2021 IEEE International Conference on Imaging Systems and Techniques (IST)最新文献

Anomalous Driving Detection for Traffic Surveillance Video Analysis 交通监控视频分析中的异常驾驶检测

2021 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2021-08-24 DOI: 10.1109/ist50367.2021.9651372

Hang Shi, Hadi Ghahremannezhad, Chengjun Liu

引用次数: 5

Deep Convolutional Neural Networks for Road Crack Detection: Qualitative and Quantitative Comparisons 深度卷积神经网络用于道路裂纹检测:定性和定量比较

2021 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2021-08-24 DOI: 10.1109/ist50367.2021.9651375

Jiahe Fan, M. J. Bocus, Li Wang, Rui Fan

{"title":"Deep Convolutional Neural Networks for Road Crack Detection: Qualitative and Quantitative Comparisons","authors":"Jiahe Fan, M. J. Bocus, Li Wang, Rui Fan","doi":"10.1109/ist50367.2021.9651375","DOIUrl":"https://doi.org/10.1109/ist50367.2021.9651375","url":null,"abstract":"Road crack detection is a crucial civil infrastructure inspection task. Road crack detection is generally performed by either certified inspectors or structural engineers. Nevertheless, this process is time-consuming and subjective. Deep convolutional neural networks (DCNNs) have demonstrated compelling results for image classification, but there are currently no comprehensive comparisons among them, in regard to road crack detection. Therefore, in this paper, we conduct extensive experiments to compare 30 state-of-the-art (SoTA) DCNNs for road crack detection: Each DCNN is trained on a training set; The best performing models are selected on the validation set; Their performance is further quantified on a test set with respect to six evaluation metrics: precision, recall, accuracy, F-score, area under receiver operating characteristic (AUROC), and runtime. The experimental results suggest that road crack detection is a relatively easy image classification task. All the SoTA DCNNs perform similarly. The DCNNs evaluated in this study also achieved very similar performance when only a small amount of training data is available. Furthermore, PNASNet achieved the best trade-off between speed and accuracy, and thus, it is more practical to be used for real-time and robust road crack detection. Moreover, it was found that the best DCNN models did not generalize well when tested on new unseen data sets consisting of images not specifically related to road cracks.","PeriodicalId":433402,"journal":{"name":"2021 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125910643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Effect of Data Noise on LSTM-FC Scattered-Field Processing for Microwave Imaging 数据噪声对微波成像LSTM-FC散射场处理的影响

2021 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2021-08-24 DOI: 10.1109/ist50367.2021.9651450

A. Fedeli, M. Pastorino, A. Randazzo

引用次数: 0

The Role of Machine Vision in Industry 4.0: an automotive manufacturing perspective 机器视觉在工业4.0中的作用:一个汽车制造的视角

2021 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2021-08-24 DOI: 10.1109/ist50367.2021.9651453

F. Konstantinidis, S. Mouroutsos, A. Gasteratos

{"title":"The Role of Machine Vision in Industry 4.0: an automotive manufacturing perspective","authors":"F. Konstantinidis, S. Mouroutsos, A. Gasteratos","doi":"10.1109/ist50367.2021.9651453","DOIUrl":"https://doi.org/10.1109/ist50367.2021.9651453","url":null,"abstract":"The challenging market of automotive industry urges the manufacturers worldwide to benefit from the incredible technological advancements of the fourth industrial revolution (Industry 4.0), which is in progress. This revolutionary era flourishes the sensing, processing and integration technologies across the systems, while the machine vision serves as the “eyes” of the cyber-physical systems. This paper systematically provides a comprehensive analysis of the applied machine vision systems in the automotive industry over the last five years and anticipates the technology opportunities and future trends. The conducted analysis reveals that the machine vision technology is mainly employed for quality related purposes. Besides, fruitful advancements have occurred in the other automotive manufacturing domains, yet the horizontal and vertical integration is not a priority in their design. The authors conclude that computer vision systems empowered with self-adjustment capacities should be integrated with existing execution systems to rectify defects in real-time, thus promoting the intelligent system design towards enabling the zero defect manufacturing in human and system level.","PeriodicalId":433402,"journal":{"name":"2021 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129921331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 13

Monocularly Generated 3D High Level Semantic Model by Integrating Deep Learning Models and Traditional Vision Techniques 结合深度学习模型和传统视觉技术，单目生成三维高级语义模型

2021 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2021-08-24 DOI: 10.1109/ist50367.2021.9651471

Steven Alsheimer, Zhigang Zhu

引用次数: 0

Dual-Branch CNN for the Identification of Recyclable Materials 用于可回收材料识别的双支路CNN

2021 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2021-08-24 DOI: 10.1109/ist50367.2021.9651347

Anton Vogiatzis, G. Chalkiadakis, K. Moirogiorgou, G. Livanos, M. Papadogiorgaki, M. Zervakis

{"title":"Dual-Branch CNN for the Identification of Recyclable Materials","authors":"Anton Vogiatzis, G. Chalkiadakis, K. Moirogiorgou, G. Livanos, M. Papadogiorgaki, M. Zervakis","doi":"10.1109/ist50367.2021.9651347","DOIUrl":"https://doi.org/10.1109/ist50367.2021.9651347","url":null,"abstract":"The classification of recyclable materials, and in particular the recovery of plastic, plays an important role in the economy, but also in environmental sustainability. This study presents a novel image classification model that can be efficiently used to distinguish recyclable materials. Building on recent work in deep learning and waste classification, we introduce the so-called “Dual-branch Multi-output CNN”, a custom convolutional neural network composed of two branches aimed to i) classify recyclables and ii) distinguish the type of plastic. The proposed architecture is composed of two classifiers trained on two different datasets, so as to encode complementary attributes of the recyclable materials. In our work, the Densenet121, ResNet50 and VGG16 architectures were used on the Trashnet dataset, along with data augmentation techniques, as well as on the WaDaBa dataset with physical variation techniques. In particular, our approach makes use of the joint utilization of the datasets, allowing the learning of disjoint label combinations. Our experiments confirm its effectiveness in the classification of waste material.","PeriodicalId":433402,"journal":{"name":"2021 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130201776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Extraction of Laryngeal Cancer Informative Frames from Narrow Band Endoscopic Videos 窄带内镜视频中喉癌信息帧的提取

2021 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2021-08-24 DOI: 10.1109/ist50367.2021.9651343

Noha A. Sobhi, S. Youssef, Marwa ElShenawy

{"title":"Extraction of Laryngeal Cancer Informative Frames from Narrow Band Endoscopic Videos","authors":"Noha A. Sobhi, S. Youssef, Marwa ElShenawy","doi":"10.1109/ist50367.2021.9651343","DOIUrl":"https://doi.org/10.1109/ist50367.2021.9651343","url":null,"abstract":"Laryngeal cancer is one of the most common types of throat cancer. One of the most powerful technologies is a Narrow-band imaging (NBI) endoscope, which helps in diagnosing the early stage of cancer and reducing the biopsy risks. However, reviewing an endoscopic video is a labor-intensive process, as it contains a large number of uninformative frames due to the illumination or reflection effect and the appearance of saliva. This paper aims at designing and implementing an enhanced automated model to select the informative Laryngoscope video frames to reduce the computational time of scanning all the frames. Also, the selection of the informative frame will help the specialist in the diagnosis process. The proposed model uses a set of quality assessment features including texture and color features. Texture features have been used to detect the sharpness of the image as it is an important measure of image clarity. Moreover, the color features will help in identifying the images with saliva or specular reflections. Then, the extracted features are fed to different classifiers such as Support Vector Machine (SVM) and different ensemble classifiers. The classifiers have been used to classify the video frame into one of four types (informative (I), blurred (B), saliva or specular reflections (S), and underexposed (U)). The experimental results show that the Random Forest (RF) classifier produced a very promising classification result, with an average classification recall equals to 95.8%. The proposed model obtained better classification recall by 2.2% compared to the existing state-of-the-art method.","PeriodicalId":433402,"journal":{"name":"2021 IEEE International Conference on Imaging Systems and Techniques (IST)","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133873674","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Single frontal projection 2D/3D switchable display based on integral imaging 基于积分成像的单正面投影2D/3D可切换显示

2021 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2021-08-24 DOI: 10.1109/ist50367.2021.9651439

Qiang Li, F. Zhong, Wei He, Huan Deng

引用次数: 0

GPU-accelerated Localization in Confined Spaces using Deep Geometric Features 基于深度几何特征的受限空间gpu加速定位

2021 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2021-08-24 DOI: 10.1109/ist50367.2021.9651425

R. Brogaard, Ole Ravn, Evangelos Boukas

引用次数: 1

Detection and Sizing of Surface Cracks in Metals Using UHF Probe 金属表面裂纹的超高频探测与定径

2021 IEEE International Conference on Imaging Systems and Techniques (IST) Pub Date : 2021-08-24 DOI: 10.1109/ist50367.2021.9651442

Mohammed Saif ur Rahman, A. Mustapha, M. Abou-Khousa

引用次数: 4