Review of Robotic Infrastructure Inspection Systems

Lattanzi, David; Miller, Gregory R.

doi:10.1061/(asce)is.1943-555x.0000353

Cited by 185 publications

(83 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, surveillance might be helped by technological advances (e.g., pipe crawler ROVs or snake robots; Sanfilippo et al 2016, Lattanzi and Miller 2017) that could facilitate deeper swabs and pair swabbing data with finer‐scale measurements of temperature and humidity.…”

Section: Discussionmentioning

confidence: 99%

Enzootic maintenance of sylvatic plague in Canada's threatened black‐tailed prairie dog ecosystem

et al. 2020

View full text Add to dashboard Cite

Data paucity can seem to hinder science‐based approaches to the conservation of imperiled species. Yet, even individually limited datasets can improve understanding and management of complex ecological systems when carefully integrated. We demonstrate this approach to gain first insights on the transmission ecology of Yersinia pestis in Grasslands National Park (GNP), Canada, where both the bacterium and its rodent host, the nationally threatened black‐tailed prairie dog (BTPD, Cynomys ludovicianus), reach the northern limit of their distribution in North America. Primarily flea‐borne, Y. pestis causes sylvatic plague, a disease of exceptional relevance to both human health and wildlife conservation. We integrated data collected independently by multiple organizations in 2010–2017 across 17 BTPD colonies, where the species co‐occur with Richardson's ground squirrels (RGS, Urocitellus richardsonii). Available data included estimates of BTPD density and occupancy from visual counts and colony mapping; information on flea distribution, abundance, and prevalence of infection with Y. pestis from burrow swabbing, animal combing, and PCR assays; and the response of these variables to deltamethrin application on BTPD colony sections. Our analyses suggest that sylvatic plague in GNP is maintained at an enzootic level (i.e., chronic presence affecting a low proportion of individuals) with no evidence of widespread mortality, at least partially due to reduced flea activity after spring (percentage of prevalence in burrows: April–May = 11.69–33.89%; June–September: 1.75–3.19%), low prevalence of Y. pestis in flea samples (95% CI = 0.42–2.27%), and relatively low BTPD densities. Nonetheless, reducing flea prevalence through insecticide application had a positive effect on BTPD abundance, suggesting that enzootic plague is causing chronic mortality. Because flea prevalence on hosts was higher following drier years and higher on RGS than on BTPD (26.69% vs. 3.27%), insecticide application may be particularly important during dry periods and may need to take RGS and their movements into consideration. Differences between flea communities sampled by burrow swabbing and host combing suggest that plague surveillance should integrate both methods. Effects of projected climate change on vector life cycles, flea community composition, and host–parasite interactions warrant continued monitoring and an adaptive approach to species recovery actions and plague mitigation measures.

show abstract

Section: Discussionmentioning

confidence: 99%

Enzootic maintenance of sylvatic plague in Canada's threatened black‐tailed prairie dog ecosystem

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Advanced sensing technologies facilitate inspection and data collection processes. For example, collecting 3D surface data by using Stereovision and Light Detection And Ranging (LIDAR) [149], utilizing Unmanned Aerial Vehicles (UAV), and robots such as Pioneer P3-AT and Pioneer 3-DX for inspection purposes [150]. Future studies should be conducted to investigate these technologies and their impacts on the cost, safety, and accuracy of data collection to identify high impact technologies.…”

Section: Discussionmentioning

confidence: 99%

Predictive Analytics for Roadway Maintenance: A Review of Current Models, Challenges, and Opportunities

Karimzadeh

Shoghli

2020

Civ Eng J

View full text Add to dashboard Cite

With the pressing need to improve the poorly rated transportation infrastructure, asset managers leverage predictive maintenance strategies to lower the life cycle costs while maximizing or maintaining the performance of highways. Hence, the limitations of prediction models can highly impact prioritizing maintenance tasks and allocating budget. This study aims to investigate the potential of different predictive models in reaching an effective and efficient maintenance plan. This paper reviews the literature on predictive analytics for a set of highway assets. It also highlights the gaps and limitations of the current methodologies, such as subjective assumptions and simplifications applied in deterministic and probabilistic approaches. This article additionally discusses how these shortcomings impact the application and accuracy of the methods, and how advanced predictive analytics can mitigate the challenges. In this review, we discuss how advancements in technologies coupled with ever-increasing computing power are creating opportunities for a paradigm shift in predictive analytics. We also propose new research directions including the application of advanced machine learning to develop extensible and scalable prediction models and leveraging emerging sensing technologies for collecting, storing and analyzing the data. Finally, we addressed future directions of predictive analysis associated with the data-rich era that will potentially help transportation agencies to become information-rich.In classifying highway asset items, it should be noted that state agencies have different classification. For example, California Department of Transportation (CalTrans) categorizes transportation assets in primary classes of pavements, bridges, culverts, and Intelligent Transportation Systems (ITS) [4]. However, North Carolina DOT classifies assets into seven primary groups of pavements, bridges, tunnels, roadside features, pavement markings, rest areas, and maintenance yards [10]. Among these categories, that are different from state to state, we reviewed prediction methods for a subset of assets, including pavements, pavement markings, traffic signs, barriers, and culverts.We focused mostly on recent papers published in the past 20 years. To the best of our knowledge, we included most of the significant research studies reporting the application of predictive analytics. The total number of the investigated papers versus years of publication is shown in Figure 2.

show abstract

“…Crack detection in the spatial domain using the Roberts filter resulted in the lowest number of TPs (32), but it also resulted in the lowest FP (5). Thus, while the Roberts filter was the least accurate (77%), its precision (86%) was among the highest.…”

Section: Spatial Domain Roberts Filtermentioning

confidence: 95%

“…Such inspections are costly, time-consuming, and labor-intensive [2,3]. Autonomous inspection could be a cost-effective solution to these problems if the accuracy of human inspection can be matched [3][4][5][6][7][8][9]. Image-based inspection of infrastructure for concrete delamination [10][11][12][13], cracks [14][15][16][17], and spalls [18,19] using unmanned aerial systems (UASs) have been proven effective based on previous literature [20].…”

Section: Introductionmentioning

confidence: 99%

Benchmarking Image Processing Algorithms for Unmanned Aerial System-Assisted Crack Detection in Concrete Structures

2019

View full text Add to dashboard Cite

This paper summarizes the results of traditional image processing algorithms for detection of defects in concrete using images taken by Unmanned Aerial Systems (UASs). Such algorithms are useful for improving the accuracy of crack detection during autonomous inspection of bridges and other structures, and they have yet to be compared and evaluated on a dataset of concrete images taken by UAS. The authors created a generic image processing algorithm for crack detection, which included the major steps of filter design, edge detection, image enhancement, and segmentation, designed to uniformly compare different edge detectors. Edge detection was carried out by six filters in the spatial (Roberts, Prewitt, Sobel, and Laplacian of Gaussian) and frequency (Butterworth and Gaussian) domains. These algorithms were applied to fifty images each of defected and sound concrete. Performances of the six filters were compared in terms of accuracy, precision, minimum detectable crack width, computational time, and noise-to-signal ratio. In general, frequency domain techniques were slower than spatial domain methods because of the computational intensity of the Fourier and inverse Fourier transformations used to move between spatial and frequency domains. Frequency domain methods also produced noisier images than spatial domain methods. Crack detection in the spatial domain using the Laplacian of Gaussian filter proved to be the fastest, most accurate, and most precise method, and it resulted in the finest detectable crack width. The Laplacian of Gaussian filter in spatial domain is recommended for future applications of real-time crack detection using UAS.

show abstract

Review of Robotic Infrastructure Inspection Systems

Cited by 185 publications

References 58 publications

Enzootic maintenance of sylvatic plague in Canada's threatened black‐tailed prairie dog ecosystem

Enzootic maintenance of sylvatic plague in Canada's threatened black‐tailed prairie dog ecosystem

Predictive Analytics for Roadway Maintenance: A Review of Current Models, Challenges, and Opportunities

Benchmarking Image Processing Algorithms for Unmanned Aerial System-Assisted Crack Detection in Concrete Structures

Contact Info

Product

Resources

About