This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.Abstract-Most of the semantic segmentation approaches have been developed for single image segmentation, and hence, video sequences are currently segmented by processing each frame of the video sequence separately. The disadvantage of this is that temporal image information is not considered, which improves the performance of the segmentation approach. One possibility to include temporal information is to use recurrent neural networks. However, there are only a few approaches using recurrent networks for video segmentation so far. These approaches extend the encoder-decoder network architecture of well-known segmentation approaches and place convolutional LSTM layers between encoder and decoder. However, in this paper it is shown that this position is not optimal, and that other positions in the network exhibit better performance. Nowadays, state-of-the-art segmentation approaches rarely use the classical encoder-decoder structure, but use multi-branch architectures. These architectures are more complex, and hence, it is more difficult to place the recurrent units at a proper position. In this work, the multi-branch architectures are extended by convolutional LSTM layers at different positions and evaluated on two different datasets in order to find the best one. It turned out that the proposed approach outperforms the pure CNNbased approach for up to 1.6 percent.

A good and robust sensor data fusion in diverse weather conditions is a quite challenging task. There are several fusion architectures in the literature, e.g. the sensor data can be fused right at the beginning (Early Fusion), or they can be first processed separately and then concatenated later (Late Fusion). In this work, different fusion architectures are compared and evaluated by means of object detection tasks, in which the goal is to recognize and localize predefined objects in a stream of data. Usually, state-of-the-art object detectors based on neural networks are highly optimized for good weather conditions, since the well-known benchmarks only consist of sensor data recorded in optimal weather conditions. Therefore, the performance of these approaches decreases enormously or even fails in adverse weather conditions. In this work, different sensor fusion architectures are compared for good and adverse weather conditions for finding the optimal fusion architecture for diverse weather situations. A new training strategy is also introduced such that the performance of the object detector is greatly enhanced in adverse weather scenarios or if a sensor fails. Furthermore, the paper responds to the question if the detection accuracy can be increased further by providing the neural network with a-priori knowledge such as the spatial calibration of the sensors.

No abstract

No abstract

Les classifications socioprofessionnelles révèlent les visions et divisions du monde social moderne qu’elles sont supposées décrire. Ces schèmes de représentation des structures sociales varient d’une façon étonnante en fonction de l’histoire et de la culture qui les conçoivent. Ils sont étroitement liés aux conceptions respectives du rôle de l’État et à la logique de régulation juridico-administrative des populations auxquelles ils s’appliquent. L’exemple allemand illustre particulièrement bien l’affinité élective entre État et représentation statistique du monde social. Ses catégories socioprofessionnelles ont été octroyées à l’époque de Bismarck et n’ont plus bougé depuis lors. Dans cet article, nous essaierons d’élucider les conditions historiques qui ont rendu possible une telle inertie et d’en analyser les conséquences sur le plan des représentations des réalités sociales, en choisissant les PCS françaises comme base de comparaison. Nous conclurons sur une réflexion générale autour des enjeux de la construction d’un espace européen unifié et uniformisé des représentations statistiques du monde social.