检索结果-内蒙古大学图书馆

A decomposition-based multiobjective evolutionary algorithm for sparse reconstruction 9th

学校读者我要写书评

暂无评论

A decomposition-based multiobjective evolutionary algorithm ...

9th International Conference on Swarm Intelligence, ICSI 2018

作者： Zhu, Jiang Cai, Muyao Tian, Shujuan Xu, Yanbing Pei, Tingrui College of Information Engineering Xiangtan University Xiangtan411105 China National Engineering Laboratory for Robot Visual Perception and Control Technology Hunan University Changsha410082 China

ISBN: (纸本)9783319938141

Sparse reconstruction is an important method aiming at obtaining an approximation to an original signal from observed data. It can be deemed as a multiobjective optimization problem for the sparsity and the observational error terms, which are considered as two conflicting objectives in evolutionary algorithm. In this paper, a novel decomposition based multiobjective evolutionary algorithm is proposed to optimize the two objectives and reconstruct the original signal more exactly. In our algorithm, a sparse constraint specific differential evolution is designed to guarantee that the solution remains sparse in the next generation. In addition, a neighborhood-based local search approach is proposed to obtain better solutions and improve the speed of convergence. Therefore, a set of solutions is obtained efficiently and is able to closely approximate the original signal. © Springer International Publishing AG, part of Springer Nature 2018.

关键词： Multiobjective optimization

MyoPS: A Benchmark of Myocardial Pathology Segmentation Combining Three-Sequence Cardiac Magnetic Resonance Images

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Lei Wu, Fuping Wang, Sihan Luo, Xinzhe Martín-Isla, Carlos Zhai, Shuwei Zhang, Jianpeng Liu, Yanfei Zhang, Zhen Ankenbrand, Markus J. Jiang, Haochuan Zhang, Xiaoran Wang, Linhong Arega, Tewodros Weldebirhan Altunok, Elif Zhao, Zhou Li, Feiyan Ma, Jun Yang, Xiaoping Puybareau, Elodie Oksuz, Ilkay Bricq, Stephanie Li, Weisheng Punithakumar, Kumaradevan Tsaftaris, Sotirios A. Schreiber, Laura M. Yang, Mingjing Liu, Guocai Xia, Yong Wang, Guotai Escalera, Sergio Zhuang, Xiahai School of Data Science Fudan University Shanghai China School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China Departament de Matemàtiques & Informàtica Universitat de Barcelona Barcelona Spain Computer Vision Center Universitat Autònoma de Barcelona Spain School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu China School of Computer Science and Engineering Northwestern Polytechnical University Xi'An China College of Electrical and Information Engineering Hunan University Changsha China National Engineering Laboratory for Robot Visual Perception and Control Technology Changsha China College of Physics and Information Engineering Fuzhou University Fuzhou China Comprehensive Heart Failure Center Wuerzburg University Hospitals Wuerzburg Germany School of Engineering University of Edinburgh Edinburgh United Kingdom School of Robotics Xi'an Jiaotong-Liverpool University Suzhou China Department of Electrical and Computer Engineering University of California Los Angeles United States Department of Radiology and Diagnostic Imaging University of Alberta Edmonton Canada Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecomm-Unications Chongqing China ImViA Laboratory Université Bourgogne Franche-Comté Dijon France Computer Engineering Department Istanbul Technical University Istanbul Turkey Le Kremlin-Bicêtre France Department of Mathematics Nanjing University of Science and Technology Nanjing China Department of Mathematics Nanjing University Nanjing China

Assessment of myocardial viability is essential in diagnosis and treatment management of patients suffering from myocardial infarction, and classification of pathology on myocardium is the key to this assessment. This work defines a new task of medical image analysis, i.e., to perform myocardial pathology segmentation (MyoPS) combining three-sequence cardiac magnetic resonance (CMR) images, which was first proposed in the MyoPS challenge, in conjunction with MICCAI 2020. The challenge provided 45 paired and pre-aligned CMR images, allowing algorithms to combine the complementary information from the three CMR sequences for pathology segmentation. In this article, we provide details of the challenge, survey the works from fifteen participants and interpret their methods according to five aspects, i.e., preprocessing, data augmentation, learning strategy, model architecture and post-processing. In addition, we analyze the results with respect to different factors, in order to examine the key obstacles and explore potential of solutions, as well as to provide a benchmark for future research. We conclude that while promising results have been reported, the research is still in the early stage, and more in-depth exploration is needed before a successful application to the clinics. Note that MyoPS data and evaluation tool continue to be publicly available upon registration via its homepage (***/zhuangxiahai/0/myops20/). © 2022, CC BY-NC-SA.

关键词： Magnetic resonance imaging

Fast ORB-SLAM without Keypoint Descriptors

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Fu, Qiang Yu, Hongshan Wang, Xiaolong Yang, Zhengeng He, Yong Zhang, Hong Mian, Ajmal The National Engineering Laboratory for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan University China The Department of Computing Science University of Alberta Canada Quanzhou Institute of Industrial Design and Machine Intelligence Innovation Hunan University China The Southern University of Science and Technology Shenzhen China The School of Mathematics and Information Science Shaanxi Normal University China The Department of Computer Science The University of Western Australia WA6009 Australia

Indirect methods for visual SLAM are gaining popularity due to their robustness to environmental variations. ORB-SLAM2 [1] is a benchmark method in this domain, however, it consumes significant time for computing descriptors that never get reused unless a frame is selected as a keyframe. To overcome these problems, we present FastORB-SLAM which is light-weight and efficient as it tracks keypoints between adjacent frames without computing descriptors. To achieve this, a two stage descriptor-independent keypoint matching method is proposed based on sparse optical flow. In the first stage, we predict initial keypoint correspondences via a simple but effective motion model and then robustly establish the correspondences via pyramid-based sparse optical flow tracking. In the second stage, we leverage the constraints of the motion smoothness and epipolar geometry to refine the correspondences. In particular, our method computes descriptors only for keyframes. We test FastORB-SLAM on TUM and ICL-NUIM RGB-D datasets and compare its accuracy and efficiency to nine existing RGB-D SLAM methods. Qualitative and quantitative results show that our method achieves state-of-the-art accuracy and is about twice as fast as the ORB-SLAM2. Copyright © 2020, The Authors. All rights reserved.

关键词： Optical flows

Target Tracking Based on Correlation Filter for Scale Offset

学校读者我要写书评

暂无评论

IOP Conference Series: Materials Science and engineering 2020年第1期790卷

作者： Jianhao Tan Xiaoping Ma Yaonan Wang College of Electrical and Information Engineering Hunan University Changsha 410082 China National Engineering Laboratory for Robot Visual Perception and Control Technology Changsha 410082 China

Existing scale estimation methods mainly use fixed-size tracking box for target tracking. However, when the moving direction of the target changes from near to far or from far to near, the size of the current tracking box cannot adapt to the scale change. In order to overcome the disadvantage of invariant size of tracking box in the scale change, this paper proposes a scale offset estimation method based on correlation filter by combining the state of previous frame and current frame of the target. Select the scale proposal box in the scale layer, and adjust the position and size of the actual tracking box in real time according to the size of the proposal box, target position and scale offset. In this paper, OTB-100 is used as the dataset. The obtained tracking results show that our algorithm Ours has better tracking performance than the existing others tracking algorithm in scale variation, and it has better tracking effect and stronger robustness in drift and occlusion events.

关键词：

Dynamic Update Siamese Networks with Deeper Features

学校读者我要写书评

暂无评论

IOP Conference Series: Materials Science and engineering 2020年第1期790卷

作者： Jianhao Tan Shanshan Tan Wang Yin Liming Liu Siyuan Zhang Yaonan Wang College of Electrical and Information Engineering Hunan University Changsha 410082 China National Engineering Laboratory for Robot Visual Perception and Control Technology Changsha 410082 China

visual object tracking has been a concern topic these years, and many trackers have achieved good results in various fields. These researches and breakthroughs have made many improvements to solve problems such as drift, lighting, deformation and occlusion. In this paper, we improve the structure of the AlexNet[1] network by designing the three important influencing factors of the receptive field size, total network step size, and feature filling of the twin network. Apart from this, we add a smoothing matrices and a background suppression matrices to effectively learn the features of the first few frames as much as possible. Fuse multilayer feature elements can learn online about target appearance changes and background suppression, and we train them by using continuous video sequences.

关键词：

Research on Selective filtering and PCNN for Nickel Foam Surface Defect Segmentation

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2018年第21期51卷 135-140页

作者： Li, Jianqi Zhu, Jiang Nie, Fangyan Cao, Binfang Huang, Lijuan Hunan Province Cooperative Innovation Center for The Construction & Development of Dongting Lake Ecological Economic Zone Hunan University of Arts and Science ChangdeHunan China College of Information Engineering Xiangtan University Xiangtan411105 China National Engineering Laboratory for Robot Visual Perception and Control Technology Hunan University Changsha410082 China

As the key basis materials of Ni-MH and Ni/Cd battery electrode, the quality of the nickel foam products is closely related with the performance and safety of rechargeable batteries. In order to meet the requirements of automatic defect inspection, this paper proposes an image segmentation method for the appearance defects of nickel foam. Nickel foam image has the characteristics of a low degree of differentiation between foreground and background, basic structure of mutual adhesion, surface morphology for complex random texture features. In order to extract defects from complex nickel foam surface image, a novel selective filtering method is proposed to preprocess the original image, thereby reducing the effects of the above factors, and then a modified PCNN method is used to segment the defect area. The results show that the proposed method can effectively segregate the defects from the background, which lays a foundation for the automatic detection of the appearance quality of nickel foam. © 2018

关键词： Image segmentation Computer vision Nickel metal hydride batteries Surface defects Appearance qualities Automatic defect inspection Automatic Detection Defect inspection modified PCNN Nickel foam Segmentation methods Selective filtering

Real time backbone for semantic segmentation

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yang, Zhengeng Yu, Hongshan Fu, Qiang Sun, Wei Jia, Wenyan Sun, Mingui Mao, Zhi-Hong National Engineering Laboratory for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan University Lushan South Rd. Yuelu Dist. Changsha410082 China University of Pittsburgh University of Pittsburgh PittsburghPA United States Department of Electrical and Computer Engineering Department of Neurosurgery

The rapid development of autonomous driving in recent years presents lots of challenges for scene understanding. As an essential step towards scene understanding, semantic segmentation thus received lots of attention in past few years. Although deep learning based state-of-the-arts have achieved great success in improving the segmentation accuracy, most of them suffer from an inefficiency problem and can hardly applied to practical applications. In this paper, we systematically analyze the computation cost of Convolutional Neural Network(CNN) and found that the inefficiency of CNN is mainly caused by its wide structure rather than the deep structure. In addition, the success of pruning based model compression methods proved that there are many redundant channels in CNN. Thus, we designed a very narrow while deep backbone network to improve the efficiency of semantic segmentation. By casting our network to FCN32 segmentation architecture, the basic structure of most segmentation methods, we achieved 60.6% mIoU on Cityscape val dataset with 54 frame per seconds(FPS) on 1024 × 2048 inputs, which already outperforms one of the earliest real time deep learning based segmentation methods: ENet. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantic Segmentation

Adaptive robust RBFNNs-based model estimator for a small quadrotor aircraft robot

学校读者我要写书评

暂无评论

Adaptive robust RBFNNs-based model estimator for a small qua...

IEEE/ASME International Conference on Mechtronic and Embedded Systems and Applications, MESA

作者： Hang Zhong Shushuai Li Yaonan Wang Hongjian Liu College of Electrical and Information Engineering Hunan University China National Engineering Laboratory for Robot Visual Perception and Control Technology

ISBN: (纸本)9781509061914

This paper presents an on-line estimator that incorporates adaptive MIMO radical basis function neural networks (RBFNNs) for model identification of quadrotor unmanned aerial vehicles (UAVs). The inputs and outputs of quadrotor aircrafts can be obtained from dynamic models or real attitude and position sensors. The adaptive learning rate is employed in the gradient descent method for the update of the weights of RBFNNs, and Lyapunov approach guarantees the stability of the global convergence of the modeling errors. The Welsch functions are also employed as the error functions to get rid of the influence from the noise due to disturbances like wind gusts. Simulation results using robotics Toolbox for Matlab verify the effectiveness and robustness of the proposed estimator compared with results of traditional RBFNNs. Experiment results from real aircraft platform show that RBFNNs combining adaptive learning rate and Welsch error functions can approximate the overall system with high accuracy and robustness to disturbances.

关键词： Atmospheric modeling Aircraft Mathematical model Adaptation models Robustness robots MIMO

Partial labeled gastric tumor segmentation via patch⇂based reiterative learning

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Nan, Yang Coppola, Gianmarc Liang, Qiaokang Zou, Kunglin Sun, Wei Zhang, Dan Wang, Yaonan Yu, Guanzhen College of Electrical and Information Engineering Hunan University Changsha410082 China National Engineering Laboratory for Robot Vision Perception and Control Hunan University Changsha Hunan410082 China Hunan Key Laboratory of Intelligent Robot Technology in Electronic Manufacturing Hunan418000 China Faculty of Engineering and Applied Science University of Ontario Institute of Technology OshawaONL1H 7K4 Canada Department of Mechanical Engineering York University TorontoONM3J 1P3 Canada Department of Oncology Longhua Hospital Affiliated to Shanghai University of Traditional Chinese Medicine Shanghai201203 China

Gastric cancer is the second leading cause of cancer‐related deaths worldwide, and the major hurdle in biomedical image analysis is the determination of the cancer extent. This assignment has high clinical relevance and would generally require vast microscopic assessment by pathologists. Recent advances in deep learning have produced inspiring results on biomedical image segmentation, while its outcome is reliant on comprehensive annotation. This requires plenty of labor costs, for the ground truth must be annotated meticulously by pathologists. In this paper, a reiterative learning framework was presented to train our network on partial annotated biomedical images, and superior performance was achieved without any pre‐trained or further manual annotation. We eliminate the boundary error of patch‐based model through our overlapped region forecast algorithm. Through these advisable methods, a mean intersection over union coefficient (IOU) of 0.883 and mean accuracy of 91.09% on the partial labeled dataset was achieved, which made us win the 2017 China Big Data & Artificial Intelligence Innovation and Entrepreneurship Competitions1. Copyright © 2017, The Authors. All rights reserved.

关键词： Diseases