Pub Date : 2023-11-06DOI: 10.22630/mgv.2023.32.2.2
Andrzej Paszkiewicz, Mateusz Salach, Dawid Wydrzyński, Joanna Woźniak, Grzegorz Budzik, Marek Bolanowski, Maria Ganzha, Marcin Paprzycki, Norbert Cierpicki
This work concerns automation of the training process, using modern information technologies, including virtual reality (VR). The starting point is an observation that automotive and aerospace industries require effective methods of preparation of engineering personnel. In this context, the technological process of preparing operations of a CNC numerical machine has been extracted. On this basis, a dedicated virtual reality environment, simulating manufacturing of a selected aircraft landing gear component, was created. For a comprehensive analysis of the pros and cons of the proposed approach, four forms of training, involving a physical CNC machine, a physical simulator, a software simulator, and the developed VR environment were instantiated. The features of each training form were analysed in terms of their potential for industrial applications. A survey, using the Net Promoter Score method, was also conducted among a target group of engineers, regarding the potential of use of each training form. As a result, the advantages and disadvantages of all four training forms were captured. They can be used as criteria for selecting the most effective training form.
{"title":"Use of virtual reality to facilitate engineer training in the aerospace industry","authors":"Andrzej Paszkiewicz, Mateusz Salach, Dawid Wydrzyński, Joanna Woźniak, Grzegorz Budzik, Marek Bolanowski, Maria Ganzha, Marcin Paprzycki, Norbert Cierpicki","doi":"10.22630/mgv.2023.32.2.2","DOIUrl":"https://doi.org/10.22630/mgv.2023.32.2.2","url":null,"abstract":"This work concerns automation of the training process, using modern information technologies, including virtual reality (VR). The starting point is an observation that automotive and aerospace industries require effective methods of preparation of engineering personnel. In this context, the technological process of preparing operations of a CNC numerical machine has been extracted. On this basis, a dedicated virtual reality environment, simulating manufacturing of a selected aircraft landing gear component, was created. For a comprehensive analysis of the pros and cons of the proposed approach, four forms of training, involving a physical CNC machine, a physical simulator, a software simulator, and the developed VR environment were instantiated. The features of each training form were analysed in terms of their potential for industrial applications. A survey, using the Net Promoter Score method, was also conducted among a target group of engineers, regarding the potential of use of each training form. As a result, the advantages and disadvantages of all four training forms were captured. They can be used as criteria for selecting the most effective training form.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"15 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135683976","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}
Pub Date : 2023-08-21DOI: 10.22630/mgv.2023.32.2.1
Ha X. Nguyen, Dong N. Hoang, Tuan A. Tran, Tuan M. Dang
In this work, an efficient pedestrian attribute recognition system is introduced. The system is based on a novel processing pipeline that combines the best-performing attribute extraction model with an efficient attribute filtering algorithm using keypoints of human pose. The attribute extraction models are developed based on several state-of-the-art deep networks via transfer learning techniques, including ResNet50, Swin-transformer, and ConvNeXt. Pre-trained models of these networks are fine-tuned using the Ensemble Pedestrian Attribute Recognition (EPAR) dataset. Several optimization techniques, including the advanced optimizer Adam with Decoupled Weight Decay Regularization (AdamW), Random Erasing (RE), and weighted loss functions, are adopted to solve issues of data unbalancing or challenging conditions like partial and occluded bodies. Experimental evaluations are performed via EPAR that contains 26993 images of 1477 person IDs, most of which are in challenging conditions. The results show that the ConvNeXt-v2-B outperforms other networks; mean accuracy (mA) reaches 85.57%, and other indices are also the highest. The addition of AdamW or RE can improve accuracy by 1-2%. The use of new loss functions can solve the issue of data unbalancing, in which the accuracy of data-less attributes improves by a maximum of 14% in the best case. Significantly, when the attribute filtering algorithm is applied, the results are dramatically improved, and mA reaches an excellent value of 94.85%. Utilizing the state-of-the-art attribute extraction model with optimization techniques on the large-scale and diverse dataset and attribute filtering has shown a good approach and thus has a high potential for practical applications.
{"title":"An efficient pedestrian attributes recognition system under challenging conditions","authors":"Ha X. Nguyen, Dong N. Hoang, Tuan A. Tran, Tuan M. Dang","doi":"10.22630/mgv.2023.32.2.1","DOIUrl":"https://doi.org/10.22630/mgv.2023.32.2.1","url":null,"abstract":"In this work, an efficient pedestrian attribute recognition system is introduced. The system is based on a novel processing pipeline that combines the best-performing attribute extraction model with an efficient attribute filtering algorithm using keypoints of human pose. The attribute extraction models are developed based on several state-of-the-art deep networks via transfer learning techniques, including ResNet50, Swin-transformer, and ConvNeXt. Pre-trained models of these networks are fine-tuned using the Ensemble Pedestrian Attribute Recognition (EPAR) dataset. Several optimization techniques, including the advanced optimizer Adam with Decoupled Weight Decay Regularization (AdamW), Random Erasing (RE), and weighted loss functions, are adopted to solve issues of data unbalancing or challenging conditions like partial and occluded bodies. Experimental evaluations are performed via EPAR that contains 26993 images of 1477 person IDs, most of which are in challenging conditions. The results show that the ConvNeXt-v2-B outperforms other networks; mean accuracy (mA) reaches 85.57%, and other indices are also the highest. The addition of AdamW or RE can improve accuracy by 1-2%. The use of new loss functions can solve the issue of data unbalancing, in which the accuracy of data-less attributes improves by a maximum of 14% in the best case. Significantly, when the attribute filtering algorithm is applied, the results are dramatically improved, and mA reaches an excellent value of 94.85%. Utilizing the state-of-the-art attribute extraction model with optimization techniques on the large-scale and diverse dataset and attribute filtering has shown a good approach and thus has a high potential for practical applications.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"11 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73840839","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}
Pub Date : 2023-08-14DOI: 10.22630/mgv.2023.32.1.6
Majid Khan, Ghassan Husnain, Waqas Ahmad, Zain Shaukat, Latif Jan, Ihtisham Ul Haq, Shahab Ul Islam, Atif Ishtiaq
Coronary Artery Disease is the type of cardiovascular disease (CVD) that happens when the blood vessels which stream the blood toward the heart, either become tapered or blocked. Of this, the heart is incapable to push sufficient blood to encounter its requirements. This would lead to angina (chest pain). CVDs are the leading cause of mortality worldwide. According to WHO, in the year 2019 17.9 million people deceased from CVD. Machine Learning is a type of artificial intelligence that uses algorithms to help analyse large datasets more efficiently. It can be used in medical research to help process large amounts of data quickly, such as patient records or medical images. By using Machine Learning techniques and methods, scientists can automate the analysis of complex and large datasets to gain deeper insights into the data. Machine Learning is a type of technology that helps with gathering data and understanding patterns. Recently, researchers in the healthcare industry have been using Machine Learning techniques to assist with diagnosing heart-related diseases. This means that the professionals involved in the diagnosis process can use Machine Learning to help them figure out what is wrong with a patient and provide appropriate treatment. This paper evaluates different machine learning models performances. The Supervised Learning algorithms are used commonly in Machine Learning which means that the training is done using labelled data, belonging to a particular classification. Such classification methods like Random Forest, Decision Tree, K-Nearest Neighbour, XGBoost algorithm, Naive Bayes, and Support Vector Machine will be used to assess the cardiovascular disease by Machine Learning.
{"title":"Performance evaluation of Machine Learning models to predict heart attack","authors":"Majid Khan, Ghassan Husnain, Waqas Ahmad, Zain Shaukat, Latif Jan, Ihtisham Ul Haq, Shahab Ul Islam, Atif Ishtiaq","doi":"10.22630/mgv.2023.32.1.6","DOIUrl":"https://doi.org/10.22630/mgv.2023.32.1.6","url":null,"abstract":"Coronary Artery Disease is the type of cardiovascular disease (CVD) that happens when the blood vessels which stream the blood toward the heart, either become tapered or blocked. Of this, the heart is incapable to push sufficient blood to encounter its requirements. This would lead to angina (chest pain). CVDs are the leading cause of mortality worldwide. According to WHO, in the year 2019 17.9 million people deceased from CVD. Machine Learning is a type of artificial intelligence that uses algorithms to help analyse large datasets more efficiently. It can be used in medical research to help process large amounts of data quickly, such as patient records or medical images. By using Machine Learning techniques and methods, scientists can automate the analysis of complex and large datasets to gain deeper insights into the data. Machine Learning is a type of technology that helps with gathering data and understanding patterns. Recently, researchers in the healthcare industry have been using Machine Learning techniques to assist with diagnosing heart-related diseases. This means that the professionals involved in the diagnosis process can use Machine Learning to help them figure out what is wrong with a patient and provide appropriate treatment. This paper evaluates different machine learning models performances. The Supervised Learning algorithms are used commonly in Machine Learning which means that the training is done using labelled data, belonging to a particular classification. Such classification methods like Random Forest, Decision Tree, K-Nearest Neighbour, XGBoost algorithm, Naive Bayes, and Support Vector Machine will be used to assess the cardiovascular disease by Machine Learning.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135263832","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}
Pub Date : 2023-08-10DOI: 10.22630/mgv.2023.32.1.5
J. D. Akinyemi, Akinkunle A. Akinola, Olajumoke O. Adekunle, T. Adetiloye, E. Dansu
Cancer is a deadly disease that has gained a reputation as a global health concern. Further, lung cancer has been widely reported as the most deadly cancer type globally, while colon cancer comes second. Meanwhile, early detection is one of the primary ways to prevent lung and colon cancer fatalities. To aid the early detection of lung and colon cancer, we propose a computer-aided diagnostic approach that employs a Deep Learning (DL) architecture to enhance the detection of these cancer types from Computed Tomography (CT) images of suspected body parts. Our experimental dataset (LC25000) contains 25000 CT images of benign and malignant lung and colon cancer tissues. We used weights from a pre-trained DL architecture for computer vision, EfficientNet, to build and train a lung and colon cancer detection model. EfficientNet is a Convolutional Neural Network architecture that scales all input dimensions such as depth, width, and resolution at the same time. Our research findings showed detection accuracies of 99.63%, 99.50%, and 99.72% for training, validation, and test sets, respectively.
{"title":"Lung and colon cancer detection from CT images using Deep Learning","authors":"J. D. Akinyemi, Akinkunle A. Akinola, Olajumoke O. Adekunle, T. Adetiloye, E. Dansu","doi":"10.22630/mgv.2023.32.1.5","DOIUrl":"https://doi.org/10.22630/mgv.2023.32.1.5","url":null,"abstract":"Cancer is a deadly disease that has gained a reputation as a global health concern. Further, lung cancer has been widely reported as the most deadly cancer type globally, while colon cancer comes second. Meanwhile, early detection is one of the primary ways to prevent lung and colon cancer fatalities. To aid the early detection of lung and colon cancer, we propose a computer-aided diagnostic approach that employs a Deep Learning (DL) architecture to enhance the detection of these cancer types from Computed Tomography (CT) images of suspected body parts. Our experimental dataset (LC25000) contains 25000 CT images of benign and malignant lung and colon cancer tissues. We used weights from a pre-trained DL architecture for computer vision, EfficientNet, to build and train a lung and colon cancer detection model. EfficientNet is a Convolutional Neural Network architecture that scales all input dimensions such as depth, width, and resolution at the same time. Our research findings showed detection accuracies of 99.63%, 99.50%, and 99.72% for training, validation, and test sets, respectively.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"54 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77626880","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}
Important information perceived by human vision comes from the low-level features of the image, which can be extracted by the Riesz transform. In this study, we propose a Riesz transform based approach to image fusion. The image to be fused is first decomposed using the Riesz transform. Then the image sequence obtained in the Riesz transform domain is subjected to the Laplacian wavelet transform based on the fractional Laplacian operators and the multi-harmonic splines. After Laplacian wavelet transform, the image representations have directional and multi-resolution characteristics. Finally, image fusion is performed, leveraging Riesz-Laplace wavelet analysis and the global coupling characteristics of pulse coupled neural network (PCNN). The proposed approach has been tested in several application scenarios, such as multi-focus imaging, medical imaging, remote sensing full-color imaging, and multi-spectral imaging. Compared with conventional methods, the proposed approach demonstrates superior performance on visual effects, contrast, clarity, and the overall efficiency.
{"title":"Riesz-Laplace Wavelet Transform and PCNN Based Image Fusion","authors":"Shuifa Sun, Yongheng Tang, Zhoujunshen Mei, Min Yang, Tinglong Tang, Yirong Wu","doi":"10.22630/mgv.2023.32.1.4","DOIUrl":"https://doi.org/10.22630/mgv.2023.32.1.4","url":null,"abstract":"Important information perceived by human vision comes from the low-level features of the image, which can be extracted by the Riesz transform. In this study, we propose a Riesz transform based approach to image fusion. The image to be fused is first decomposed using the Riesz transform. Then the image sequence obtained in the Riesz transform domain is subjected to the Laplacian wavelet transform based on the fractional Laplacian operators and the multi-harmonic splines. After Laplacian wavelet transform, the image representations have directional and multi-resolution characteristics. Finally, image fusion is performed, leveraging Riesz-Laplace wavelet analysis and the global coupling characteristics of pulse coupled neural network (PCNN). The proposed approach has been tested in several application scenarios, such as multi-focus imaging, medical imaging, remote sensing full-color imaging, and multi-spectral imaging. Compared with conventional methods, the proposed approach demonstrates superior performance on visual effects, contrast, clarity, and the overall efficiency.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"36 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81064817","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}
Pub Date : 2023-04-06DOI: 10.22630/mgv.2023.32.1.3
A. Mimi, Sayeda Fatema Tuj Zohura, Muhammad Ibrahim, Riddho Ridwanul Haque, Omar Farrok, T. Jabid, M. Ali
Leaf diseases may harm plants in different ways, often causing reduced productivity and, at times, lethal consequences. Detecting such diseases in a timely manner can help plant owners take effective remedial measures. Deficiencies of vital elements such as nitrogen, microbial infections and other similar disorders can often have visible effects, such as the yellowing of leaves in Catharanthus roseus (bright eyes) and scorched leaves in Fragaria × ananassa (strawberry) plants. In this work, we explore approaches to use computer vision techniques to help plant owners identify such leaf disorders in their plants automatically and conveniently. This research designs three machine learning systems, namely a vanilla CNN model, a CNN-SVM hybrid model, and a MobileNetV2-based transfer learning model that detect yellowed and scorched leaves in Catharanthus roseus and strawberry plants, respectively, using images captured by mobile phones. In our experiments, the models yield a very promising accuracy on a dataset having around 4000 images. Of the three models, the transfer learning-based one demonstrates the highest accuracy (97.35% on test set) in our experiments. Furthermore, an Android application is developed that uses this model to allow end-users to conveniently monitor the condition of their plants in real time.
{"title":"Identifying selected diseases of leaves using deep learning and transfer learning models","authors":"A. Mimi, Sayeda Fatema Tuj Zohura, Muhammad Ibrahim, Riddho Ridwanul Haque, Omar Farrok, T. Jabid, M. Ali","doi":"10.22630/mgv.2023.32.1.3","DOIUrl":"https://doi.org/10.22630/mgv.2023.32.1.3","url":null,"abstract":"Leaf diseases may harm plants in different ways, often causing reduced productivity and, at times, lethal consequences. Detecting such diseases in a timely manner can help plant owners take effective remedial measures. Deficiencies of vital elements such as nitrogen, microbial infections and other similar disorders can often have visible effects, such as the yellowing of leaves in Catharanthus roseus (bright eyes) and scorched leaves in Fragaria × ananassa (strawberry) plants. In this work, we explore approaches to use computer vision techniques to help plant owners identify such leaf disorders in their plants automatically and conveniently. This research designs three machine learning systems, namely a vanilla CNN model, a CNN-SVM hybrid model, and a MobileNetV2-based transfer learning model that detect yellowed and scorched leaves in Catharanthus roseus and strawberry plants, respectively, using images captured by mobile phones. In our experiments, the models yield a very promising accuracy on a dataset having around 4000 images. Of the three models, the transfer learning-based one demonstrates the highest accuracy (97.35% on test set) in our experiments. Furthermore, an Android application is developed that uses this model to allow end-users to conveniently monitor the condition of their plants in real time.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82060219","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}
Pub Date : 2023-03-07DOI: 10.22630/mgv.2023.32.1.2
S. Rao, Nitya Mitnala
Open, broken, and improperly closed manholes can pose problems for autonomous vehicles and thus need to be included in obstacle avoidance and lane-changing algorithms. In this work, we propose and compare multiple approaches for manhole localization and classification like classical computer vision, convolutional neural networks like YOLOv3 and YOLOv3-Tiny, and vision transformers like YOLOS and ViT. These are analyzed for speed, computational complexity, and accuracy in order to determine the model that can be used with autonomous vehicles. In addition, we propose a size detection pipeline using classical computer vision to determine the size of the hole in an improperly closed manhole with respect to the manhole itself. The evaluation of the data showed that convolutional neural networks are currently better for this task, but vision transformers seem promising.
{"title":"Exploring automated object detection methods for manholes using classical computer vision and deep learning","authors":"S. Rao, Nitya Mitnala","doi":"10.22630/mgv.2023.32.1.2","DOIUrl":"https://doi.org/10.22630/mgv.2023.32.1.2","url":null,"abstract":"Open, broken, and improperly closed manholes can pose problems for autonomous vehicles and thus need to be included in obstacle avoidance and lane-changing algorithms. In this work, we propose and compare multiple approaches for manhole localization and classification like classical computer vision, convolutional neural networks like YOLOv3 and YOLOv3-Tiny, and vision transformers like YOLOS and ViT. These are analyzed for speed, computational complexity, and accuracy in order to determine the model that can be used with autonomous vehicles. In addition, we propose a size detection pipeline using classical computer vision to determine the size of the hole in an improperly closed manhole with respect to the manhole itself. The evaluation of the data showed that convolutional neural networks are currently better for this task, but vision transformers seem promising.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"160 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86215153","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}
Pub Date : 2023-02-16DOI: 10.22630/mgv.2023.32.1.1
Yu Liang Liew, J. F. Chin
This study used stick model augmentation on single-camera motion video to create a markerless motion classification model of manual operations. All videos were augmented with a stick model composed of keypoints and lines by using the programming model, which later incorporated the COCO dataset, OpenCV and OpenPose modules to estimate the coordinates and body joints. The stick model data included the initial velocity, cumulative velocity, and acceleration for each body joint. The extracted motion vector data were normalized using three different techniques, and the resulting datasets were subjected to eight classifiers. The experiment involved four distinct motion sequences performed by eight participants. The random forest classifier performed the best in terms of accuracy in recorded data classification in its min-max normalized dataset. This classifier also obtained a score of 81.80% for the dataset before random subsampling and a score of 92.37% for the resampled dataset. Meanwhile, the random subsampling method dramatically improved classification accuracy by removing noise data and replacing them with replicated instances to balance the class. This research advances methodological and applied knowledge on the capture and classification of human motion using a single camera view.
{"title":"Vision-based biomechanical markerless motion classification","authors":"Yu Liang Liew, J. F. Chin","doi":"10.22630/mgv.2023.32.1.1","DOIUrl":"https://doi.org/10.22630/mgv.2023.32.1.1","url":null,"abstract":"This study used stick model augmentation on single-camera motion video to create a markerless motion classification model of manual operations. All videos were augmented with a stick model composed of keypoints and lines by using the programming model, which later incorporated the COCO dataset, OpenCV and OpenPose modules to estimate the coordinates and body joints. The stick model data included the initial velocity, cumulative velocity, and acceleration for each body joint. The extracted motion vector data were normalized using three different techniques, and the resulting datasets were subjected to eight classifiers. The experiment involved four distinct motion sequences performed by eight participants. The random forest classifier performed the best in terms of accuracy in recorded data classification in its min-max normalized dataset. This classifier also obtained a score of 81.80% for the dataset before random subsampling and a score of 92.37% for the resampled dataset. Meanwhile, the random subsampling method dramatically improved classification accuracy by removing noise data and replacing them with replicated instances to balance the class. This research advances methodological and applied knowledge on the capture and classification of human motion using a single camera view.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"56 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74916933","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}
Pub Date : 2022-12-19DOI: 10.22630/mgv.2022.31.1.5
R. Bohush, S. Ihnatsyeva, S. Ablameyko
The paper is aimed to improve person re-identification accuracy in distributed video surveillance systems based on constructing a large joint image dataset of people for training convolutional neural networks (CNN). For this aim, an analysis of existing datasets is provided. Then, a new large joint dataset for person re-identification task is constructed that includes the existing public datasets CUHK02, CUHK03, Market, Duke, MSMT17 and PolReID. Testing for re-identification is performed for such frequently cited CNNs as ResNet-50, DenseNet121 and PCB. Re-identification accuracy is evaluated by using the main metrics Rank, mAP and mINP. The use of the new large joint dataset makes it possible to improve Rank1 mAP, mINP on all test sets. Re-ranking is used to further increase the re-identification accuracy. Presented results confirm the effectiveness of the proposed approach.
{"title":"Person re-identification accuracy improvement by training a CNN with the new large joint dataset and re-rank","authors":"R. Bohush, S. Ihnatsyeva, S. Ablameyko","doi":"10.22630/mgv.2022.31.1.5","DOIUrl":"https://doi.org/10.22630/mgv.2022.31.1.5","url":null,"abstract":"The paper is aimed to improve person re-identification accuracy in distributed video surveillance systems based on constructing a large joint image dataset of people for training convolutional neural networks (CNN). For this aim, an analysis of existing datasets is provided. Then, a new large joint dataset for person re-identification task is constructed that includes the existing public datasets CUHK02, CUHK03, Market, Duke, MSMT17 and PolReID. Testing for re-identification is performed for such frequently cited CNNs as ResNet-50, DenseNet121 and PCB. Re-identification accuracy is evaluated by using the main metrics Rank, mAP and mINP. The use of the new large joint dataset makes it possible to improve Rank1 mAP, mINP on all test sets. Re-ranking is used to further increase the re-identification accuracy. Presented results confirm the effectiveness of the proposed approach.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76316851","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}
Pub Date : 2022-12-15DOI: 10.22630/mgv.2022.31.1.1
Tomasz Lehmann
Image demoiréing is a particular example of a picture restoration problem. Moiré is an interference pattern generated by overlaying similar but slightly offset templates.In this paper, we present a deep learning based algorithm to reduce moiré disruptions. The proposed solution contains an explanation of the cross-sampling procedure – the training dataset management method which was optimized according to limited computing resources.Suggested neural network architecture is based on Attention U-Net structure. It is an exceptionally effective model which was not proposed before in image demoiréing systems. The greatest improvement of this model in comparison to U-Net network is the implementation of attention gates. These additional computing operations make the algorithm more focused on target structures.We also examined three MSE and SSIM based loss functions. The SSIM index is used to predict the perceived quality of digital images and videos. A similar approach was applied in various computer vision areas.The author’s main contributions to the image demoiréing problem contain the use of the novel architecture for this task, innovative two-part loss function, and the untypical use of the cross-sampling training procedure.
{"title":"Attention-based U-Net for image demoiréing","authors":"Tomasz Lehmann","doi":"10.22630/mgv.2022.31.1.1","DOIUrl":"https://doi.org/10.22630/mgv.2022.31.1.1","url":null,"abstract":"Image demoiréing is a particular example of a picture restoration problem. Moiré is an interference pattern generated by overlaying similar but slightly offset templates.In this paper, we present a deep learning based algorithm to reduce moiré disruptions. The proposed solution contains an explanation of the cross-sampling procedure – the training dataset management method which was optimized according to limited computing resources.Suggested neural network architecture is based on Attention U-Net structure. It is an exceptionally effective model which was not proposed before in image demoiréing systems. The greatest improvement of this model in comparison to U-Net network is the implementation of attention gates. These additional computing operations make the algorithm more focused on target structures.We also examined three MSE and SSIM based loss functions. The SSIM index is used to predict the perceived quality of digital images and videos. A similar approach was applied in various computer vision areas.The author’s main contributions to the image demoiréing problem contain the use of the novel architecture for this task, innovative two-part loss function, and the untypical use of the cross-sampling training procedure.","PeriodicalId":39750,"journal":{"name":"Machine Graphics and Vision","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82486740","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：