Search

The subject matter of this research article is automatic detection of pavement distress on highway roads using computer vision algorithms. Specifically, deep learning convolutional neural network models are employed towards the implementation of the detector. Source data for training the detector come in the form of orthoframes acquired by a mobile mapping system. Compared to our previous work, the orthoframes are generally of better quality, but more importantly, in this work, we introduce a manual preprocessing step: sets of orthoframes are carefully selected for training and manually digitized to ensure adequate performance of the detector. Pretrained convolutional neural networks are then fine-tuned for the problem of pavement distress detection. Corresponding experimental results are provided and analyzed and indicate a successful implementation of the detector. [ABSTRACT FROM AUTHOR]

Self-awareness facilitates a proper assessment of cost-constrained cyber-physical systems, allocating limited resources where they are most needed. Together, situation awareness and attention are key enablers for self-awareness in efficient distributed sensing and computing networks. [ABSTRACT FROM PUBLISHER]

In the manuscript, the issue of detecting and segmenting out pavement defects on highway roads is addressed. Specifically, computer vision (CV) methods are developed and applied to the problem based on deep learning of convolutional neural networks (ConvNets). A novel neural network structure is considered, based on a pipeline of three ConvNets and endowed with the capacity for context awareness, which improves grid-based search for defects on orthoframes by considering the surrounding image content—an approach, which essentially draws inspiration from how humans tend to solve the task of image segmentation. Also, methods for assessing the quality of segmentation are discussed. The contribution also describes the complete procedure of working with pavement defects in an industrial setting, involving the workcycle of defect annotation, ConvNet training and validation. The results of ConvNet evaluation provided in the paper hint at a successful implementation of the proposed technique. [ABSTRACT FROM AUTHOR]

Computing on the edge of the Internet of things comprises among other tasks in-sensor signal processing and performing distributed data fusion and aggregation at network nodes. This poses a challenge to distributed sensor networks of low computing power devices that have to do complex fusion, aggregation and signal processing in situ. One of the difficulties lies in ensuring validity of data collected from heterogeneous sources. Ensuring data validity, for example, the temporal and spatial correctness of data, is crucial for correct in-network data fusion and aggregation. The article considers wireless sensor technology in military domain with the aim of improving situation awareness for military operations. Requirements for contemporary intelligence, surveillance and reconnaissance applications are explored and an experimental wireless sensor network, designed to enhance situation awareness to both in-the-field units and remote intelligence operatives, is described. The sensor nodes have the capability to perform in-sensor signal processing and distributed in-network data aggregation and fusion complying with edge computing paradigm. In-network data processing is supported by service-oriented middleware which facilitates run-time sensor discovery and tasking and ad hoc (re)configuration of the network links. The article describes two experiments demonstrating the ability of the wireless sensor network to meet intelligence, surveillance and reconnaissance requirements. The efficiency of distributed data fusion is evaluated and the importance and effect of establishing data validity is shown. [ABSTRACT FROM AUTHOR]