A Sensor for Urban Driving Assistance Systems Based on Dense Stereovision

Abstract

Advanced driving assistance systems (ADAS) form a complex multidisciplinary research field, aimed at improving traffic efficiency and safety. A realistic analysis of the requirements and of the possibilities of the traffic environment leads to the establishment of several goals for traffic assistance, to be implemented in the near future (ADASE, INVENT, PREVENT, INTERSAFE) including: highway, rural and urban assistance, intersection management, pre-crash. While there are approaches to driving safety and efficiency that focus on the conditions exterior to the vehicle (intelligent infrastructure), it is reasonable to assume that we should expect the best results from the in-vehicle systems. Traditionally, vehicle safety is mainly defined by passive safety measures. Passive safety is achieved by a highly sophisticated design and construction of the vehicle body. The occupant cell has become a more rigid structure in order to mitigate deformations. The frontal part of vehicles has been improved as well, e.g. it incorporates specially designed "soft" areas to reduce the impact in case of a collision with a pedestrian. In the recent decades a lot of improvements have been done in this field. Similarly to the passive safety systems, primitive active safety systems, such as airbags, are only useful when the crash is actually happening, without much assessment of the situation, and sometimes they are acting against the well-being of the vehicle occupants. It has become clear that the future of the safety systems is in the realm of the artificial intelligence, systems that sense, decide and act. Sensing implies a continuous, fast and reliable estimation of the surroundings. The decision component takes into account the sensorial information and assesses the situation. For instance, a pre-crash application must decide whether the situation is of no danger, whether the crash is possible or when the crash is imminent, because depending on the situation different actions are required: warning, emergency braking or deployment of irreversible measures (internal airbags for passenger protection, or inflatable hood for pedestrian protection). While warning may be annoying, and applying the brakes potentially dangerous, deploying non-reversible safety causes permanent damage to the vehicle, and therefore the decision is not to be taken lightly. However, in a pre-crash scenario it is even more damaging if the protection systems fail to act. Therefore, it is paramount that the

Barriers detection method for stereovision-based ACC systems

“…The proposed method can be improved in order to extend the detection range and the robustness of the detection by: -Using a drivable tunnel derived from the car dynamics and 3D elevations map [8] as search region in the 3D validation step in cases when the current lane information is not available.…”

“…This can be explained by the impossibility to correlate long horizontal edge segments which appear at the boom-background frontier (Figure 1.a). Even if the boom's surface has some artifacts which can be correlated (Figure 1.b), the 3D points are so sparse that are ignored by a grouping algorithm [8] which groups 3D points in objects on density and vicinity criteria. The same applies to other horizontal structures as transversal road markings (Figure 1.c) a.…”

“…The integration of the barrier detection module in a stereo-vision based application for driving assistance systems [8] is presented in the flowchart from Figure 11. The input dependences of the barriers' detection module are the list of 3D reconstructed points, the vertical profile of the road (if detected by the lane detection module) and the horizontal profile of the current lane's center (if available).…”

“…Dense-stereo vision sensors [6], [7] have been proved to be the most reliable ones in such scenarios and are able to detect and track clothoid and nonclothoid lanes, drivable areas in the absence of lane markings, cars, pedestrians and other types of obstacles [8].…”

Camera motion estimation using monocular and stereo-vision

“…The algorithm makes full usage of the available 3D data, as supplied by a dense stereo reconstruction hardware system (described in [10]). The algorithm is integrated into a complete stereo vision based driving assistance system, described in [11] and uses the results of the lane detection and object detection modules. The stereo reconstruction hardware provides 3D coordinates for some 2D image pixels, allowing us to perform all the computations in 3D.…”