Automated valet parking services provide great potential to increase the attractiveness of electric vehicles by mitigating their two main current deficiencies: reduced driving ranges and prolonged refueling times. The European research project V-Charge aims at providing this service on designated parking lots using close-to-market sensors only. For this purpose the project developed a prototype capable of performing fully automated navigation in mixed traffic on designated parking lots and GPS-denied parking garages with cameras and ultrasonic sensors only. This paper summarizes the work of the project, comprising advances in network communication and parking space scheduling, multi-camera calibration, semantic mapping concepts, visual localization and motion planning. The project pushed visual localization, environment perception and automated parking to centimetre precision. The developed infrastructure-based camera calibration and semi-supervised semantic mapping concepts greatly reduce maintenance efforts. Results are presented from extensive month-long field tests.

One major problem, when using statistical shape information in image segmentation problems, is that many training samples are needed in order to obtain a satisfactory shape prior for a particular class, especially when the intra-class variability of the object shapes is high. To cope with this problem, we present an elegant variational formulation that allows local adaptations of the parameters associated with a trained shape prior. This enables us to obtain accurate segmentation results with a limited amount of training shapes. We provide a sound mathematical foundation for our approach and embed it into the well-known level set segmentation framework, which makes our approach applicable to a large class of problems. Moreover, we show how a smooth transition from global to local adaptations of the shape parameters can be achieved. We point out the advantages of our new variational global-to-local approach by comparing it with another level set segmentation approach that includes a global shape prior.

The a priori signal-to-noise ratio (SNR) plays an important role in many speech enhancement algorithms. In this paper, we present a data-driven approach to a priori SNR estimation. It may be used with a wide range of speech enhancement techniques, such as, e.g., the minimum mean square error (MMSE) (log) spectral amplitude estimator, the super Gaussian joint maximum a posteriori (JMAP) estimator, or the Wiener filter. The proposed SNR estimator employs two trained artificial neural networks, one for speech presence, one for speech absence. The classical decision-directed a priori SNR estimator by Ephraim and Malah is broken down into its two additive components, which now represent the two input signals to the neural networks. Both output nodes are combined to represent the new a priori SNR estimate. As an alternative to the neural networks, also simple lookup tables are investigated. Employment of these data-driven nonlinear a priori SNR estimators reduces speech distortion, particularly in speech onset, while retaining a high level of noise attenuation in speech absence.