检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Xu, Mingye Zhou, Zhipeng Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Siat Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

In spite of the recent progresses on classifying 3D point cloud with deep CNNs, large geometric transformations like rotation and translation remain challenging problem and harm the final classification performance. To address this challenge, we propose Geometry Sharing Network (GS-Net) which effectively learns point descriptors with holistic context to enhance the robustness to geometric transformations. Compared with previous 3D point CNNs which perform convolution on nearby points, GS-Net can aggregate point features in a more global way. Specially, GS-Net consists of Geometry Similarity Connection (GSC) modules which exploit Eigen-Graph to group distant points with similar and relevant geometric information, and aggregate features from nearest neighbors in both Euclidean space and Eigenvalue space. This design allows GS-Net to efficiently capture both local and holistic geometric features such as symmetry, curvature, convexity and connectivity. Theoretically, we show the nearest neighbors of each point in Eigenvalue space are invariant to rotation and translation. We conduct extensive experiments on public datasets, ModelNet40, ShapeNet Part. Experiments demonstrate that GS-Net achieves the state-of-the-art performances on major datasets, 93.3% on ModelNet40, and are more robust to geometric transformations. Code is released on https://***/MingyeXu/GS-Net. Copyright © 2019, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Robust road marking detection & recognition using density-based grouping & machine learning techniques 17

Robust road marking detection & recognition using density-ba...

引用

17th IEEE Winter Conference on Applications of computer vision, WACV 2017

作者： Bailo, Oleksandr Lee, Seokju Rameau, Francois Yoon, Jae Shin Kweon, In So KAIST Robotics and Computer Vision Laboratory United States

ISBN: (纸本)9781509048229

This paper presents a robust approach for road marking detection and recognition from images captured by an embedded camera mounted on a car. Our method is designed to cope with illumination changes, shadows, and harsh meteorological conditions. Furthermore, the algorithm can effectively group complex multi-symbol shapes into an individual road marking. For this purpose, the proposed technique relies on MSER features to obtain candidate regions which are further merged using density-based clustering. Finally, these regions of interest are recognized using machine learning approaches. Worth noting, the algorithm is versatile since it does not utilize any prior information about lane position or road space. The proposed method compares favorably to other existing works through a large number of experiments on an extensive road marking dataset. © 2017 IEEE.

关键词： Road and street markings

来源：评论

学校读者我要写书评

暂无评论

Gaussian curvature filter on 3d mesh

arXiv

引用

arXiv 2020年

作者： Tang, Wenming Gong, Yuanhao Liu, Kanglin Liu, Jun Pan, Wei Liu, Bozhi Qiu, Guoping College of Information Engineering Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Mechanical & Automotive Engineering South China University of Technology Department of Research and Development OPT Machine Vision Tech Co. Ltd Jinsheng Road Changan Dongguan Guangdong523860 China School of Computer Science University of Nottingham NottinghamNG8 1BB United Kingdom

Minimizing Gaussian curvature of meshes is fundamentally important for obtaining smooth and developable surfaces. However, there is a lack of computationally efficient and robust Gaussian curvature optimization method. In this paper, we present a simple yet effective method that can efficiently reduce Gaussian curvature for 3D meshes. We first present the mathematical foundation of our method, which states that for any point on a developable surface there must be another point that lives on its tangent plane. Then, based on this theoretical insight, we introduce a simple and robust implicit Gaussian curvature optimization method named Gaussian Curvature Filter (GCF). GCF implicitly minimizes Gaussian curvature without the need to explicitly calculate the Gaussian curvature itself. GCF is highly efficient and is 20 times faster than the classical standard Gaussian curvature flow method. We present extensive experiments to demonstrate that GCF significantly outperforms state-of-the-art methods in minimizing Gaussian curvature, geometric feature preserving smoothing and mesh noise removal. This method can be used in a large range of applications that involve Gaussian curvature. Copyright © 2020, The Authors. All rights reserved.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Fusion of metadata and dermoscopic images for melanoma detection: Deep learning and feature importance analysis

引用

Information Fusion 2025年 124卷

作者： Misbah Ahmad Imran Ahmed Abdellah Chehri Gwangill Jeon Centre for Machine Vision Bristol Robotics Laboratory University of West of England Frenchy Campus Bristol BS16 1QY Bristol UK Department of Animal and Agriculture Hartpury University Hartpury House Gloucester GL19 3BE Gloucestershire UK School of Computing and Information Science Anglia Ruskin University East Road Cambridge CB1 1PT Cambridgeshire UK Department of Mathematics and Computer Science Royal Military College of Canada (RMC) P.O. Box 17000 Station Forces Kingston K7K 7B4 Ontario Canada Department of Embedded Systems Engineering Incheon National University 119 Academy-ro Incheon 22012 Incheon Republic of Korea

In the era of smart healthcare, integrating multimodal data is essential for improving diagnostic accuracy and enabling personalized care. This study presented a deep learning-based multimodal approach for melanoma detection, leveraging both dermoscopic images and clinical metadata to enhance classification performance. The proposed model integrated a multi-layer convolutional neural network (CNN) to extract image features and combined them with structured metadata, including patient age, gender, and lesion location, through feature-level fusion. The fusion process occurred at the final CNN layer, where high-dimensional image feature vectors were concatenated with processed metadata. The metadata was handled separately through a fully connected neural network comprising multiple dense layers. The final fused representation was passed through additional dense layers, culminating in a classification layer that outputted the probability of melanoma presence. The model was trained end-to-end using the SIIM-ISIC dataset, allowing it to learn a joint representation of image and metadata features for optimal classification. Various data augmentation techniques were applied to dermoscopic images to mitigate class imbalance and improve model robustness. Additionally, exploratory data analysis (EDA) and feature importance analysis were conducted to assess the contribution of each metadata feature to the overall classification. Our fusion-based deep learning architecture outperformed single-modality models, boosting classification accuracy. The presented model achieved an accuracy of 94.5% and an overall F1-score of 0.94, validating its effectiveness in melanoma detection. This study aims to highlight the potential of deep learning-based multimodal fusion in enhancing diagnostic precision, offering a scalable and reliable solution for improved melanoma detection in smart healthcare systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid convolutional neural network for accurate organ segmentation in 3d head and neck CT images

arXiv

引用

arXiv 2021年

作者： Chen, Zijie Li, Cheng He, Junjun Ye, Jin Song, Diping Wang, Shanshan Gu, Lixu Qiao, Yu Shenzhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China Shanghai AI Lab Shanghai China Shenzhen Yino Intelligence Techonology Co. Ltd. Guangdong Shenzhen China Co. Ltd. Guangdong Shenzhen China Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China Peng Cheng Laboratory Guangdong Shenzhen China Pazhou Lab Guangdong Guangzhou China

Radiation therapy (RT) is widely employed in the clinic for the treatment of head and neck (HaN) cancers. An essential step of RT planning is the accurate segmentation of various organs-at-risks (OARs) in HaN CT images. Nevertheless, segmenting OARs manually is time-consuming, tedious, and error-prone considering that typical HaN CT images contain tens to hundreds of slices. Automated segmentation algorithms are urgently required. Recently, convolutional neural networks (CNNs) have been extensively investigated on this task. Particularly, 3D CNNs are frequently adopted to process 3D HaN CT images. There are two issues with naïve 3D CNNs. First, the depth resolution of 3D CT images is usually several times lower than the in-plane resolution. Direct employment of 3D CNNs without distinguishing this difference can lead to the extraction of distorted image features and influence the final segmentation performance. Second, a severe class imbalance problem exists, and large organs can be orders of times larger than small organs. It is difficult to simultaneously achieve accurate segmentation for all the organs. To address these issues, we propose a novel hybrid CNN that fuses 2D and 3D convolutions to combat the different spatial resolutions and extract effective edge and semantic features from 3D HaN CT images. To accommodate large and small organs, our final model, named Organ-Net2.5D, consists of only two instead of the classic four downsampling operations, and hybrid dilated convolutions are introduced to maintain the respective field. Experiments on the MICCAI 2015 challenge dataset demonstrate that OrganNet2.5D achieves promising performance compared to state-of-the-art methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Online 3D Underwater Exploration and Coverage

Online 3D Underwater Exploration and Coverage

引用

Symposium on Autonomous Underwater Vehicle Technology (AUV)

作者： Eduard Vidal Narcís Palomeras Marc Carreras Computer Vision and Robotics Institute Universitat de Girona Pic de Peguera 13 Girona Spain

ISBN: (纸本)9781728102542

This work proposes a novel 3-dimensional (3D) exploration and coverage methodology for autonomous underwater vehicles (AUVs). Exploration can be defined as the task of discovering an unknown region in the space. Most robotic exploration algorithms seek full coverage of the unknown region with data from one sensor (in the underwater domain, it is usually occupancy data from profiling sonars, or optical data from cameras). Our method is able to guide the robot so that full discovery and coverage is obtained in a single exploration for both occupancy data and optical data. Since the algorithm has to run in the AUV's onboard computer, with limited processing power, our method is based around efficient operations that can be performed to an octree data structure. This work extends our previous 2-dimensional (2D) method, which has proved to work in real tests conducted with the Sparus II AUV. In this work, we have used three real datasets to generate environments for its exploration in simulation: an underwater seamount, a shipwreck and an underwater cave. Results using the Girona 500 AUV show the feasibility of our exploration approach in all tested scenarios.

关键词： Cameras Three-dimensional displays Robot vision systems Optical sensors Optical imaging

来源：评论

学校读者我要写书评

暂无评论

Vehicular Multi-Camera Sensor System for Automated Visual Inspection of Electric Power Distribution Equipment

Vehicular Multi-Camera Sensor System for Automated Visual In...

引用

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Jinsun Park Ukcheol Shin Gyumin Shim Kyungdon Joo Francois Rameau Junhyeok Kim Dong-Geol Choi In So Kweon Robotics and Computer Vision Laboratory School of Electrical Engineering KAIST Daejeon Republic of Korea Korea Electric Power Corporation Korea Electric Power Research Institute Daejeon Republic of Korea Department of Information and Communication Engineering Hanbat National University Daejeon Republic of Korea

In this paper, we present a multi-camera sensor system along with its control algorithm for automated visual inspection from a moving vehicle. To accomplish this task, we propose a unique hardware configuration consisting of a frontal stereo vision system, six lateral cameras motorized to tilt, and a GPS/IMU sensor mounted on the roof of a car. From the frontal stereo system, we detect electric poles and estimate their corresponding 3D positions. Based on this 3D estimation, the tilt angles of the motorized lateral cameras are controlled in real-time to capture high resolution images of the equipment - typically installed a few meters above the road surface. In addition, inertial odometry information from the GPS/IMU module is utilized for pose estimation, object localization, and re-identification among cameras. Experimental results demonstrate the efficiency and robustness of our system for automated electric equipment maintenance, which can reduce human effort significantly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quality analysis of DCGAN-generated mammography lesions

arXiv

引用

arXiv 2019年

作者： Alyafi, Basel Diaz, Oliver Vilanova, Joan C. del Riego, Javier Marti, Robert Computer Vision and Robotics Institute University of Girona Spain Dept. of Mathematics and Computer Science University of Barcelona Spain Faculty of Medicine University of Girona Girona Spain Dept. of Radiology UDIAT Centre Diagnostic Parc Tauli Hospital Universitari Institut d’Investigacio Parc Tauli I3PT Spain

Medical image synthesis has gained a great focus recently, especially after the introduction of Generative Adversarial Networks (GANs). GANs have been used widely to provide anatomically-plausible and diverse samples for augmentation and other applications, including segmentation and super resolution. In our previous work, Deep Convolutional GANs were used to generate synthetic mammogram lesions, masses mainly, that could enhance the classification performance in imbalanced datasets. In this new work, a deeper investigation was carried out to explore other aspects of the generated images evaluation, i.e., realism, feature space distribution, and observers studies. t-Stochastic Neighbor Embedding (t-SNE) was used to reduce the dimensionality of real and fake images to enable 2D visualisations. Additionally, two expert radiologists performed a realism-evaluation study. Visualisations showed that the generated images have a similar feature distribution of the real ones, avoiding outliers. Moreover, Receiver Operating Characteristic (ROC) curve showed that the radiologists could not, in many cases, distinguish between synthetic and real lesions, giving 48% and 61% accuracies in a balanced sample *** Codes I.6.6, I.4.10 Copyright © 2019, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Fast Perception, Planning, and Execution for a Robotic Butler: Wheeled Humanoid M-Hubo

Fast Perception, Planning, and Execution for a Robotic Butle...

引用

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Moonyoung Lee Yujin Heo Jinyong Park Hyun-Dae Yang Ho-Deok Jang Philipp Benz Hyunsub Park In So Kweon Jun-Ho Oh Research Center Korea Advanced Institute of Science and Technology 291 Daehak-ro Yuseong-gu Daejeon Korea Robotics and Computer Vision Laboratory that is in charge of object perception part Korea Advanced Institute of Science and Technology 291 Daehakro Yuseong-gu Daejeon Korea

As the aging population grows at a rapid rate, there is an ever growing need for service robot platforms that can provide daily assistance at practical speed with reliable performance. In order to assist with daily tasks such as fetching a beverage, a service robot must be able to perceive its environment and generate corresponding motion trajectories. This becomes a challenging and computationally complex problem when the environment is unknown and thus the path planner must sample numerous trajectories that often are sub-optimal, extending the execution time. To address this issue, we propose a unique strategy of integrating a 3D object detection pipeline with a kinematically optimal manipulation planner to significantly increase speed performance at run-time. In addition, we develop a new robotic butler system for a wheeled humanoid that is capable of fetching requested objects at 24% of the speed a human needs to fulfill the same task. The proposed system was evaluated and demonstrated in a real-world environment setup as well as in public exhibition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Underwater 3D laser scanners: The deformation of the plane

引用

Workshop on Sensing and Control for Autonomous Vehicles: Applications to Land, Water and Air Vehicles, 2017

作者： Palomer, Albert Ridao, Pere Ribas, David Forest, Josep Computer Vision and Robotics Institute Universitat de Girona Girona Spain

ISBN: (纸本)9783319553719

Development of underwater 3D perception is necessary for autonomous manipulation and mapping. Using a mirror-galvanometer system to steer a laser plane and using triangulation, it is possible to produce full 3D perception without the need of moving the sensor. If the sensor does not meet certain hardware requirements, the laser plane is distorted when it passes through the different media (air–viewport– water). However, the deformation of this plane has not been studied. In this work a ray-tracing model is presented to study the deformation of the laser plane. To validate it, two types of datasets have been used, one synthetically generated using the model presented below, and another one using real data gathered underwater with an actual laser scanner. For both datasets an elliptic cone is fitted on the data and compared to a plane fit (the surface commonly used for triangulation). In the two experiments, the elliptic cone proved to be a better fit than the plane. © Springer International Publishing AG 2017.

关键词： Triangulation

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：