检索结果-内蒙古大学图书馆

Robust active contours based on local threshold preprocessing fitting energies for fast segmentation of inhomogenous images

引用

ELECTRONICS LETTERS 2021年第15期57卷 576-578页

作者： Guo, Baojun Cui, Jinlong Gao, Beibei Beijing Jiaotong Univ Haibin Coll Sch Elect & Elect Engn Huanghua Peoples R China

This letter presents a robust active contour model driven by the local threshold preprocessing fitting energies to actualize fast segmentation of inhomogenous images. First, the local threshold preprocessing is carried out to compute two local intensity means. Second, these two means are sorted and serve as the local area fitting centres, which makes the contour move along the internal or external target boundaries. Finally, the above local area fitting centres are used to build the model's energy functional based on the symmetric cross entropy. Experimental results of the real inhomogenous images confirm that the presented model can segment inhomogenous images much faster and is robust to the setting up of the original contour.

关键词： Optical, image and video signal processing Interpolation and function approximation (numerical analysis) computer vision and image processing techniques Interpolation and function approximation (numerical analysis)

来源：评论

学校读者我要写书评

暂无评论

Analysis of feasibility and advantages of multi-source image registration using regional features

引用

ELECTRONICS LETTERS 2021年第7期57卷 285-287页

作者： Zeng, Liang Lu, Danwei Zhu, Qingtao Xing, Cheng Yin, Junjun Yang, Jian Tsinghua Univ Dept Elect Engn Beijing Peoples R China Univ Sci & Technol Sch Comp & Commun Engn Beijing Peoples R China

Automatic registration of multi-source remote sensing data is a challenging task due to the high non-linearity of radiometric differences among various data. Feature extraction is a key enabling technique in registration algorithm design. In this letter, we prove the feasibility of using extracted regional features for multi-source image registration. In particular, regional features can be extracted through pixel-level image classification, and existing off-the-shelf algorithms can be directly adopted. Experiment results demonstrate the robustness of the regional-feature-based registration method.

关键词： Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research Optical, image and video signal processing computer vision and image processing techniques Patient diagnostic methods and instrumentation Biology and medical computing

来源：评论

学校读者我要写书评

暂无评论

Few-shot action recognition using task-adaptive parameters

引用

ELECTRONICS LETTERS 2021年第22期57卷 848-850页

作者： Zong, Pengcheng Chen, Peng Yu, Tianwei Yan, Lingqiang Huan, Ruohong Zhejiang Univ Technol Coll Informat & Engn Hangzhou Peoples R China Zhejiang Univ Technol Coll Comp Sci & Technol Hangzhou Peoples R China

Few-shot action recognition aims to recognise unseen actions given a few examples. Thus, this letter proposes a model named meta relation network (Meta RN) to address such problem. This model contains two parts: a MetaNet and a relation network. Relation network is utilised to extract video features and classify actions. A second-order pooling followed by power normalization is used for feature enhancement, and target videos are finally classified by exploring nonlinear distance relations. The MetaNet module is designed to model different task distributions and generate task-adaptive parameters for the embedding layer of the relation network in different tasks. Experimental results on two public action recognition datasets demonstrate that the network achieves higher accuracies than several state-of-the-art approaches.

关键词： Optical, image and video signal processing image recognition Other topics in statistics computer vision and image processing techniques Video signal processing

来源：评论

学校读者我要写书评

暂无评论

Recognizing the formations of CVBG based on shape context using electronic reconnaissance data

引用

ELECTRONICS LETTERS 2021年第14期57卷 562-563页

作者： Shi, Lei Huang, Zhen Feng, Xuefeng Tsinghua Univ Sch Aerosp Engn Beijing Peoples R China Tsinghua Univ Beijing Natl Res Ctr Informat Sci & Technol Beijing Peoples R China Tsinghua Univ Space Ctr Beijing Peoples R China

To recognize the formation of the carrier battle group (CVBG) from passive electronic reconnaissance and location data, a shape context-based method is proposed. The proposed method treats the location data as a graph model, and a graph matching method is used for formation recognition. The shape context and background context for each unit in CVBG is calculated and used for multi-viewpoint shape feature, which is rotation invariance and distinctive. The experimental results show that the proposed method can recognize the formation with a higher accuracy and locate the ship with electromagnetic silence.

关键词： Laser beam modulation, pulsing and switching mode locking and tuning Ultrafast optical techniques image recognition computer vision and image processing techniques Combinatorial mathematics

来源：评论

学校读者我要写书评

暂无评论

Head pose-free gaze estimation using domain adaptation

引用

ELECTRONICS LETTERS 2021年第16期57卷 618-620页

作者： Ahn, Byungtae Seo, Minseok Choi, Dong-Geol Korea Inst Machinery & Mat Dept AI Machinery Mech Syst Safety Res Div Daejeon South Korea Hanbat Natl Univ Dept Informat & Commun Engn Daejeon South Korea

Human gaze information has been widely used in various areas, such as medical diagnosis and human-computer interactions (HCI). This study proposes a head pose-free 3D gaze estimation method using a deep convolutional neural network (DCNN). To infer gaze direction, only a small grayscale image is required without any special devices such as an infrared (IR) illuminator and RGBD sensor. A domain adaptation method to reduce the feature gap between real and synthetic image data is also proposed here. Moreover, a novel synthetic dataset (SynFace) that contains head poses, gaze directions, and facial landmarks is established and released. The proposed method outperforms state-of-the-art methods and achieves a mean error of less than 4(White circle).

关键词： Optical, image and video signal processing image recognition image sensors computer vision and image processing techniques Other topics in statistics Other topics in statistics User interfaces

来源：评论

学校读者我要写书评

暂无评论

Face anti-spoofing with refined triplet loss and multi-level attention constraint network

引用

ELECTRONICS LETTERS 2021年第24期57卷 912-914页

作者： Nong, Xingzhong Zeng, Ying Hu, Haifeng Guangzhou Metro Design & Res Inst Co Ltd Guangzhou Peoples R China Sun Yat Sen Univ Sch Elect & Informat Technol Guangzhou Peoples R China

One critical issue for existing face recognition (FR) systems is to ensure its accuracy and robustness, which calls for the development of face anti-spoofing (FAS) algorithms to work against presentation attacks (PA). This letter proposes a novel Multi-level Attention Constraint Network with a Refined Triplet Loss (MACN-RTL) for the task of FAS. Specifically, an MACN which consists of two components is designed, that is, Multi-level Attention Network (MAN) and Distribution Constraint (DC). MAN aims to exploit effective information from different levels, while DC helps to learn a more compact and discriminative feature embedding for classification. Besides, a Refined Triplet Loss for better model optimisation is devised. Compared with existing FAS works, MACN is designed for better feature extraction and a better solution for optimisation by RTL. Experimental results demonstrate the superiority of the proposed approach. To ensure the security of FR systems towards PA, a novel MACN-RTL is proposed, which can generate a more informative and discriminative feature embedding for accurate classification. The designed MACN leverages attention mechanisms to obtain effective representations and reduces the distributional discrepancy of cross-domain samples. An RTL is devised to refine the widely used triplet loss by adding a refinement term to achieve a better optimisation of the model. ***.

关键词： image recognition computer vision and image processing techniques Data security Neural nets

来源：评论

学校读者我要写书评

暂无评论

PRGFlow: Unified SWAP-aware deep global optical flow for aerial robot navigation

引用

ELECTRONICS LETTERS 2021年第16期57卷 614-617页

作者： Sanket, Nitin J. Singh, Chahat Deep Fermuller, Cornelia Aloimonos, Yiannis Univ Maryland Percept & Robot Grp College Pk MD 20742 USA

Global optical flow estimation is the foundation stone for obtaining odometry which is used to enable aerial robot navigation. However, such a method has to be of low latency and high robustness whilst also respecting the size, weight, area and power (SWAP) constraints of the robot. A combination of cameras coupled with inertial measurement units (IMUs) has proven to be the best combination in order to obtain such low latency odometry on resource-constrained aerial robots. Recently, deep learning approaches for visual inertial fusion have gained momentum due to their high accuracy and robustness. However, an equally noteworthy benefit for robotics of these techniques are their inherent scalability (adaptation to different sized aerial robots) and unification (same method works on different sized aerial robots). To this end, we present a deep learning approach called PRGFlow for obtaining global optical flow and then loosely fuse it with an IMU for full 6-DoF (Degrees of Freedom) relative pose estimation (which is then integrated to obtain odometry). The network is evaluated on the MSCOCO dataset and the dead-reckoned odometry on multiple real-flight trajectories without any fine-tuning or re-training. A detailed benchmark comparing different network architectures and loss functions to enable scalability is also presented. It is shown that the method outperforms classical feature matching methods by 2x under noisy data. The supplementary material and code can be found at .

关键词： Optical, image and video signal processing image recognition Optimisation techniques Spatial variables control Transducers and sensing devices Aerospace control Mobile robots Telerobotics Sensor fusion computer vision and image processing techniques File organisation Control engineering computing Optimisation techniques Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

Restore DeepFakes video frames via identifying individual motion styles

引用

ELECTRONICS LETTERS 2021年第4期57卷 183-186页

作者： Zhang, Haichao Lu, Zhe-Ming Luo, Hao Feng, Ya-Pei Zhejiang Univ Sch Aeronaut & Astronaut Hangzhou Peoples R China Hangzhou Dianzi Univ Coll Comp Sci & Technol Hangzhou Peoples R China

Recent advance on highly realistic AI-synthesised video approaches makes it hard to distinguish whether a speaker in video is real. Many existing DeepFakes detection approaches can be invalidated by using them as supervision in adversarial training, which in turn improves the performance of DeepFakes. This makes the problem a dilemma. However, human can recognise the identity of familiar persons by observing their motion styles. Inspired by this, the paper proposes a novel method to recognise original speaker's identity clues in DeepFakes videos by learning individual motion styles. As a biological signature, motion styles can neither be used in the training process of DeepFakes nor be modified to deceive detection methods without reducing realistic performance. Also, this paper proposes a novel pipeline to continuously restore the original frames from DeepFakes videos without knowing the DeepFakes approach in advance. Based on above ideas, our scheme makes it possible to restore DeepFakes videos. Through training the cross-modal transfer module, the appearance embedding can be inferred from the identity code. Extensive experiments are conducted to reveal the effectiveness of the method, it shows for the first time that the original persons can be identified automatically and the original video from DeepFakes videos can be generated.

关键词： Speech and audio signal processing Optical, image and video signal processing computer vision and image processing techniques Video signal processing Speech processing techniques

来源：评论

学校读者我要写书评

暂无评论

A remote healthcare monitoring framework for diabetes prediction using machine learning

引用

HEALTHCARE TECHNOLOGY LETTERS 2021年第3期8卷 45-57页

作者： Ramesh, Jayroop Aburukba, Raafat Sagahyroon, Assim Amer Univ Sharjah Comp Sci & Engn Sharjah U Arab Emirates

Diabetes is a metabolic disease that affects millions of people each year. It is associated with an increased likelihood of vital organ failures and decreased quality of life. Early detection and regular monitoring are crucial for managing diabetes. Remote patient monitoring can facilitate effective intervention and treatment paradigms using current technology. This work proposes an end-to-end remote monitoring framework for automated diabetes risk prediction and management, using personal health devices, smart wearables and smartphones. A support vector machine was developed for diabetes risk prediction using the Pima Indian Diabetes Database, after feature scaling, imputation, selection and augmentation. This work achieved the performance metrics of accuracy, sensitivity and specificity scores at 83.20%, 87.20% and 79% respectively through the tenfold stratified cross validation method, which is competitive with existing methods. Patients can use multiple healthcare devices, smartphones and smartwatches to measure vital parameters, curb the progression of diabetes and close the communication loop with medical professionals. The proposed framework enables medical professionals to make informed decisions based on the latest diabetes risk predictions and lifestyle insights while attaining unobtrusiveness, reduced cost, and vendor interoperability.

关键词： Optical, image and video signal processing Biomedical communication computer vision and image processing techniques Data handling techniques Medical administration Patient diagnostic methods and instrumentation Patient care and treatment Biology and medical computing

来源：评论

学校读者我要写书评

暂无评论

Hough transform based ego-velocity estimation in automotive radar system

引用

ELECTRONICS LETTERS 2021年第2期57卷 80-82页

作者： Lim, Sohee Lee, Seongwook Seoul Natl Univ Seoul South Korea Korea Aerosp Univ Gyeonggi Do South Korea

In general, the velocity estimated through the automotive radar is the relative velocity between the ego-vehicle and the target. To estimate the absolute velocity of the ego-vehicle (i.e. ego-velocity), it is necessary to get help from other automotive sensors, such as cameras and lidars. In this letter, therefore, a method for estimating the ego-velocity is proposed using only radar sensor data. To estimate the ego-velocity, stationary targets in the detection result have to be identified because the velocity relative to the stationary target can be directly converted to the ego-velocity. In the proposed method, the radar data is first processed to extract the relative distance from the ego-vehicle to the target, relative velocity between the ego-vehicle and the target, and angle between the ego-vehicle and the target. Then, the detected targets are represented in the angle-velocity domain because moving and stationary targets in this domain exhibit different characteristics. In other words, the moving targets are randomly placed, but the stationary targets exist around a specific line. Finally, the Hough transformation is applied to automatically determine the line, and the ego-velocity is calculated from the transform result. The proposed method shows a maximum error of 2.4% in the velocity range of 30-90 km/h.

关键词： Optical, image and video signal processing Radar equipment, systems and applications Optical radar computer vision and image processing techniques Automobile electronics and electrics

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：