Anomalous road manhole covers pose a potential risk to road safety in cities. In the development of smart cities, computer vision techniques use deep learning to automatically detect anomalous ...manhole covers to avoid these risks. One important problem is that a large amount of data are required to train a road anomaly manhole cover detection model. The number of anomalous manhole covers is usually small, which makes it a challenge to create training datasets quickly. To expand the dataset and improve the generalization of the model, researchers usually copy and paste samples from the original data to other data in order to achieve data augmentation. In this paper, we propose a new data augmentation method, which uses data that do not exist in the original dataset as samples to automatically select the pasting position of manhole cover samples and predict the transformation parameters via visual prior experience and perspective transformations, making it more accurately capture the actual shape of manhole covers on a road. Without using other data enhancement processes, our method raises the mean average precision (mAP) by at least 6.8 compared with the baseline model.
Abstract
Mechanical damages of the main structural elements of the process equipment of hazardous production facilities are quite often detected during the revision process after repairs when ...assessing the quality of the work performed. One of the most common mechanical damages on the surface of parts and assemblies of technical devices includes scratches and risks. Significant scratches and risks that have a relatively large area and depth and limit the commissioning of the facility are subject to sampling and removal during re-repair. Superficial and non-extended scratches and risks do not belong to unacceptable defects, the technical device should not be taken into account, and further operation occurs with their presence. During further operation of the facility, such defects may not manifest themselves in any way, but may be high-voltage concentrators, which in the vast majority of cases are not critical. However, the presence of two or more scratches on the surface of the structural elements, their different location relative to each other, and therefore different mutual influence, can have a significant effect on the redistribution of zones and values of increased stresses on the surfaces where they are located. In the current regulatory and technical documents for diagnostics, these points are not considered, and accordingly are not taken into account. Therefore, the actual work is to perform a strength analysis of a flat manhole cover with two scratches, which have a different location on the surface, and a different angle of intersection relative to each other.
Automated pavement distress recognition is a key step in smart infrastructure assessment. Advances in deep learning and computer vision have improved the automated recognition of pavement distresses ...in road surface images. This task remains challenging due to the high variation of defects in shapes and sizes, demanding a better incorporation of contextual information into deep networks. In this paper, we show that an attention-based multi-scale convolutional neural network (A+MCNN) improves the automated classification of common distress and non-distress objects in pavement images by (i) encoding contextual information through multi-scale input tiles and (ii) employing a mid-fusion approach with an attention module for heterogeneous image contexts from different input scales. A+MCNN is trained and tested with four distress classes (crack, crack seal, patch, pothole), five non-distress classes (joint, marker, manhole cover, curbing, shoulder), and two pavement classes (asphalt, concrete). A+MCNN is compared with four deep classifiers that are widely used in transportation applications and a generic CNN classifier (as the control model). The results show that A+MCNN consistently outperforms the baselines by 1∼26% on average in terms of the F-score. A comprehensive discussion is also presented regarding how these classifiers perform differently on different road objects, which has been rarely addressed in the existing literature.
The consumption of plastic raw materials has been exponentially growing throughout the world in the last decade and so has, in the same proportion, their associated waste. Recycling through the ...mechanical treatment of the heavy fraction of these plastics is the most economic and the safest alternative to use this waste and to recirculate it for reuse within the same industry or for other related industries located near the place where the waste is generated. In this paper, a study of characterization and post-processing of recycled high density polyethylene received by a hazardous waste manager in southern Spain is presented, an area in which containers, Intermediate Bulk Containers, and drums, originally used for oil products from refineries and petrochemical industries nearby, are employed. These high density polyethylene materials are validated to meet the requirements of the harmonized standards to be used as self-supply in the production of manhole covers. EN 124–6:2015 standard allows the use of plastic materials such as PE or PP, even using material externally reprocessed, such as material derived from thermoplastic products that have not been previously used as lids or manhole covers. Class A-15 and B-125 of the standard are oriented for the construction of these types of elements to cover or close in certain urban spaces such as pedestrian areas, parking areas or multi-story car parks for vehicles. The study shows that the recycled material fully complies with the density; it keeps unalterable during fire test after application of the coating, there are no adverse effects on artificial ageing; the decrease of the average value of the tensile impact strength by 21.84%; and achieves 6 mm of maximum deflection against the test load Fp (45.3 MPa). Therefore, it can be considered a valid scenario for the effective use of solid plastic waste in products that make up part of the urban or industrial areas, as an example of complete circularity material and offers a valid alternative to the end-of-waste condition.
Display omitted
Abstract Eine gut geplante Entwässerungsanlage im Bereich des Straßenkörpers und der darin integrierten Ingenieurbauwerke trägt maßgeblich zur Verkehrssicherheit bei. Gleichzeitig reduziert eine ...geschickte Planung in Verbindung mit geeigneten Materialien und Konstruktionen langfristig die Unterhaltungskosten und sorgt so für einen reibungslosen Betrieb der Anlage. Die Wartungsfreundlichkeit des Systems hat einen großen Anteil an der Minimierung von Sperrzeiten für Reinigungs‐ und Instandsetzungsarbeiten. Gerade bei Tunnelbauwerken sorgen u. a. die Entwässerungssysteme regelmäßig für Sperrungen aufgrund von Wartung und Instandsetzung. Besonders im Bereich der permanent überfahrenen Kontrollschächte kommt es immer wieder zu Schäden, deren Behebung mitunter zu langen Sperrzeiten der Verkehrswege führt. Mit dem Einsatz eines modifizierten Tauchwandschachts am Fahrbahnrand – ohne Schachtdeckel in der Fahrbahn – sollen der Betrieb, die Unterhaltung der Entwässerungsleitung und die daraus resultierenden Kosten reduziert werden. In vorliegendem Beitrag werden der modifizierte Tauchwandschacht und dessen Vorteile für den Betrieb von Tunnelbauwerken vorgestellt.
Translation abstract Sustainable operation of tunnel drainage without shaft covers in the roadway A well‐planned drainage system for the road infrastructure and its integrated engineering structures contributes decisively to the traffic safety in road construction. Simultaneously, a carefully engineered drainage system in conjunction with suitable materials and constructions reduces the maintenance costs in the long term, thus ensuring a smooth operation of the system. The ease of cleaning of the system plays a major part in reducing road blocking time related associated to maintenance or repair works. In tunnels in particular, the drainage systems regularly cause closures precisely due to maintenance and repair works. Damages occur regularly, particularly in areas of permanent overrun of inspection shafts, and repairing them leads often to time‐consuming road closures. In order to reduce the resulting costs to a minimum, the use of a modified baffle shaft at the edge of the carriageway should make it possible to operate and maintain the drainage pipe without a manhole cover in the carriageway. This article highlights the modified baffle shaft and its advantages for the operation of tunnels.
Abstract
In the research of the power cable anti-theft problem, the demand for high-precision positioning of the cable manhole cover is proposed. For this reason, a wireless sensor WSN node with ...ranging function is studied. The system uses the Stm32 chip as the MCU core, uses 433MH radio frequency signals and ultrasonic signals to implement a ranging circuit based on the TODA principle of arrival time difference, and sends data to the cloud server through the NB-IoT module to achieve the purpose of alarming. The system has the characteristics of good real-time performance and high positioning accuracy. It can be applied to the theft prevention of cable manhole covers, and can also be extended to the detection of indoor moving objects.
There is a need to map underground pipelines due to nonavailable existing pipeline maps caused by poor management of statutory records and insufficient updating of documentation whenever pipeline ...construction or rerouting occurs. By fusing multisource data, a novel method to map underground pipelines is proposed in this article. Statutory records of the underground pipelines are converted into the initial pipeline map. Pipeline information obtained from manhole covers and remote sensing technologies are normalized into the pipeline dataset composed of detected points. The probabilistic pipeline mapping model (PPMM) is then proposed to map the buried pipelines from the conducted pipeline dataset, with or without statutory pipeline records. In this model, each detected point is classified into the specific pipeline that most likely generates the data of this point, and detected points generated from the same pipeline are fit to revise the pipelines' locations and directions. The above classification and fitting operations are performed iteratively, and PPMM would output the pipeline map with the highest probability. Experimental studies on real-world datasets are conducted and analyzed, and the obtained results demonstrate the effectiveness of the proposed method.
Pavement images contain various objects, such as lane-marker, manhole covers, patches, potholes, and curbing. Accurate and robust computer vision algorithms are necessary to detect these various ...objects that have random shapes, colors, and sizes. In this paper, we have addressed the problem of automatic object detection in pavement images using a unified framework. To detect an object of arbitrary shape in an efficient way, we first divide the image into small consistent regions called superpixels. These superpixels are fast to calculate and preserve object boundaries. We then compute several texture and intensity features within each superpixel. After that, we train support vector machine (SVM) classifier for every feature separately in one-verses-all paradigm. In testing, we first estimate the probability of each superpixel being the part of some object of interest using these SVM classifiers. Since these superpixels' probabilistic scores are independently computed, they do not preserve neighborhood consistency. Therefore, to enforce superpixel neighborhood label consistency, we use contextual optimization technique i.e., conditional random field (CRF). The output of CRF is a pixel-wise binary label map for the objects and background. In addition, due to the lack of any publically available dataset for pavement objects' detection evaluation, we have introduced a new challenging object detection dataset for pavement images. We have performed extensive experiments on this dataset and have obtained encouraging results.
The study investigated the whole-body vibration (WBV) levels that people riding in the vehicle are exposed to while passing through the manhole covers subsidence of passenger cars. In this context, ...vibration measurements were made with a passenger car at different speeds on two separate road sections with a bump with a known geometry in the middle. With the help of these data obtained, a vehicle dynamic model was calibrated, and vehicle responses were digitized. WBVs were dynamically simulated at 2.5, 5.0, 7.5, and 10 cm manhole depths at one-to-one and five-to-one transition slopes on before and after manhole passes. The simulated vibrations were produced by increasing ten units at speeds between 10 and 50 km/h in these criteria and evaluated the effects of ride speed on WBV. Within the scope of the study, vertical vibration data were characterized and evaluated with the help of frequency weighted root-mean-square acceleration (aw), vibration dose value (VDV), and equivalent static compressive stress (Se) parameters defined in ISO 2631. The analysis found that many passes through the manhole at ride speeds of 40 km/h and above at depths of 7.5 cm and above, potential health risk occurs in the human body.
•Whole-body vibrations that occur at manhole cover passes with a passenger car were evaluated.•aw, VDV and Se parameters were used to evaluate vibration's discomfort and adverse effects on health while riding.•Significant discomfort begins at manhole covers depths of 5.0 cm and above.
Accurate and automatic detection of road surface element (such as road marking or manhole cover) information is the basis and key to many applications. To efficiently obtain the information of road ...surface element, we propose a content-adaptive hierarchical deep learning model to detect arbitrary-oriented road surface elements from mobile laser scanning (MLS) point clouds. In the model, we design a densely connected feature integration module (DCFM) to connect and reorganize feature maps of each stage in the backbone network. Besides, we propose a hierarchical prediction module (HPM) to innovatively use the reorganized feature maps to recognize different types of road surface elements, and thus, semantic information of road surface element can be adaptively expressed on multilevel feature maps. We also add a cascade structure (CS) in the head of model to detect the target efficiently, which can learn the offset between the predicted minimum bounding box of road surface element and ground truth. In experiments, we prove that the proposed method mainly contributed by HPM can maintain robust detection performance, even in the cases of unbalanced category number or overlapping of road surface elements. The experiments also prove that the proposed DCFM can improve the recognition effects of small targets. The CS for predicting boundary offset can detect each target more accurately. We also integrate the designed modules into some rotation detectors, e.g., the EAST and R3Det, and achieve the state-of-the-art results in three road scenes with different categories and uneven distribution of road surface elements, which further shows the effectiveness of the proposed method.