Impact of COVID-19 on Traffic Signal Systems: Survey of Agency Interventions and Observed Changes in Pedestrian Activity.

The COVID-19 pandemic, the most significant public health crisis since the 1918-1919 influenza epidemic, is the first such event to occur since the development of modern transportation systems in the twentieth century. Many states across the U.S. imposed lockdowns in early spring 2020, which reduced demand for trips of various types and affected transportation systems. In urban areas, the shift resulted in a reduction in traffic volumes and an increase in bicycling and walking in certain land use contexts. This paper seeks to understand the changes occurring at signalized intersections as a result of the lockdown and the ongoing pandemic, as well as the actions taken in response to these impacts. The results of a survey of agency reactions to COVID-19 with respect to traffic signal operations and changes in pedestrian activity during the spring 2020 lockdown using two case study examples in Utah are presented. First, the effects of placing intersections on pedestrian recall (with signage) to stop pedestrians from pushing the pedestrian button are examined. Next, the changes in pedestrian activity at Utah signalized intersections between the first 6 months of both 2019 and 2020 are analyzed and the impact of land use characteristics is explored. Survey results reveal the importance of using technologies such as adaptive systems and automated traffic signal performance measures to drive decisions. While pedestrian pushbutton actuations decreased in response to the implementation of pedestrian recalls, many pedestrians continued to use the pushbutton. Pedestrian activity changes were also largely driven by surrounding land uses.

Deep Learning-Based Object Detection for Unmanned Aerial Systems (UASs)-Based Inspections of Construction Stormwater Practices.

Construction activities typically create large amounts of ground disturbance, which can lead to increased rates of soil erosion. Construction stormwater practices are used on active jobsites to protect downstream waterbodies from offsite sediment transport. Federal and state regulations require routine pollution prevention inspections to ensure that temporary stormwater practices are in place and performing as intended. This study addresses the existing challenges and limitations in the construction stormwater inspections and presents a unique approach for performing unmanned aerial system (UAS)-based inspections. Deep learning-based object detection principles were applied to identify and locate practices installed on active construction sites. The system integrates a post-processing stage by clustering results. The developed framework consists of data preparation with aerial inspections, model training, validation of the model, and testing for accuracy. The developed model was created from 800 aerial images and was used to detect four different types of construction stormwater practices at 100% accuracy on the Mean Average Precision (MAP) with minimal false positive detections. Results indicate that object detection could be implemented on UAS-acquired imagery as a novel approach to construction stormwater inspections and provide accurate results for site plan comparisons by rapidly detecting the quantity and location of field-installed stormwater practices.