In this paper we propose a novel part-based approach to scene understanding, that allows us to infer the properties of traffic scenes, such as location and geometry of lanes and roads. Lanes and roads are parts of our undirected graphical model in which nodes represent parts or sub-parts of scenes and edges represent spatial constraints. Spatial constraints are statistically formulated and allow us to take advantage of low-level relations as well as high-level contextual information. The estimation of scene properties is formulated as an inference problem, which is solved using non-parametric belief propagation. Inferring about high-level scene properties, while relying on error-prone sensory cues is challenging and computational expensive. Therefore, we introduced a novel depth-first message passing scheme. This scheme is applied to several challenging real world scenarios showing robust results and real-time performance.
The vehicular market is undergoing a profound transformation that includes a trend toward fully automated driving. When travelling in automated systems, the main task is no longer driving. Therefore, the interior design of automated vehicles requires a renovation to adapt to new use cases. With this motivation, the use case of sleeping while travelling was chosen for this user study, in which different seat configuration conditions were evaluated. The three preselected seat positions for this research included the upright, reclined and flat seat positions. To the best of our knowledge, this study is the first to examine the comfort of different seat angles in meeting the need to sleep in a moving vehicle. Since the physical experience of the occupants with a high-fidelity seat prototype is essential to evaluate the new interior concept of the vehicle of the future, in this study, the experimental participants were asked about their perception of comfort and overall user experience while travelling by car under close-to-real test conditions. Therefore, the primary objective of this evaluation was to explore different seat configurations and find the most suitable seat position for the use case of sleeping in a car while moving. Our findings suggest that users prefer reclining and flat seats in short-/medium- and long-term use cases, respectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.