Nachricht

Am Mittwoch, den 19. Dezember 2018 hält Herr Christian Daube um 16:30 Uhr im Raum P 1.4.17 einen Zwischenvortrag über seine Masterarbeit mit dem Titel:

Semantic Motion Segmentation using Deep Convolutional Neural Networks

Abstract:

The analysis of complex and challenging environments by autonomous systems requires fast and accurate algorithms for the detection of semantic classes and motion states. In previous works, conventional methods used constraints to perform semantic motion segmentation. These constraints limit the results of the motion segmentation approaches to specific scenarios. However, for handling more challenging and variable environments, generalized approaches without limiting constraints are required. Recently, deep convolutional neural networks have been used for object detection in autonomous systems acting in dynamic real-world environments. These neural networks provide a superior performance in comparison to previous approaches. In this thesis, the task is to design a deep convolutional neural network, which incorporates optical flow and semantic segmentation to detect moving objects. Thus the neural network will learn to predict the semantic class as well as the motion state at each pixel from a pair of consecutive images. Finally, the proposed neural network will be evaluated and examined with labeled datasets. Furthermore, it will be tested on a real-world environment using a camera mounted on a robot.