28 October 2022 in Transportation Research Record: Journal of the Transportation Research Board
EJErnesto Ferreira Nobre Júnior
Ernesto Ferreira Nobre Júnior
Distress measurement is essential in pavement management. Image-based distress identification is increasingly becoming an integral part of traffic speed network-level road condition surveys. This allows an aggregated summary of road conditions over the whole network, so it does not require an exact distress location within the lane. In this context, multi-label classification (MLC), based on convolutional neural networks (CNN), is proposed as a potential solution for distress identification from a network-level right-of-way (ROW) video survey. MLC has the advantage of low computing resource consumption, as it is implemented from lightweight classification networks. In this work, the developed MLC models used three different CNN architectures (VGG16, ResNet-34, and ResNet-50) to detect potholes, cracks, patches, and bleeding. The best model obtained 97% average accuracy with an F1-score of 93% in distress identification despite the variability in imaging hardware. This makes it possible to generalize the classification algorithm, allowing versatile applications and incorporating it into network-level pavement management systems. This model has good potential for fast and accurate distress identification from a video survey, avoiding the need for various types of expensive sensors like laser scanners.
26 August 2026 in Vigilância Sanitária Em Debate: Sociedade, Ciência & Tecnologia
Introduction: The advantages associated with the use of nanotechnology have led to numerous applications across a wide range of fields. Mastering the ability to manipulate the unique properties of nanomaterials tailoring them to human needs has been pivotal in this regard. In agriculture, the use of formulations containing nanoparticles with agrochemical activity (such as nano-pesticides and nano-fertilizers) is believed to offer the potential for increased productivity, reduced costs, and a decrease in adverse impacts on ecosystem health. Key among these benefits is greater profitability resulting from reduced losses and enhanced pest control effectiveness. However, the widespread adoption of this technology has been constrained by a lack of knowledge regarding its impact on ecosystem health stemming from the variability of formulations and the physicochemical characteristics of nanoparticles at their sites of action as well as the absence of an internationally harmonized risk assessment methodology that accounts for current uncertainties. Conclusions: Existing uncertainties must be resolved before governments authorize the large-scale registration and use of such formulations, in order to prevent potential damage to ecosystems.