HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Abstract-Many computational models of visual attention performing well in predicting salient areas of 2D images have been proposed in the literature. The emerging applications of stereoscopic 3D display bring additional depth information affecting the human viewing behavior, and require extensions of the efforts made in 2D visual modeling. In this paper, we propose a new computational model of visual attention for stereoscopic 3D still image. Apart from detecting salient areas based on 2D visual features, the proposed model takes depth as an additional visual dimension. The measure of depth saliency is derived from the eye movement data obtained from an eye-tracking experiment using synthetic stimuli. Two different ways of integrating depth information in the modeling of 3D visual attention are then proposed and examined. For the performance evaluation of 3D visual attention models, we have created an eye-tracking database which contains stereoscopic images of natural content and is publicly available along with this paper. The proposed model gives a good performance, compared to that of state-of-the-art 2D models on 2D images. The results also suggest that a better performance is obtained when depth information is taken into account through the creation of a depth saliency map rather than when it is integrated by a weighting method.

The main objective of this research is to demonstrate potential benefits, including documenting best practices and lessons learned, of implementation and evaluation of trespass prevention strategies on the rail network in West Palm Beach, Florida and all of its rights-of-way.This technical paper will describe and provide the most up-to-date results from this study, which is beginning its second year of a three year study period. The cumulative results of the trespass prevention strategies will be analyzed to better inform the determination of areas of potential risk, develop solutions to prevent and minimize risk exposure and implement successful countermeasures in the future. Preliminary analysis from the WPB corridor trespass prevention activities are described in this technical paper. The ultimate objective of the research is to aid in the development of national recommendations or guidelines for reducing trespass-related incidents and fatalities.

The United States Department of Transportation’s (US DOT) Research and Innovative Technology Administration’s John A. Volpe National Transportation Systems Center (Volpe Center), under the direction of the US DOT Federal Railroad Administration (FRA) Office of Research and Development (R&D), is leveraging the National Highway Traffic Safety Administration (NHTSA) sponsored Integrated Vehicle Based Safety System (IVBSS) Light Vehicle (LV) Field Operational Test (FOT) to collect and analyze drivers’ activities at or on approach to highway-rail grade crossings. Grade crossings in Michigan, Indiana, and Ohio were cross-referenced with IVBSS LV FOT research vehicle location to identify the time research vehicles were present at a crossing. The IVBSS LV FOT included 108 participants that took a total of 22,656 trips. Of the 22,656 total trips, 3,137 trips included a total of 4,215 grade crossing events. The analysis was based of drivers’ activities at the 4,215 grade crossing events. Both looking behavior and distractions did not significantly differ based on gender. However when analyzed per age-group, younger drivers (between 20 to 30 years old) were significantly more likely to be distracted than middle-aged drivers (between 40 to 50 years old) or older drivers (between 60 to 70 years old). For looking behavior, the data revealed that older drivers are more likely to look at least one way at or on approach to highway-rail crossing (43.8 percent exhibited this behavior) than either middle-aged drivers (35.0 percent exhibited this behavior) or younger drivers (25.3 percent exhibited this behavior).

No abstract

The United States Department of Transportation’s (USDOT) John A. Volpe National Transportation Systems Center (Volpe Center), under the direction of the USDOT Federal Railroad Administration (FRA) Office of Research and Development (R&D), recently completed a study on the use of pavement markings to reduce instances of vehicles stopping on the tracks at grade crossings. Specifically, the study evaluated the effectiveness of pavement markings placed within the dynamic envelope, the region between and immediately adjacent to the tracks at a grade crossing, and new corresponding signage at the Commercial Boulevard grade crossing (ID# 628186E) in Ft. Lauderdale, Florida. The goal of this research study was to gain an understanding of the effect of dynamic envelope pavement markings and accompanying signage on driver’s not stopping while traversing the tracks. The addition of the dynamic envelope markings and signage is intended to make this area more pronounced, resulting in fewer motorists entering the dynamic envelope if they are unable to exit the other side. Researchers coded driver stopping behavior at this crossing before and after the surface treatments were installed. Vehicles were coded as having stopped in one of four zones: behind the stop line and gate arm (Zone 1), past the stop line but before the tracks (Zone 2), on the tracks (Zone 3), or immediately after the tracks (Zone 4). Stopping in Zone 3 is considered to be the most dangerous behavior that a driver could perform, while stopping in Zone 1 is the safest. The goal of the added markings and signage is to reduce the number of vehicles which come to a stop within the dynamic envelope, thus reducing the possibility that a vehicle is present on the tracks when a train approaches resulting in a collision. The addition of the dynamic envelope pavement markings and modified signage resulted in a statistically significant change in driver stopping behavior. Specifically, the pavement markings and signage reduced the proportion of vehicles that stopped in Zone 3, resulting in a 45% reduction in vehicles stopped in Zone 3 for eastbound vehicles and 14% for westbound vehicles. They also increased the proportion of vehicles stopping in Zone 1, which is the safest behavior a driver can perform (9% increase for eastbound and 6% increase for westbound). Additionally, fewer vehicles were found to stop in both Zone 2 and Zone 4, which are both moderately dangerous. Based on these results, the Florida Department of Transportation is exploring the use of this safety treatment at additional grade crossings with a high risk for unsafe vehicle stopping behavior.