehicle and forward of the equipped vehicle and (ii) views from the windshield of the equipped vehicle into the interior cabin of the equipped vehicle. A control includes an image processor that processes image data captured by the photosensor array. The image processor processes captured image data to detect an object viewed by the camera. The photosensor array is operable at a plurality of exposure periods and at least one exposure period of the plurality of exposure periods is dynamically variable.

Vehicular vision system

Since the potential of soft computing for driver assistance systems has been recognized, much effort has been spent in the development of appropriate techniques for robust lane detection, object classification, tracking, and representation of task relevant objects. For such systems in order to be able to perform their tasks the environment must be sensed by one or more sensors. Usually a complex processing, fusion, and interpretation of the sensor data is required and imposes a modular architecture for the overall system. In this paper, we present specific approaches considering the main components of such systems. We concentrate on image processing as the main source of relevant object information, representation and fusion of data that might arise from different sensors, and behavior planning and generation as a basis for autonomous driving. Within our system components most paradigms of soft computing are employed; in this article we focus on Kalman filtering for sensor fusion, neural field dynamics for behavior generation, and evolutionary algorithms for optimization of parts of the system.

Image processing and behavior planning for intelligent vehicles

In this paper, the authors present a method for fusing algorithms and sensors for image segmentation, a process which is used in automatic traffic scene analysis. Three different solutions for image segmentation by fusion are presented and compared. The fusion of base algorithms with color information and a sensor fusion process of an optical and a radar sensor including a feedback over time is presented. A feature-in decision-out fusion process is also solved with a multi-layer perceptron (MLP) used as a coupling net.

Fusion of different sensors and algorithms for segmentation

Derzeitige Projekte am Institut fur Neuroinformatik in Bochum beschaftigen sich mit der Analyse von Strasenverkehrsszenen mittels Computer Vision [12]. Dies impliziert, wegen der durch die naturliche Umwelt aufgestellten Randbedingungen, hohe Anforderungen an die zu entwickelnden Algorithmen. Im speziellen wird versucht, Verkehrsteilnehmer aus Videobildern zu extrahieren und die so gewonnenen Objekthypothesen weiter zu attributieren (z.B. Objektklasse, Abstand, Geschwindigkeit, Gefahrenpotential hinsichtlich der beabsichtigten Eigentrajektorie etc.), um im Hinblick auf den Einsatz in Assistenzsystemen in Fahrzeugen eine moglichst genaue Beschreibung der Umwelt zu erreichen. Nicht nur die grose Vielfalt der unterschiedlichen Umweltszenarien, sondern auch das hohe Mas an Sicherheit, das die gestellte Aufgabe erfordert, bedingen ein breitbandiges und flexibles Gesamtsystem [6]. Ein Losungsvorschlag wird im folgenden behandelt.

Gesa Lorenz

Papers

Image processing and behavior planning for intelligent vehicles

Fusion of different sensors and algorithms for segmentation

Fusion von Basisalgorithmen zur Segmentierung von Straßenverkehrsszenen