检索结果-内蒙古大学图书馆

作者： Schöne, Sandra Pol, Nirmal Kahrs, Lueder A. Medical Computer Vision and Robotics Lab University of Toronto Toronto Canada University of Stuttgart Stuttgart Germany Medical Computer Vision and Robotics Lab Institute of Biomedical Engineering University of Toronto Toronto Canada Department of Mathematical and Computational Sciences University of Toronto Mississauga Mississauga Canada

To automate surgical (sub-)tasks in robotic surgery, the knowledge of the exact pose of the instrument is mandatory. The application of Optical Coherence Tomography (OCT) to the problem of pose measurement appears promising due to its advantages of 3D imaging and micron-scale resolution. To investigate this, 175 image sequences of the EndoWrist Round Tip Scissor Tool were acquired with an OCT system. The images differ in the opening angles of the scissor blades and the rotation angles of the entire instrument about its central axis. These image sequences were further processed through computer vision methods of the individual images followed by point cloud generation. For pose estimation, an Iterative Closest Point algorithm was implemented to register the acquired point clouds to reference point clouds created from the instrument CAD file. The implemented algorithm was able to determine the opening angle with an overall error of 2 ± 1.3 and the rotation angle with a standard deviation between several runs of 0.6 ±2.8. However, the overall processing time of (39 ± 17)s on a standard PC leaves room for further investigations. © 2024 by Walter de Gruyter Berlin/Boston.

关键词： Optical coherence tomography

来源：评论

学校读者我要写书评

暂无评论

Lung and Colon Cancer Classification of Histopathology Images Using Convolutional Neural Network

引用

SN computer Science 2024年第2期5卷 223页

作者： Singh, Onkar Kashyap, Kanchan Lata Singh, Koushlendra Kumar Machine Vision and Intelligence Lab Department of Computer Science and Engineering National Institute of Technology Jamshedpur Jharkhand India Computing Science Engineering Indian Institute of Information Technology Kottayam Kerala India

The greatest significant contributor to cancer-related morbidity and mortality worldwide is malignant lung tumors. Lung cancer frequency has been seen to be on the rise recently. Lung cancer histopathology diagnosis is a crucial part of the patient’s treatment. The current study aims to demonstrate the efficiency of convolutional neural networks for the identification of squamous cell carcinoma and adenocarcinoma of the lung and colon by investigating the diagnosis of histopathology images. Five state-of-the-art pre-trained (ImageNet) convolutional neural network architectures, VGG-19, InceptionResNetV2, DenseNet201, EfficientNetB6, and MobileNetV2, are employed in this investigation to tri-categorize lung cancer images (normal, adenocarcinoma, and squamous cell carcinoma), together with colon cancer images (normal and adenocarcinoma). Regularization strategies have been applied to fine-tune the learning rate for improving accuracy. The LC25000 dataset has been used to validate the proposed method. EfficientNetB6, VGG19, InceptionResNetV2, DenseNet201, and MobileNetV2 accuracy on test data is reported to be 93.12, 98.00, 97.92, 99.12, and 99.32 percent respectively. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： DenseNet201 EfficientNetB6 Histopathology images InceptionResNetV2 Lung cancer MobileNetV2 VGG19

来源：评论

学校读者我要写书评

暂无评论

Specificity-preserving RGB-D saliency detection

引用

Computational Visual Media 2023年第2期9卷 297-317页

作者： Tao Zhou Deng-Ping Fan Geng Chen Yi Zhou Huazhu Fu School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Key Laboratory of System Control and Information Processing Ministry of EducationShanghaiChina Computer Vision Lab ETH Z¨urichZ¨urichSwitzerland School of Computer Science and Engineering Northwestern Polytechnical UniversityXi’anChina School of Computer Science and Engineering Southeast UniversityNanjingChina Inception Institute of Artificial Intelligence Abu DhabiUnited Arab Emirates

Salient object detection(SOD)in RGB and depth images has attracted increasing research *** RGB-D SOD models usually adopt fusion strategies to learn a shared representation from RGB and depth modalities,while few methods explicitly consider how to preserve modality-specific *** this study,we propose a novel framework,the specificity-preserving network(SPNet),which improves SOD performance by exploring both the shared information and modality-specific ***,we use two modality-specific networks and a shared learning network to generate individual and shared saliency prediction *** effectively fuse cross-modal features in the shared learning network,we propose a cross-enhanced integration module(CIM)and propagate the fused feature to the next layer to integrate cross-level ***,to capture rich complementary multi-modal information to boost SOD performance,we use a multi-modal feature aggregation(MFA)module to integrate the modalityspecific features from each individual decoder into the shared *** using skip connections between encoder and decoder layers,hierarchical features can be fully *** experiments demonstrate that our SPNet outperforms cutting-edge approaches on six popular RGB-D SOD and three camouflaged object detection *** project is publicly available at https://***/taozh2017/SPNet.

关键词： salient object detection(SOD) RGB-D cross-enhanced integration module(CIM) multi-modal feature aggregation(MFA)

来源：评论

学校读者我要写书评

暂无评论

Class Activation Mapping and Uncertainty Estimation in Multi-Organ Segmentation

Class Activation Mapping and Uncertainty Estimation in Multi...

引用

Medical Imaging 2023: computer-Aided Diagnosis

作者： Sadique, M.S. Farzana, W. Temtam, A. Iftekharuddin, K.M. Vision Lab Department of Electrical and Computer Engineering Old Dominion University NorfolkVA23529 United States

ISBN: (纸本)9781510660359

Deep learning (DL)-based medical imaging and image segmentation algorithms achieve impressive performance on many benchmarks. Yet the efficacy of deep learning methods for future clinical applications may become questionable due to the lack of ability to reason with uncertainty and interpret probable areas of failures in prediction decisions. Therefore, it is desired that such a deep learning model for segmentation classification is able to reliably predict its confidence measure and map back to the original imaging cases to interpret the prediction decisions. In this work, uncertainty estimation for multiorgan segmentation task is evaluated to interpret the predictive modeling in DL solutions. We use the state-of-the-art nnU-Net to perform segmentation of 15 abdominal organs (spleen, right kidney, left kidney, gallbladder, esophagus, liver, stomach, aorta, inferior vena cava, pancreas, right adrenal gland, left adrenal gland, duodenum, bladder, prostate/uterus) using 200 patient cases for the Multimodality Abdominal Multi-Organ Segmentation Challenge 2022. Further, the softmax probabilities from different variants of nnU-Net are used to compute the knowledge uncertainty in the deep learning framework. Knowledge uncertainty from ensemble of DL models is utilized to quantify and visualize class activation map for two example segmented organs. The preliminary result of our model shows that class activation maps may be used to interpret the prediction decision made by the DL model used in this study. © 2023 SPIE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

computer-Aided Leaf Disease Classification Based on Logistic Regression and Transfer Learning Approach

Computer-Aided Leaf Disease Classification Based on Logistic...

引用

International Conference on Machine vision and Augmented Intelligence, MAI 2022

作者： Saikia, Trishna Hansdah, Malho Singh, Koushlendra Kumar Machine Vision and Intelligence Lab Department of Computer Science and Engineering National Institute of Technology Jamshedpur Jamshedpur India

ISBN: (纸本)9789819901883

Over 60% of the total Indian population depends on agriculture. It is one of the key fields of Indian Economy which comes up with 17%–18% of total GDP. Therefore, it is very important to detect and classify plant leaf diseases properly in agricultural field. Sometimes, it is difficult to detect and identify the disease correctly by naked eye. So, a computer-aided system is very much necessary to identify the disease accurately. Moreover, it is also helpful in large farms of crops as it reduces great work of monitoring each plant individually. In this research study, we have implemented three different techniques, among those one is Logistic Regression (LR) and another two techniques are the combination of transfer learning method with Support Vector Machine (SVM). For all the techniques, we have used Adam optimizer. For our experiment, we have utilized a subset of PlantVillage datasets. We have compared all the methods and listed in a table. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Adaptive Critic Network for Person Tracking using 3D Skeleton Data 34

Adaptive Critic Network for Person Tracking using 3D Skeleto...

引用

Pattern Recognition and Tracking XXXIV 2023

作者： Zalameda, Joseph G. Glandon, Alex Iftekharuddin, Khan M. Vision Lab in Department of Electrical and Computer Engineering Old Dominion University NorfolkVA23529 United States

ISBN: (数字)9781510661691

ISBN: (纸本)9781510661684

Analysis of human gait using 3-dimensional co-occurrence skeleton joints extracted from Lidar sensor data has been shown a viable method for predicting person identity. The co-occurrence based networks rely on the spatial changes between frames of each joint in the skeleton data sequence. Normally, this data is obtained using a Lidar skeleton extraction method to estimate these co-occurrence features from raw Lidar frames, which can be prone to incorrect joint estimations when part of the body is occluded. These datasets can also be time consuming and expensive to collect and typically offer a small number of samples for training and testing network models. The small number of samples and occlusion can cause challenges when training deep neural networks to perform real time tracking of the person in the scene. We propose preliminary results with a deep reinforcement learning actor critic network for person tracking of 3D skeleton data using a small dataset. The proposed approach can achieve an average tracking rate of 68.92±15.90% given limited examples to train the network. © 2023 SPIE.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Low-Cost Real-World Benchmark Framework for Closed-Loop Robot Navigation Systems with SLAM

Low-Cost Real-World Benchmark Framework for Closed-Loop Robo...

引用

2024 IEEE Opportunity Research Scholars Symposium, ORSS 2024

作者： Cort, Carlton Dalal, Aditya De Ocampo, James Du, Yanwei Feng, Shiyu Vela, Patricio A. Intelligent Vision and Automation Lab Georgia Tech Institute for Robots and Intelligent Machines Georgia Tech School of Electrical and Computer Engineering United States

ISBN: (纸本)9798350390698

Simultaneous localization and mapping (SLAM) and navigation systems are pivotal to realizing autonomous robotic capabilities. Research toward these systems will have direct impacts on the already large and rapidly growing market of autonomous robotics. Typically, research efforts in SLAM and navigation isolate one of the two systems when benchmarking their performance. As such, potential confounding issues from integrating the full navigation stack with pose estimates from a SLAM algorithm, such as the compounded latency of both systems, never arise. This paper aims to remove this shortcoming by providing a cost-effective closed-loop benchmarking framework for several navigation stacks integrated with several SLAM algorithms on a physical platform (Turtlebot2 in an office environment). A frugal vision-based motion capture method is utilized to capture the localization data. The lessened cost of such a system removes the barriers to real-world testing of this type often presented by common expensive motion capture systems. In the benchmarking framework, conventional performance metrics for both SLAM and navigation research and novel metrics were collected to characterize the closed-loop performance. An analysis of these metrics will enable the selection of algorithms for real-world applications since the framework tests complete mobile autonomy stacks in a task-driven closed-loop environment. © 2024 IEEE.

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

2D Ear Recognition Using Data Augmentation and Deep CNN

2D Ear Recognition Using Data Augmentation and Deep CNN

引用

International Conference on Machine vision and Augmented Intelligence, MAI 2022

作者： Mehta, Ravishankar Singh, Koushlendra Kumar Machine Vision and Intelligence Lab Department of Computer Science and Engineering National Institute of Technology Jamshedpur Jharkhand Jamshedpur India

ISBN: (纸本)9789819901883

Ear recognition is one of the challenging tasks in the era of computer vision. In this work, we have highlighted the role of augmentation technique on convolutional neural networks (CNNs) for the purpose of improving the recognition rate. Here, we developed a simple CNN-based model for feature extraction and classification task using ear image for person identification. Over the last few years, many researchers have worked on different techniques to improve the recognition accuracy for person identification using ear images. We evaluated our method on unconstrained and unconstrained dataset. For this purpose, we have used AWE and AMI ear datasets for the purpose of ear recognition. The results show that the application of augmentation technique improves the accuracy of the model. In contrast to other method without augmentation, training a model with augmentation of data increases the accuracy from 52 to 82%. Hence, we can conclude that the data augmentation can be applied for the recognition task using ear images when there is lack of sufficient data in the dataset. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Learn & drop: fast learning of cnns based on layer dropping

引用

Neural Computing and Applications 2024年第18期36卷 10839-10851页

作者： Cruciata, Giorgio Cruciata, Luca Lo Presti, Liliana van Gemert, Jan La Cascia, Marco Engineering Department University of Palermo V.le delle Scienze Ed. 6 Palermo90128 Italy Computer Vision Lab Delft University of Technology Van Mourik Broekmanweg 6 Delft2628 XE Netherlands

This paper proposes a new method to improve the training efficiency of deep convolutional neural networks. During training, the method evaluates scores to measure how much each layer’s parameters change and whether the layer will continue learning or not. Based on these scores, the network is scaled down such that the number of parameters to be learned is reduced, yielding a speed-up in training. Unlike state-of-the-art methods that try to compress the network to be used in the inference phase or to limit the number of operations performed in the back-propagation phase, the proposed method is novel in that it focuses on reducing the number of operations performed by the network in the forward propagation during training. The proposed training strategy has been validated on two widely used architecture families: VGG and ResNet. Experiments on MNIST, CIFAR-10 and Imagenette show that, with the proposed method, the training time of the models is more than halved without significantly impacting accuracy. The FLOPs reduction in the forward propagation during training ranges from 17.83% for VGG-11 to 83.74% for ResNet-152. As for the accuracy, the impact depends on the depth of the model and the decrease is between 0.26% and 2.38% for VGGs and between 0.4 and 3.2% for ResNets. These results demonstrate the effectiveness of the proposed technique in speeding up learning of CNNs. The technique will be especially useful in applications where fine-tuning or online training of convolutional models is required, for instance because data arrive sequentially. © The Author(s) 2024.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of 2D Ear Recognition for Constrained and Unconstrained Dataset Using Deep Learning Approach

A Comparative Analysis of 2D Ear Recognition for Constrained...

引用

International Conference on Machine vision and Augmented Intelligence, MAI 2022

ISBN: (纸本)9789819901883

In this paper, we have made a comparative analysis of ear recognition for constrained and unconstrained dataset. We have also analyzed the effect of image quality like illumination, occlusion, brightness, and pose variation in our work. We have addressed the problem of limited dataset for ear recognition task using deep learning-based approach. We aim at building a deep convolutional neural network model that does the task of classification for ear recognition task. Our model considers both constrained and unconstrained dataset of ear image for analysis purpose. In this paper, we have explored the benefits of deep learning and its different approached to enhance the performance ear based biometric systems where sample images are captured in constrained and unconstrained condition. This paper mainly focuses on creation of deep learning model and compared its performance on three different datasets (AWE, AMI, and IITD-II) of ear images by varying the network architecture. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：