Surface Inspection System for Cold Rolled Strips Based on Image ProcessingTechnique

A new surface inspection system for cold rolled strips based on image processing is introduced. The system is equipped withtwo different illumination structures and CCD matrix cameras. The structure and image processing of the inspection system are described. Some efficient algorithms for image processing and classification are presented. The system is tested with strip samples fromcold rolling plants. The results show that the system can detect and recognize six common defects of cold rolled strips successfully.

Automated deep learning system for power line inspection image analysis and processing: architecture and design issues

The continuous growth in the scale of unmanned aerial vehicle (UAV) applications in transmission line inspection has resulted in a corresponding increase in the demand for UAV inspection image processing. Owing to its excellent performance in computer vision, deep learning has been applied to UAV inspection image processing tasks such as power line identification and insulator defect detection. Despite their excellent performance, electric power UAV inspection image processing models based on deep learning face several problems such as a small application scope, the need for constant retraining and optimization, and high R&D monetary and time costs due to the black-box and scene data-driven characteristics of deep learning. In this study, an automated deep learning system for electric power UAV inspection image analysis and processing is proposed as a solution to the aforementioned problems. This system design is based on the three critical design principles of generalizability, extensibility, and automation. Pre-trained models, fine-tuning (downstream task adaptation), and automated machine learning, which are closely related to these design principles, are reviewed. In addition, an automated deep learning system architecture for electric power UAV inspection image analysis and processing is presented. A prototype system was constructed and experiments were conducted on the two electric power UAV inspection image analysis and processing tasks of insulator self-detonation and bird nest recognition. The models constructed using the prototype system achieved 91.36% and 86.13% mAP for insulator self-detonation and bird nest recognition, respectively. This demonstrates that the system design concept is reasonable and the system architecture feasible .

An FPGA-based real-time image processing system

This paper analyzes the current difficulties encountered in on-line inspection systems of strip surface quality, specifically relating to problems with real-time processing of huge amounts of data. To address this need, this paper describes an FPGA-based high-speed image processing module with both hardware and software aspects. Improving these two aspects together will help the system achieve real-time processing of massive image data, and simplifies the architecture of the strip surface quality on-line inspection system.

Damage detection with image processing: a comparative study

Large structures,such as bridges,highways,etc.,need to be inspected to evaluate their actual physical and functional condition,to predict future conditions,and to help decision makers allocating maintenance and rehabilitation resources.The assessment of civil infrastructure condition is carried out through information obtained by inspection and/or monitoring operations.Traditional techniques in structural health monitoring(SHM)involve visual inspection related to inspection standards that can be time-consuming data collection,expensive,labor intensive,and dangerous.To address these limitations,machine vision-based inspection procedures have increasingly been investigated within the research community.In this context,this paper proposes and compares four different computer vision procedures to identify damage by image processing:Otsu method thresholding,Markov random fields segmentation,RGB color detection technique,and K-means clustering algorithm.The first method is based on segmentation by thresholding that returns a binary image from a grayscale image.The Markov random fields technique uses a probabilistic approach to assign labels to model the spatial dependencies in image pixels.The RGB technique uses color detection to evaluate the defect extensions.Finally,K-means algorithm is based on Euclidean distance for clustering of the images.The benefits and limitations of each technique are discussed,and the challenges of using the techniques are highlighted.To show the effectiveness of the described techniques in damage detection of civil infrastructures,a case study is presented.Results show that various types of corrosion and cracks can be detected by image processing techniques making the proposed techniques a suitable tool for the prediction of the damage evolution in civil infrastructures.

A Systematic Review of Computer Vision Techniques for Quality Control in End-of-Line Visual Inspection of Antenna Parts

The rapid evolution of wireless communication technologies has underscored the critical role of antennas in ensuring seamless connectivity.Antenna defects,ranging from manufacturing imperfections to environmental wear,pose significant challenges to the reliability and performance of communication systems.This review paper navigates the landscape of antenna defect detection,emphasizing the need for a nuanced understanding of various defect types and the associated challenges in visual detection.This review paper serves as a valuable resource for researchers,engineers,and practitioners engaged in the design and maintenance of communication systems.The insights presented here pave the way for enhanced reliability in antenna systems through targeted defect detection measures.In this study,a comprehensive literature analysis on computer vision algorithms that are employed in end-of-line visual inspection of antenna parts is presented.The PRISMA principles will be followed throughout the review,and its goals are to provide a summary of recent research,identify relevant computer vision techniques,and evaluate how effective these techniques are in discovering defects during inspections.It contains articles from scholarly journals as well as papers presented at conferences up until June 2023.This research utilized search phrases that were relevant,and papers were chosen based on whether or not they met certain inclusion and exclusion criteria.In this study,several different computer vision approaches,such as feature extraction and defect classification,are broken down and analyzed.Additionally,their applicability and performance are discussed.The review highlights the significance of utilizing a wide variety of datasets and measurement criteria.The findings of this study add to the existing body of knowledge and point researchers in the direction of promising new areas of investigation,such as real-time inspection systems and multispectral imaging.This review,on its whole,offers a complete study of computer vision approaches for quality control in antenna parts.It does so by providing helpful insights and drawing attention to areas that require additional exploration.

DEVELOPMENT AND PRELIMINARY APPLICATION OF OBJECTIFYING SYSTEM FOR TCM COLOR INSPECTION

An objectifying system for color inspections of traditional Chinese medicine （CITCM） is developed. The entire system includes two parts ： The hardware and the software. The hardware is an image acquiring device under a standard lighting condition, and it mainly includes a xenon lamp with color temperature of 5 500 K as light source, an integrating sphere used for diffusing light and a high resolution CCD camera. The software is used for digital image processing, and the procedure is divided into three steps. Firstly the skin/non-skin classifi- cation is performed by utilizing the threshold in chrominance channels of the RGB color space. Secondly, the fa- cial features are localized by using the image segmentation and coordinates sorting. Finally, the facial special re- gion（SR） corresponding to five internal organs is achieved by utilizing masks designed to take advantage of mor- phology. Subsequently, the chromaticity is calculated. The system is tested by taking 83 samples of 30 young and 53 elderly people. The experiment shows that there is significant difference of all SRs between the young and the elderly, and the system has better performance for objectifying research of CITCM.

Realtime Vision-Based Surface Defect Inspection of Steel Balls

In the proposed system for online inspection of steel balls, a diffuse illumination is developed to enhance defect appearances and produce high quality images. To fully view the entire sphere, a novel unfolding method is put forward based on geometrical analysis, which only requires one-dimensional movement of the balls and a pair of cameras to capture images from different directions. Moreover, a realtime inspection algorithm is customized to improve both accuracy and efficiency. The precision and recall of the sample set were 87.7% and 98%, respectively. The average time cost on image processing and analysis for a steel ball was 47 ms, and the total time cost was less than 200 ms plus the cost of image acquisition and balls' movement. The system can sort 18 000 balls per hour with a spatial resolution higher than 0.01 mm.

Development of an automatic post-weld inspection system based on laser vision

In order to overcome the limitations of manual post-weld visual inspection approach, an automated inspection system is developed which uses three-dimensioual laser vision system based on the principle of optical triangulation. The system hardware consists of a modular development kit （MDK）, a computer, an actuating mechanism and so on. In image processing algorithms, extraction accuracy of centric line of laser stripe is the critical factor that determines the system performance. So according to the features of laser stripe image, a novel algorithm is developed to detect the central line of laser stripe fast and accurately. Experiments have demonstrated that this system can be used in various weld features inspection of both butt and fillet types of weld. Compared with traditional manual inspection method, this method has obvious dominance. The three-dimensional reconstruction result shows that this system has high accuracy and reliability.

Weld seam recognition algorithm based on HSI space for pipeline ultrasonic flaw inspection

In order to realize automatic weld seam tracking for pipeline ultrasonic flaw inspection, an image processing algorithm based on HSI color space was presented. Since the color tones of weld seam were different from the parent metal, weld seam images were transformed to HSI color space. In the HSl colar space, the weld seam and base metal area can be apparently distinguished. By using this image processing algorithm, the edges and centerline of pipeline weld seam can be correctly extracted. An industrial application system was developed based on the image processing algorithm, and the image processing time is less than 70 ms and the accuracy of weld seam recognition is better than 2mm.

Imagery Enhancement and Interpretation for Remote Visual Inspection of Aging Civil Infrastructure

In this paper, we describe an image enhancement and interpretation methodology to enhance and recognize surface defects and critical patterns from remote imagery of sewer pipeline inspection. The objective is to provide inspectors and professionals with better tools to allow them to examine the imagery for condition assessment. We present initial results of a collaboration with a robotic company through a case study on computer-assisted processing and interpretation of sewer pipeline inspection imagery. In the mean time, the described enhancement and interpretation methodology can also be applied to sewer pipeline condition assessment in an offline mode, where this methodology can support professionals’ examination of acquired sewer condition imagery.

Application of Digital Image Analysis Method in Metric Screw Thread Metrology

This paper describes the use of computer-aided measurement for external metric screw threads. Thread parameters, including thread pitch, thread angle, pitch diameter and major diameter, were measured with CCD cameras and image analysis software. New technologies such as digital image processing were used to increase the efficiency of measurements. In this study, by reconstructing the toolmaker’s microscope, the computer-aided semi-automated measuring system was developed, which could evaluate the accuracy of screw thread profile. It is concluded that the measurement accuracy is comparable to that of traditional toolmaker’s microscope method. Key words screw threads - quality inspection - accuracy - digital image processing

基于ImageJ图像处理技术检测家蚕一代杂交种的良卵数和良卵率

家蚕一代杂交种的良卵数、良卵率是蚕种品质检验的2项重要指标。为了提高检验效率,利用ImageJ图像处理软件建立检测家蚕一代杂交种良卵数、良卵率的新方法。分别利用这种图像处理方法和人工计数方法检测12个家蚕品种的蚕卵样本每克蚕卵的良卵数、总卵数,采用新方法检测获得的结果数据的相对误差均<1%。对2种方法获取的每克蚕卵良卵数、总卵数数据进行t测验,其t值均小于t0.05(22)=2.074,说明2种检测方法获取的检测结果差异不显著。相关性分析表明,利用2种检测方法对每克蚕卵良卵数、总卵数的检测结果的相关系数分别为0.9979、0.9982,2种检测方法获得的结果数据间呈极显著的线性相关。与人工计数检测方法相比,采用ImageJ图像处理技术的检测方法具有方便快捷的特点,可用于生产上家蚕一代杂交种的良卵数、良卵率检测。

Color ImageBased Defect Detection Method for Bridge Coating Assessment

This paper presents a highly efficient method for recognizing the existence of bridge coating rust defects by using color image processing. The detection of defects on steel bridge surfaces during the operation and maintenance of bridge structures is important to ensure the safety and reliability of them. More advanced techniques such as digital image processing have been studied for better monitoring and detection as existing infrastructure systems are aged and deteriorated rapidly. Recently, image-based defect recognition and assessment methods have gained considerable attention in the civil engineering domain due to their accuracy, speed, and lower cost. The proposed method in this paper is a fast decision-making system by utilizing color image processing. It was developed by processing original bridge coating images to generate color values and calculating eigenvalues from each digitized image. The values from two different groups, a defective group and a nondefective group, are compared each other to figure out the feasibility of this approach. Finally, an automated defect recognition method is presented and tested with more images. This method can be used to make a decision whether a given digitized image contains defects.

基于机器视觉的飞机故障检查系统

针对当前飞机维修检查工作以人工目视检查为主、效率低且存在人为因素影响的情况,设计一套基于图像识别与机器深度学习的飞机部件表面无损检测系统。收集并整理了某航空公司一线飞机维修员拍摄的飞机机身及发动机部件图片,对图片集进行预处理,包括通道提取、Sobel滤波处理及二值化;最后用Blob分析对处理后的图像进行特征提取与系统分析。系统运行速度快、准确率高且可连续自动识别图像。利用机器视觉技术对飞机部件表面进行无损检测不仅可以提高生产效率,同时可以去除人为因素对航空器飞行安全的影响,使得飞机的飞行安全得到进一步提升。实践证明,该系统性能稳定可靠,具有极高的推广应用价值。

钢筋混凝土结构移动式精准检测技术开发

无损检测技术是一种在不损害材料及结构服役性能的前提下,对其性质进行评估和测量的检测技术。然而,随着无损检测技术的发展和实践,结构内部的复杂损伤检测缺乏多层次精准性成为该领域的难点和核心问题。该文旨在结合国内外的研究成果,对无损检测技术的发展、分类和挑战进行梳理和分析,并在此基础上,介绍作者研究团队建立的一套由宏观到细观,再到内部的全面精准检测系统研究成果。针对表面宏观识别与细观定量识别,作者团队开发了表观病害视觉检测技术,包括构建的空间基准点自动追踪融合和亚像素级病害分割的全景图像快速拼接及表观病害厘米级定位方法,以及提出的全景图像中0.05 mm~0.2 mm多尺寸微细裂缝同步识别及真伪判别的人工智能算法。针对结构内部损伤识别,作者团队首创了智能变频敲击声波扫描及各类损伤精准识别新原理,发明建立了自适应激励分布移动敲击声波的损伤检测评估理论方法、声波及声纹图像特征人工智能算法及智能装备关键技术。经过实验验证,裂缝检测中宽度为0.05 mm时最大深度可达40 mm,剥离检测中最大深度可达400 mm,最小识别范围为50 mm。

基于图像视觉检测技术的激光标线仪校准装置研究

针对传统激光标线仪靶标测量方法难度大、人工读数困难且效率低的问题,基于图像视觉检测技术,设计了激光标线仪校准装置硬件系统及软件算法。通过数据采集单元、靶标系统单元和多功能升降工作台单元搭建出系统硬件装置。采用图像预处理方法将原始图像激光线与背景分割,提取出基准中心原点并进行系统标定,利用骨架提取算法拟合出激光测量线,计算出计量特性的偏移量,并根据算法设计出交互软件,自动测量和保存数据。最终通过所研制的校准装置和传统校准方法,校准同一激光标线仪进行比对实验,实验结果|E_(n)|≤1,结果判定为满意,验证了校准系统的可行性。

基于计算机视觉的锂电池连接片焊接检测系统

为了满足锂电池生产企业对锂电池连接片的焊接质量进行自动化检测的需求,设计了一种基于计算机视觉的锂电池连接片焊接质量检测系统.针对正、负电极材料的光学特性和检测精度要求,设计了两套光学系统分别实现锂电池正、负电极的成像,提出了多重自适应模板匹配算法提取正、负电极焊缝区域,采用自适应阈值分割法对焊缝区域实现灰度化操作,使用灰度形态学运算弱化灰度图的噪点突出焊盘特征点,利用轮廓提取算法实现焊盘特征点的提取,依据特征点数量实现极耳裁切缺陷的检测,将U^(2)-Net语义分割模型引入焊接质量检测任务,采集正、负电极焊缝和烧穿、虚焊、焊接氧化缺陷数据集,利用数据增强技术扩充数据集,解决焊接缺陷的小样本和小目标问题,融合应用U^(2)-Net语义分割模型和轮廓提取算法实现焊缝尺寸测量以及虚焊等缺陷的检测.系统试运行结果表明,缺陷检出率为99.98%,误检率仅为0.06%,满足企业的实际需求,实现了快速、无接触且准确的自动化检测.

变电站智能巡检机器人云台控制系统设计

在这个技术飞速发展的时代,智能电网技术的进步带来了变电站运维方式的革新。智能巡检机器人的出现彻底改变了变电站的巡检模式,让无人化巡检成为可能。智能巡检机器人在变电站巡检中的作用体系,需要依赖完善的空中管理系统,根据巡检需求设计系统是自动巡检实现的必然需求。基于此,本研究聚焦于这些机器人的心脏部分——云台控制系统的设计,详细介绍了云台控制系统的设计理念、实现方法以及所面临的挑战和解决方案。

一种基于图像的燃气轮机叶型参数测量方法

叶型参数的准确测量是实现叶片性能诊断和逆向建模的关键步骤。为了提高叶型参数的测量效率,提出了一种基于图像的参数提取方法。首先,采用骨架提取算法对叶片中弧线进行定位;然后,通过拟合计算获得中弧线函数及叶型厚度分布;最后,采用优化算法提高叶型参数辨识精度。实验结果表明,所提出的基于图像的叶型测量方法具有较高的准确性,测量相对误差小于1.5%,且应用方便、灵活,为叶片几何参数的快速、准确测量提供了新的解决方法。

面向电力无人机巡检图像分析处理的自动化深度学习系统:架构设计与关键技术

当前电力无人机巡检图像处理模型存在适用范围小、研发成本高、研发周期长等问题,文章提出一种面向无人机巡检图像分析处理的自动化深度学习系统,明确该系统设计的泛化性、可拓展性、自动化三要素,综述与三要素密切相关的技术进展,设计系统架构,构建原型系统。实验表明,在绝缘子自爆识别和鸟巢识别2项电力无人机巡检图像分析处理上,系统自动化构建的模型全类平均精度分别可达91.36%和86.13%,表明系统设计理念合理且系统架构可行。