Published on Thu Jan 17 2019

FARSA: Fully Automated Roadway Safety Assessment

Weilian Song, Scott Workman, Armin Hadzic, Xu Zhang, Eric Green, Mei Chen, Reginald Souleyrette, Nathan Jacobs

This paper addresses the task of road safety assessment. We propose to automate this process using a deep convolutional neural network. Our network also estimates many other road-level attributes, including curvature, roadside hazards, and the type of median.

0
0
0
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 street-level 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 road-level attributes, including curvature, roadside hazards, and the type of median. To support this, we incorporate task-specific 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.

Sat Dec 01 2018
Machine Learning
Assigning a Grade: Accurate Measurement of Road Quality Using Satellite Imagery
Roads are critically important infrastructure to societal and economic development. However, monitoring those investments can be time-consuming and laborious. In this work, we develop a model for monitoring the quality of road infrastructure using satellite imagery.
0
0
0
Sun Feb 11 2018
Computer Vision
RoadTracer: Automatic Extraction of Road Networks from Aerial Images
Mapping road networks is currently both expensive and labor-intensive. RoadTracer uses an iterative search process guided by a CNN-based decision function to derive the road network graph.
0
0
0
Wed Jun 13 2018
Computer Vision
Fully Convolutional Network for Automatic Road Extraction from Satellite Imagery
An approach for automatic road extraction based on a fully convolutional neural network of U-net family. This network consists of ResNet-34 pre-trained on an original image and decoder adapted from vanilla U-Net.
0
0
0
Mon Jul 15 2019
Machine Learning
Mapping road safety features from streetview imagery: A deep learning approach
Each year, around 6 million car accidents occur in the U.S. on average. Road safety features (e.g., concrete barriers, metal crash barriers, rumble strips) play an important role in preventing or mitigating vehicle crashes. Accurate maps of road safety features is an important
0
0
0
Tue Oct 22 2019
Computer Vision
WeatherNet: Recognising weather and visual conditions from street-level images using deep residual learning
Extracting information related to weather and visual conditions is indispensable for scene awareness. Despite the significance of this subject, it is still not fully addressed by the machine intelligence relying on deep learning and computer vision. A pipeline of four deep Convolutional Neural Network (CNN) models, so-called the WeatherNet, is trained.
0
0
0
Tue Jan 31 2017
Computer Vision
DeepNav: Learning to Navigate Large Cities
We present DeepNav, a Convolutional Neural Network (CNN) based algorithm for navigating large cities using locally visible street-view images. The DeepNav agent learns to reach its destination quickly by making the correct navigation decisions at intersections. We propose3 supervised learning approaches for the navigation task.
0
0
0