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

Abstract

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.

Decade of Research in Review at the Auburn University Stormwater Research Facility

“…While this review covers the completed, publicly funded research, it is not all-inclusive of the efforts made at AU-SRF and additional facilities to progress the E&SC field. Additional literature exists on unmanned aerial vehicles for E&SC inspections ( 26 , 36 ) but was not included in this review. Ongoing research is being conducted including additional SB systems, detention practices, EC, and flocculant applications.…”

Soil Loss Risk Analysis for Construction Activities

“…The project entailed the construction of a four-lane-divided highway section. A digital surface model (DSM) was created by applying photogrammetry techniques on aerial imagery captured by unmanned aerial system ( 31 , 32 ). This DSM was used as an input raster layer for the contour tool in ArcMap © and a feature class of contours was created from this raster surface.…”

Safe reward‐based deep reinforcement learning control for an electro‐hydraulic servo system

“…where v d is the desired velocity. By combining (4) with (5), the nonlinear polynomial model of the tracking error of the EHSS can be formulated as follows:…”

“…Deep reinforcement learning (DRL) has been well used for nonlinear systems with uncertainties and complex dynamics, such as controlling robots 1‐3 and self‐driving vehicles, 4,5 because of its powerful ability to capture features from high‐dimensional data and learn complicated control policies 6 . Several classical DRL algorithms including asynchronous advantage actor‐critic (A3C), 7 deep Q‐network, 8 and deep deterministic policy gradient (DDPG), 9 have been developed to solve all kinds of problems.…”