Abstract-Most road marking detection systems use image processing to extract potential marking elements in their first stage. Hence, the performances of extraction algorithms clearly impact the result of the whole process. In this paper, we address the problem of extracting road markings in high resolution environment images taken by inspection vehicles in a urban context. This situation is challenging since large special markings, such as crosswalks, zebras or pictographs must be detected as well as lane markings. Moreover, urban images feature many white elements that might lure the extraction process. In prior work an efficient extraction process, called Median Local Threshold algorithm, was proposed that can handle all kinds of road markings. This extraction algorithm is here improved and compared to other extraction algorithms. An experimental study performed on a database of images with ground-truth shows that the stereovision strategy reduces the number of false alarms without significant loss of true detection.
Single-vehicle road departure accidents represent a substantial amount of today’s accidents. This paper presents the design and experimental test of an active steering assistance system that offers two functions: lane departure avoidance by temporary activation and maintaining vehicle heading by permanent activation. Each of the two functions can be used exclusively or in combination. Specific constraints related to each of the two functions are taken into account in the control design of the steering assistance by using LMI (linear matrix inequality) and BMI (bilinear matrix inequality) optimization methods. Consequently, lane overshoot is minimized for assistance activations near the border of the lane even during curve negotiation and robust lane keeping is ensured. Furthermore, the effects on lane keeping performance of simultaneous steering by the driver and the assistance are theoretically quantified. The results are verified using a fully equipped prototype vehicle. The obtained field test is consistent with the expected performance.
International audienceThis paper proposes an active steering assistance system that could act as lane departure avoidance and lane keeping system. The assistance has been designed initially for a lane departure avoidance purpose. In this paper the driver-assistance interaction is studied with the objective to allow a permanent system activation and hence a lane keeping functionality. The lane keeping performance of the assistance system is analyzed while the driver is intervening. More specifically, bounds for the lane keeping performance are theoretically computed and experimentally validated
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.