FARSA: Fully Automated Roadway Safety Assessment

Abstract

This paper addresses the task of road safety assessment. An emerging approach for conducting such assessments in the United States is through the US Road Assessment Program (usRAP), which rates roads from highest risk (1 star) to lowest (5 stars). Obtaining these ratings requires manual, fine-grained labeling of roadway features in streetlevel panoramas, a slow and costly process. We propose to automate this process using a deep convolutional neural network that directly estimates the star rating from a street-level panorama, requiring milliseconds per image at test time. Our network also estimates many other roadlevel attributes, including curvature, roadside hazards, and the type of median. To support this, we incorporate taskspecific attention layers so the network can focus on the panorama regions that are most useful for a particular task. We evaluated our approach on a large dataset of real-world images from two US states. We found that incorporating additional tasks, and using a semi-supervised training approach, significantly reduced overfitting problems, allowed us to optimize more layers of the network, and resulted in higher accuracy.

Explainable, automated urban interventions to improve pedestrian and vehicle safety

“…We used our same ResNet architecture for each of those binary classifiers. After training, we obtained a balanced accuracy of 0.47 (with a the dummy classifier accuracy of 0.25) which is comparable to the performance reported in [20] for a similar task. That is, the ResNet architecture can also provide competitive results for a finer assessment of pedestrian safety.…”

“…What's more, the disposition of those objects is related to hazard indices, adding a perceptual-attentional link to other possible concomitant variables that affect vehicle and pedestrian safety. Along this line, our work can be used in conjunction with other similar pipelines, such as [20], which automates road safety assessment in terms of infrastructure and estimates road attributes, or may contribute to more focused analysis, relating what a person pays attention to while driving [73]. Additionally, further information such as temporal accident data, or factors known to influence accident rate (e.g.…”

“…The combination of increasingly available street-level imagery sources and city open data portals, together with advances in the field of computer vision and larger training datasets [15,16], has opened up promising new opportunities for facing challenges in urban science. Examples include the quantification of physical change and pattern identification in cities [17][18][19], road safety assessment [20], the prediction of human-perceived features of street scenes [21,22], the automated estimation of demographic variables across the United States [23] and Great Britain [24], or the beautification of urban images through the generation of prototypes [25]. Turning to transportation research, however, computer vision has focused mostly on traffic control and surveillance [26], and automatic detection and collision prevention [27,28] for autonomous vehicles.…”

Dynamic Traffic Modeling From Overhead Imagery

“…However, identifying roads is just the first step. Other work has focused on estimating properties of roads, including safety [30].…”

Holistic Multi-View Building Analysis in the Wild with Projection Pooling

“…(a) As street-view imagery is becoming more ubiquitous, it brings new research opportunities. One can assess socioeconomic statistics [15,16], evaluate the safety, beauty and popularity of the neighborhood [1,12,5], estimate the road safety [40], perform road scene segmentation [10], and determine precise geolocalization of the car [2,19,34,3]. Combining house rental ads and streetview imagery allows for performing 3D building reconstruction [8].…”