Video Inspection Research Articles

Features of recurrence and contralateral metachronous inguinal hernia (CMIH) in the patients underwent laparoscopic percutaneous extraperitoneal closure (LPEC) for pediatric inguinal hernia.

Recurrence and contralateral metachronous inguinal hernia (CMIH) are important postoperative complications in patients with inguinal hernia (IH) who undergo laparoscopic percutaneous extraperitoneal closure (LPEC). This study aimed to evaluate the incidence and causes of recurrence and CMIH after LPEC. Among the included patients, 2484 hernias were included in the analysis of recurrence. CMIH was analyzed in 2094 cases with unilateral IH without a history of contralateral IH. Overall, 21 hernias (0.85%) recurred and seven patients (0.34%) experienced CMIH. Based on the video inspection, injury and skipping of the peritoneum were suspected as the cause of recurrence in eight cases, while loose ligation was suspected in five cases. The cause of recurrence could not be predicted in the remaining eight patients. Of the seven patients with CMIH, three had a mild depression around the internal inguinal ring at the first surgery. In the remaining four CMIH cases, no noteworthy findings were noted around the internal ring. More than half of the recurrences, in which skipping of the peritoneum and loose ligation were suspected, could have been prevented by secure ligation during the first surgery. Extending the indications of prophylactic surgery for shallow depressions may reduce CMIH.

Real-World Video Denoising for Visual Inspection in High-Dose Radiological Environments

In high-dose radiological environments, where precision and safety are of utmost importance, the ability to acquire accurate and clear visual information is of paramount importance for ensuring safety and reliability in critical industrial processes. However, these environments inherently introduce significant challenges due to the adverse effects of radiation on imaging equipment. As a consequence, inspection videos captured within such high-radiation environments often contain a significant amount of noise. This noise substantially complicates the task of identifying and assessing potential defects in vital components. It also diverts attention and resources toward investigating false positives created by noise, leading to inefficiencies, and for industrial processes on the critical path, this can further prolong the outage. Addressing this noise is essential not only for precision, but also for ensuring safety, reliability, and efficiency in critical industrial processes. In this paper, we present a custom-designed filter utilizing a priori information about camera position and trajectory to remove the noise from the inspection videos, making the defects easier to manually identify. As the camera movement is in one direction at a constant speed, the proposed approach uses this temporal and spatial information to accurately remove the noise. This approach applies to a subset of visual inspection problems throughout the nuclear industry, as well as many other industries where there is knowledge available about the camera speed and direction of travel. The proposed approach is compared with three accepted/well-known approaches, median filtering, bilateral filtering, and fast nonlocal means denoising, and an additional state-of-the-art deep learning model is also used for comparison. It was found that the proposed approach produces the most accurate video denoising in terms of visual quality and the retainment of the defect features throughout the videos tested.

Enhanced Video-Level Anomaly Feature Detection for Nuclear Power Plant Component Inspections Using the Latency Mechanism

The conditions of various nuclear power plant facilities are regularly examined through manual inspections. Remote visual inspection is commonly applied and requires engineers to watch lengthy inspection footage and seek anomaly features therein. This is a labor-intensive process as anomaly features of interest usually only appear in very short segments of the original whole video. Therefore, an automated anomaly detection system is preferred to lessen the intensive labor cost in the inspection process. The detection process could also benefit from useful information that could potentially contribute to addressing reasoning traceability. With a well-prepared training data set of the anomaly feature, a convolutional neural network (CNN) can be developed to automatically detect anomaly indications in the inspection video. However, false-positive detections may occur and can be difficult to remove without seeking manual verification. To overcome this problem, we present a new automated video-level anomaly detection framework that utilizes the latency mechanism to effectively lessen false-positive occurrences, and therefore, increase detection accuracy. In this framework, a CNN-based anomaly classifier first performs initial scanning of the anomaly type of interest in every region of the sampled frames. Then our latency mechanism is applied to refine the initial scanning results by flagging up a region as an “anomaly” indication only when “anomaly” is detected by CNN in the current frame and also in a sequence of previous consecutive frames of the same region. We present a case study of crack feature detection in superheater inspection videos to illustrate the performance of the proposed framework. The results show that the latency mechanism can effectively remove the original false-positive detections seen in the initial scanning. In order to provide a primary exploration of suggesting possible formats for addressing reasoning traceability, knowledge graphs of the reasoning process in the video-level detection framework are built to provide a better understanding of why a specific section of the video is flagged as anomaly contents by the video-level detection framework.

Real-Time Object Detection from UAV Inspection Videos by Combining YOLOv5s and DeepStream.

The high-altitude real-time inspection of unmanned aerial vehicles (UAVs) has always been a very challenging task. Because high-altitude inspections are susceptible to interference from different weather conditions, interference from communication signals and a larger field of view result in a smaller object area to be identified. We adopted a method that combines a UAV system scheduling platform with artificial intelligence object detection to implement the UAV automatic inspection technology. We trained the YOLOv5s model on five different categories of vehicle data sets, in which mAP50 and mAP50-95 reached 93.2% and 71.7%, respectively. The YOLOv5s model size is only 13.76 MB, and the detection speed of a single inspection photo reaches 11.26 ms. It is a relatively lightweight model and is suitable for deployment on edge devices for real-time detection. In the original DeepStream framework, we set up the http communication protocol to start quickly to enable different users to call and use it at the same time. In addition, asynchronous sending of alarm frame interception function was added and the auxiliary services were set up to quickly resume video streaming after interruption. We deployed the trained YOLOv5s model on the improved DeepStream framework to implement automatic UAV inspection.

Automated Defect-Detection System for Water Pipelines Based on CCTV Inspection Videos of Autonomous Robotic Platforms

Automated Defect-Detection System for Water Pipelines Based on CCTV Inspection Videos of Autonomous Robotic Platforms

Segmentation and Tracking Based on Equalized Memory Matching Network and Its Application in Electric Substation Inspection

With the wide application of deep learning, power inspection technology has made great progress. However, substation inspection videos often present challenges such as complex backgrounds, uneven lighting distribution, variations in the appearance of power equipment targets, and occlusions, which increase the difficulty of object segmentation and tracking, thereby adversely affecting the accuracy and reliability of power equipment condition monitoring. In this paper, a pixel-level equalized memory matching network (PEMMN) for power intelligent inspection segmentation and tracking is proposed. Firstly, an equalized memory matching network is designed to collect historical information about the target using a memory bank, in which a pixel-level equalized matching method is used to ensure that the reference frame information can be transferred to the current frame reliably, guiding the segmentation tracker to focus on the most informative region in the current frame. Then, to prevent memory explosion and the accumulation of segmentation template errors, a mask quality evaluation module is introduced to obtain the confidence level of the current segmentation result so as to selectively store the frames with high segmentation quality to ensure the reliability of the memory update. Finally, the synthetic feature map generated by the PEMMN and the mask quality assessment strategy are unified into the segmentation tracking framework to achieve accurate segmentation and robust tracking. Experimental results show that the method performs excellently on real substation inspection scenarios and three generalized datasets and has high practical value.

The Influence of The Chinese Documentary A Bite of China Upon Short Videos of Food Scouts on Chinese Media Platform

In today's Internet fragmented information age, short video has become a popular information dissemination medium, and the short video industry also has a place in the category of new media. In short videos, the popularity of food shopping videos has been high. This paper mainly discusses the progress of short food shop video, and studies how it extracts inspiration from traditional documentary A Bite of China, emulates shooting methods, and integrates actual content with audience emotion. This can give people a better understanding of how short videos have improved by exploring the reasons for the popularity of food inspection videos. Through interviews with experienced food shop bloggers, this paper further explores the source of inspiration in the production of food videos and its impact on creators: Food documentaries, such as A Bite of China, help creators take many of the techniques of documentary and storytelling and apply them to their own video production, allowing creators to pay more attention to detail and personal style expression. The conclusion of this paper is that the blogger of food shop draws inspiration from A Bite of China, learns from the aspects of shooting more exquisite food scenes, video content and style, imitating the music, adding more science popularization, and integrating the audience's emotions, and has achieved great success in the short video of food shop.

Deep spatiotemporal fusion network for vision-based robotic inspection of structures

The convolutional neural networks commonly deployed for semantic understanding of visual inspection data can, in general, learn robust spatial features. However, they lack the ability to capture temporal dependencies that characterize the video data collected by various robotic inspection systems. As a result, they are found lacking in dealing with various challenges arising from cross-view illumination variation, perspective difference, scale change, background clutter, and occlusion. Their performance is further deteriorated by motion blur and other distortions induced by rapid camera movement. This study aims to address this challenge by extending the task of visual scene understanding from the still image domain to the video domain by incorporating cross-frame information fusion. A deep end-to-end network is developed by integrating an encoder–decoder-based convolutional neural network with a long short-term memory-based recurrent neural network for pixel-level semantic labeling of sequential visual inspection data. The proposed multishot architecture can jointly learn discriminative fusion features leading to a rich understanding of the complex spatiotemporal dynamics. The proposed approach is validated with two case studies involving automatic structural element segmentation in robotic building and bridge inspection videos. Two different multishot fusion techniques are suggested leveraging sequence-to-one and sequence-to-sequence architectures. Additionally, two different fusion schemes based on the sum-of-scores and Bayesian updating rules are examined to aggregate multiple label maps produced at each time step by an overlapping sliding window-based inference scheme. A comprehensive performance evaluation indicated that multishot fusion could enhance the intersection over union (IoU) score by 4.6% and 13.3% for building and bridge component segmentation tasks, respectively, compared to a baseline single-shot approach.

In-situ Artefact Documentation of Underwater Cultural Heritage Using Third-Party Data

Abstract Large underwater construction projects generate hundreds of potential cultural heritage objects requiring archaeological assessment and – potentially – mitigation. Some can easily be avoided in planning, whereas others cannot. Singular objects tend to present a dilemma in heritage management: their archaeological significance tends to lie in their association to an – at the time of finding – unknown context rather than in the object itself. Though these objects may be protected by heritage legislation, they are often undesired in museum collections, and even if destined for disposal, they can only be salvaged and documented at significant cost. Their cultural heritage ‘value’ is often, though mostly tacitly, considered low or at least undecided. We argue that in-situ preservation by record can be a viable solution for such objects, provided that appropriate documentation methods are employed. Fortunately, these objects are often targeted by other types of pre-construction surveys and inspections, usually conducted using remotely operated vehicles (ROVs), making hours of third-party video footage available to the archaeologist. This article examines if existing third-party video inspection data can be used towards acceptable archaeological recording without compromising the cost-efficiency so crucial to the industry. Hence, the focus of this article is the typical industry-standard inspection-, work class-, or even low-end hobby-ROV (from where the jump to legacy data or, indeed, crowdsourcing is obvious), suggesting a few simple amendments to data acquisition specifications which may potentially save the cost of a dedicated archaeological inspection campaign.

Uranium anomaly in groundwater of the hard rock aquifer system in southeast Brazil

This study presents a hydrogeological characterization that fills knowledge gaps in an area where a complex geological scenario connects two fractured (granite/metamorphic rocks and diabase) and one porous (sedimentary rocks) aquifer systems. Previous groundwater studies from the four local deep supply wells suggested the sedimentary aquifer as the source of uranium (∼60 μg/L) in one of the wells. Despite the water extraction interruption from this well, this finding needed to be supported by evidence provided by the geological and structural characteristics of the aquifers. Data collected through video inspection, caliper, optical (OPTV), and acoustic borehole televiewers (ATV) revealed the predominance of the crystalline aquifer in the area. As recorded by video inspection, the well's borehole with high U intersects the crystalline rocks at several open fractures and presents the highest gamma radiation values. Therefore, we infer that the origin of dissolved U is the weathering of primary minerals locally occurring in those rocks. The U leaching and complexation as calcium-uranyl-carbonates favors its solubility in that specific aqueous medium, as shown by hydrogeochemical modeling using PHREEQC. Additionally, the major ions and trace elements concentrations allow the division of the wells into two groups: a) two with higher U concentrations, influenced by the granite/metamorphic aquifer and possibly longer residence times, and b) the other two wells with lower U concentrations, higher nitrate concentrations, influenced by the diabase aquifer, possibly have younger residence times.

Three-Dimensional Multi-UAV Trajectory Design for Cooperative Video Inspection and Uploading

This paper studies the multiple unmanned aerial vehicles (UAVs) trajectory design for post-disaster cooperative video inspection and information uploading. The locations to be inspected are modeled as points of interest (PoIs) with heterogeneous resolution requirements. The three-dimensional (3D) trajectories for multiple cooperative UAVs are designed to minimize the time for successfully inspecting all the PoIs and maximize the communication time for the video uploading. An UAV inspection model is built to clarify the criteria for successful inspection, which is related to the UAV's 3D positions and velocity. The proposed UAV trajectory design involves two steps. First, the PoIs in proximity are grouped using convex optimization. Then, the multiple UAV trajectories are jointly designed by solving a multiple traveling salesman problem (MTSP). Numerical results show that the proposed design can significantly reduce the mission completion time.

PKAMNet: A Transmission Line Insulator Parallel- Gap Fault Detection Network Based on Prior Knowledge Transfer and Attention Mechanism

Insulator parallel gaps in a transmission line protect the insulator from arc burn and provide protection from lightning. Detection of insulator parallel-gap faults based on aerial inspection images of transmission lines may be hindered by various factors, such as complex background, scale distortion, and occlusion. In this study, we propose a prior knowledge transfer and attention mechanism network (PKAMNet) to detect faulty insulator parallel gaps. First, the capability of PKAMNet to learn the features of different types of parallel-gap faults is improved by constructing a prior knowledge transfer model based on visual saliency. Owing to the difficulty of effectively expressing the features of the fault target due to the deviation of the shooting angle and complex background of the inspection image, we enhance the feature expression ability of the fault area by embedding the coordinate attention block. Additionally, the parameters of the detection network are simplified, and the modules are optimized to improve detection efficiency. Comparison results on 3-year aerial inspection videos of 500 kV high-voltage transmission lines show that PKAMNet has a high detection accuracy and can ameliorate the phenomenon of missed and erroneous detection caused by insufficient expression of parallel-gap faults.

Wastewater pipe defect rating model for pipe maintenance using natural language processing

IntroductionClosed-circuit video (CCTV) inspection has been the most popular technique for visually evaluating the interior status of pipelines in recent decades. Certified inspectors prepare the pipe repair document based on the CCTV inspection. The traditional manual method of assessing structural wastewater conditions from pipe repair documents takes a long time and is prone to human mistakes. The automatic identification of necessary texts has received little attention. Computer Vision based Machine Learning models failed to estimate structural damage because they are not entirely understood and have difficulty providing high data needs. Hence, they have problems providing physically consistent findings due to their high data needs. Currently, a very small curated annotated image and video data set with well-defined, precisely labeled categories to test Computer Vision based Machine Learning models.MethodsThis study provides a valuable method to determine the pipe defect rating of the pipe repair documents by developing an automated framework using Natural Language Processing (NLP) on very small, curated annotated images, video data, and more text data. The text used in this study is broken into grammatical units using NLP technologies. The next step in the analysis entails using words to find the frequency of pipe defects and then classify them into respective defect ratings for pipe maintenance.Results and discussionsThe proposed model achieved 95.0% accuracy, 94.9% recall, 95% specificity, 95.9% precision score, and 95.7% F1 score, showing the potential of the proposed model to be used in large-scale pipe repair documents for accurate and efficient pipeline failure detection to improve the quality of the pipeline.

Early stage damage detection of wind turbine blades based on UAV images and deep learning

In response to the shortcomings of existing image detection algorithms in the early damage detection of wind turbine blades, such as insufficient applicability and unsatisfactory detection results, this paper proposes an improved DINO (DETR with improved denoizing anchor boxes for end-to-end object detection) model for wind turbine blade damage detection called WTB-DINO. The improvement strategy of the DINO model is obtained by collecting and analyzing unmanned aerial vehicle (UAV) daily inspection image data in wind farms. First, the lightweight design of DINO's feature extraction backbone is implemented to meet the requirement of fast and effective video inspection by drones. Based on this, the Focus down-sampling and enhanced channel attention mechanism are incorporated into the model to enhance the feature extraction ability of the Backbone for damaged areas according to the characteristics of wind turbine blade images. Second, a parallel encoder structure is built, and a multi-head attention mechanism is used to model the relationship between samples for each type of damage with uneven distribution in the dataset to improve the feature modeling effect of the model for less-sample damage categories. Experimental results show that the WTB-DINO model achieves a detection precision and recall rate of up to 93.2% and 93.6% for wind turbine blade damage, respectively, while maintaining a high frame rate of 27 frames per second. Therefore, the proposed WTB-DINO model can accurately and in real-time classify and locate damaged areas in wind turbine blade images obtained by UAVs.

Integration of ROV and vision-based underwater inspection for Limnoperna fortunei in water conveyance structure

The invasion of Limnoperna fortunei (L. fortunei) has been identified as one major biofouling in the operation of hydraulic engineering, which not only corrodes the concrete structures but also reduces the pipe diameter and increases the surface roughness, leading to the decrease of water conveyance capacity and the increase of the project operation cost. To better cope with this problem, an automated underwater inspection analysis scheme for the biofouling of L. fortune is provided in this study, which innovatively integrates the underwater remote operating rover (ROV) and computer vision techniques to inspect and evaluate the invasion of L. fortunei in water conveyance structure. This scheme first presents an image enhancement approach based on the fusion strategy to improve the quality of images extracted from underwater robot inspection videos. Then, the L. fortunei is segmented by U-Net in the enhanced underwater images, and the definition of adherent area ratio quantitatively assesses the biofouling severity. At last, the underwater inspection analysis scheme is implemented in a typical aqueduct, and the automatic analysis results are compared with the field investigation during the emptying maintenance of the aqueduct. In this study, the dataset of real ROV inspection video sequences was first used to evaluate the effectiveness of the proposed method for inspecting L. fortunei invasions in realistic scenarios, and then for the comparison with state-of-the-art methods. The results show that the proposed automated inspection scheme is capable of efficiently improving the underwater imaging quality and accurately detecting the L. fortunei.

Hazard assessment framework for statistical analysis of cut slopes using track inspection videos and geospatial information

ABSTRACT Transportation corridors constructed using through- and side-cuts are susceptible to hazardous slope failures, potentially causing infrastructure damage, operational suspensions and loss of life. To monitor the stability of known geohazards at the local scale, geotechnical investigation of each slope is typically performed to calculate a factor of safety. In many corridors, however, this method is labour-intensive due to the quantity of geohazards and statistical methods are instead used to identify hazardous sections. This paper introduces a new slope failure hazard assessment technique, utilising susceptibility mapping of geospatial information and computer vision-based analysis of right-of-way videos recorded by railroad track inspection vehicles, applied to a section of railroad track near Harrisburg, Pennsylvania. Combining these results, an enhanced relative hazard assessment algorithm was formulated. Using the developed framework, geohazards of primary concern were determined which should be prioritised for future geotechnical investigation and remediation efforts.

Boosting Nitrate to Ammonia Electroconversion through Hydrogen Gas Evolution over Cu-foam@mesh Catalysts.

The hydrogen evolution reaction (HER) is often considered parasitic to numerous cathodic electro-transformations of high technological interest, including but not limited to metal plating (e.g., for semiconductor processing), the CO2 reduction reaction (CO2RR), the dinitrogen → ammonia conversion (N2RR), and the nitrate reduction reaction (NO3-RR). Herein, we introduce a porous Cu foam material electrodeposited onto a mesh support through the dynamic hydrogen bubble template method as an efficient catalyst for electrochemical nitrate → ammonia conversion. To take advantage of the intrinsically high surface area of this spongy foam material, effective mass transport of the nitrate reactants from the bulk electrolyte solution into its three-dimensional porous structure is critical. At high reaction rates, NO3-RR becomes, however, readily mass transport limited because of the slow nitrate diffusion into the three-dimensional porous catalyst. Herein, we demonstrate that the gas-evolving HER can mitigate the depletion of reactants inside the 3D foam catalyst through opening an additional convective nitrate mass transport pathway provided the NO3-RR becomes already mass transport limited prior to the HER onset. This pathway is achieved through the formation and release of hydrogen bubbles facilitating electrolyte replenishment inside the foam during water/nitrate co-electrolysis. This HER-mediated transport effect "boosts" the effective limiting current of nitrate reduction, as evidenced by potentiostatic electrolyses combined with an operando video inspection of the Cu-foam@mesh catalysts under operating NO3-RR conditions. Depending on the solution pH and the nitrate concentration, NO3-RR partial current densities beyond 1 A cm-2 were achieved.

Research on Arc Sag Measurement Methods for Transmission Lines Based on Deep Learning and Photogrammetry Technology

Arc sag is an important parameter in the design and operation and maintenance of transmission lines and is directly related to the safety and reliability of grid operation. The current arc sag measurement method is inefficient and costly, which makes it difficult to meet the engineering demand for fast inspection of transmission lines. In view of this, this paper proposes an automatic spacer bar segmentation algorithm, CM-Mask-RCNN, that combines the CAB attention mechanism and MHSA self-attention mechanism, which automatically extracts the spacer bars and calculates the center coordinates, and combines classical algorithms such as beam method leveling, spatial front rendezvous, and spatial curve fitting, based on UAV inspection video data, to realize arc sag measurement with a low cost and high efficiency. It is experimentally verified that the CM-Mask-RCNN algorithm proposed in this paper achieves an AP index of 73.40% on the self-built dataset, which is better than the Yolact++, U-net, and Mask-RCNN algorithms. In addition, it is also verified that the adopted approach of fusing CAB and MHSA attention mechanisms can effectively improve the segmentation performance of the model, and this combination improves the model performance more significantly compared with other attention mechanisms, with an AP improvement of 2.24%. The algorithm in this paper was used to perform arc sag measurement experiments on 10 different transmission lines, and the measurement errors are all within ±2.5%, with an average error of −0.11, which verifies the effectiveness of the arc sag measurement method proposed in this paper for transmission lines.

Design and Implementation of Three-Channel Drainage Pipeline Ground Penetrating Radar Device.

In order to solve the current problems that conventional video inspection can only detect, as an internal pipeline defect and drainage pipeline radar inspection device detects in a single direction and at radar frequency in water pipeline defect detection, a three-channel drainage pipeline ground penetrating radar (GPR) inspection device was designed and developed, the assembly and commissioning of the device prototype were completed, and an actual engineering test application was carried out. Focusing on the problem that the detection direction and depth of the single-channel detection device are limited, a three-channel drainage pipeline GPR inspection device is designed to realize the synchronous detection of the inside of the pipeline, the pipeline body, and the external environment of the pipeline, improving the detection depth and efficiency. According to the design scheme of the three-channel drainage pipeline GPR inspection device, the assembly of the device prototype was completed. The device contains three radar channels, the top of the main frequency of the antenna is 1.4 GHz, the two sides are 750 MHz, the video camera has a pixel count of 4 million, and the positioning accuracy is less than 1 mm, the waterproof grade is IP68, the detection accuracy of pipe deformation (slope) is 0.1°, the detection depth outside the pipe is 1.2 m, and the detection accuracy of corrosion thickness is 15 mm. In a practical application of the device, the Jianguomenqiao sewage pipeline in Beijing, China, was tested, resulting in the discovery of 87 defects, including 39 loose soil areas at the bottom of the pipe exterior, 40 void areas, and 8 cavities.

Covid-19 pandemic induced measures in food industry improves food safety as perceived by food business operators in Finland

ABSTRACT This study examines the response of food business operators (FBOs) to the COVID-19 pandemic in relation to food safety and FBOs’ experiences of remote inspections performed by official food control. The study was conducted between November and December 2020 with a web-based questionnaire for food processing businesses in Finland. Most of the 60 responded FBOs had made changes to many own-check sectors such as working hygiene (83.4%) and preparedness for special situations (78.0%). Of the FBOs, 47.1–83.0% assessed that the changes in the own-check sectors had a positive impact on food safety and 43.2–100.0% believed that some of the changes would remain after the pandemic. Of the FBOs, 69.8% found on-site inspections at least partially replaceable with video inspection of the production areas. This study shows that, although the pandemic seriously interfered with food production, it also induced FBOs to take measures that promote food safety.