检索结果-内蒙古大学图书馆

Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Yang Yu, Xin Lu, Xiaobo Liu, Ping The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The Australian Institute of Artificial Intelligence University of Technology Sydney UltimoNSW2007 Australia The School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Singapore138634 Singapore

In this paper, we study the task of hallucinating an authentic high-resolution (HR) face from an occluded thumbnail. We propose a multi-stage Progressive Upsampling and Inpainting Generative Adversarial Network, dubbed Pro-UIGAN, which exploits facial geometry priors to replenish and upsample (8×) the occluded and tiny faces (16×16 pixels). Pro-UIGAN iteratively (1) estimates facial geometry priors for low-resolution (LR) faces and (2) acquires non-occluded HR face images under the guidance of the estimated priors. Our multi-stage hallucination network upsamples and inpaints occluded LR faces via a coarse-to-fine fashion, significantly reducing undesirable artifacts and blurriness. Specifically, we design a novel cross-modal attention module for facial priors estimation, in which an input face and its landmark features are formulated as queries and keys, respectively. Such a design encourages joint feature learning across the input facial and landmark features, and deep feature correspondences will be discovered by attention. Thus, facial appearance features and facial geometry priors are learned in a mutually beneficial manner. Extensive experiments show that our Pro-UIGAN attains visually pleasing completed HR faces, thus facilitating downstream tasks, i.e., face alignment, face parsing, face recognition as well as expression classification. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

Fast and accurate single-image depth estimation on mobile devices, mobile AI 2021 challenge: Report

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ignatov, Andrey Malivenko, Grigory Plowman, David Shukla, Samarth Timofte, Radu Zhang, Ziyu Wang, Yicheng Huang, Zilong Luo, Guozhong Yu, Gang Fu, Bin Wang, Yiran Li, Xingyi Shi, Min Xian, Ke Cao, Zhiguo Du, Jin-Hua Wu, Pei-Lin Ge, Chao Yao, Jiaoyang Tu, Fangwen Li, Bo Yoo, Jung Eun Seo, Kwanggyoon Xu, Jialei Li, Zhenyu Liu, Xianming Jiang, Junjun Chen, Wei-Chi Joya, Shayan Fan, Huanhuan Kang, Zhaobing Li, Ang Feng, Tianpeng Liu, Yang Sheng, Chuannan Yin, Jian Benavides, Fausto T. Computer Vision Lab ETH Zurich Switzerland Ltd AI Witchlabs Switzerland Tencent GY-Lab China Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Nanjing Artificial Intelligence Chip Research Institute of Automation Chinese Academy of Sciences China Black Sesame Technologies Inc. Singapore Singapore Visual Media Lab KAIST Korea Republic of Harbin Institute of Technology China Peng Cheng Laboratory China Multimedia and Computer Vision Laboratory National Cheng Kung University Taiwan Samsung Research UK United Kingdom OPPO Research Institute China ETH Zurich Switzerland

Depth estimation is an important computer vision problem with many practical applications to mobile devices. While many solutions have been proposed for this task, they are usually very computationally expensive and thus are not applicable for on-device inference. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based depth estimation solutions that can demonstrate a nearly real-time performance on smartphones and IoT platforms. For this, the participants were provided with a new large-scale dataset containing RGB-depth image pairs obtained with a dedicated stereo ZED camera producing high-resolution depth maps for objects located at up to 50 meters. The runtime of all models was evaluated on the popular Raspberry Pi 4 platform with a mobile ARM-based Broadcom chipset. The proposed solutions can generate VGA resolution depth maps at up to 10 FPS on the Raspberry Pi 4 while achieving high fidelity results, and are compatible with any Android or Linux-based mobile devices. A detailed description of all models developed in the challenge is provided in this paper. Copyright © 2021, The Authors. All rights reserved.

关键词： computer operating systems

Point cloud-based registration and image fusion between cardiac SPECT MPI and CTA

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Shaojie, Tang Penpen, Miao Xingyu, Gao Yu, Zhong Dantong, Zhu Haixing, Wen Zhihui, Xu Qiuyue, Wei Hongping, Yao Xin, Huang Rui, Gao Chen, Zhao Weihua, Zhou School of Automation Xi’an University of Posts and Telecommunications Shaanxi Xi’an710121 China Xi'an Key Laboratory of Advanced Control and Intelligent Process Shaanxi Xi’an710121 China Second Clinical Medical School of Nanjing Medical University Jiangsu Nanjing210011 China Department of Cardiology The First Affiliated Hospital of Nanjing Medical University Jiangsu Nanjing210000 China Department of Pharmacy The First Affiliated Hospital of Xi’an Jiaotong University Shaanxi Xi’an710061 China Department of Cardiology The First Affiliated Hospital of Xi’an Jiaotong University Shaanxi Xi’an710061 China Department of Nuclear Medicine The First Affiliated Hospital of Xi’an Jiaotong University Shaanxi Xi’an710061 China Department of Computer Science Kennesaw State University MariettaGA30060 United States Department of Applied Computing Center for Biocomputing and Digital Health Institute of Computing and Cybersystems Health Research Institute Michigan Technological University HoughtonMI49931 United States

A method was proposed for the point cloud-based registration and image fusion between cardiac single photon emission computed tomography (SPECT) myocardial perfusion images (MPI) and cardiac computed tomography angiograms (CTA). Firstly, the left ventricle (LV) epicardial regions (LVERs) in SPECT and CTA images were segmented by using different U-Net neural networks trained to generate the point clouds of the LV epicardial contours (LVECs). Secondly, according to the characteristics of cardiac anatomy, the special points of anterior and posterior interventricular grooves (APIGs) were manually marked in both SPECT and CTA image volumes. Thirdly, we developed an in-house program for coarsely registering the special points of APIGs to ensure a correct cardiac orientation alignment between SPECT and CTA images. Fourthly, we employed ICP, SICP or CPD algorithm to achieve a fine registration for the point clouds (together with the special points of APIGs) of the LV epicardial surfaces (LVERs) in SPECT and CTA images. Finally, the image fusion between SPECT and CTA was realized after the fine registration. The experimental results showed that the cardiac orientation was aligned well and the mean distance error of the optimal registration method (CPD with affine transform) was consistently less than 3 mm. The proposed method could effectively fuse the structures from cardiac CTA and SPECT functional images, and demonstrated a potential in assisting in accurate diagnosis of cardiac diseases by combining complementary advantages of the two imaging modalities. © 2024, CC BY.

关键词： Image fusion

Universal enzymatic numerical P systems with small number of enzymatic variables

学校读者我要写书评

暂无评论

science China(Information sciences) 2018年第9期61卷 38-49页

作者： Zhiqiang ZHANG Tingfang WU ANDrei P■UN Linqiang PAN Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Automation Huazhong University of Science and Technology Department of Computer Science Faculty of Mathematics and Computer ScienceUniversity of Bucharest Bioinformatics Department National Institute of Research and Development for Biological Sciences School of Electric and Information Engineering Zhengzhou University of Light Industry

Numerical P systems(for short, NP systems) are distributed and parallel computing models inspired from the structure of living cells and economics. Enzymatic numerical P systems(for short, ENP systems) are a variant of NP systems, which have been successfully applied in designing and implementing controllers for mobile robots. Since ENP systems were proved to be Turing universal, there has been much work to simplify the universal systems, where the complexity parameters considered are the number of membranes, the degrees of polynomial production functions or the number of variables used in the *** the number of enzymatic variables, which is essential for ENP systems to reach universality, has not been investigated. Here we consider the problem of searching for the smallest number of enzymatic variables needed for universal ENP systems. We prove that for ENP systems as number acceptors working in the all-parallel or one-parallel mode, one enzymatic variable is sufficient to reach universality; while for the one-parallel ENP systems as number generators, two enzymatic variables are sufficient to reach *** results improve the best known results that the numbers of enzymatic variables are 13 and 52 for the all-parallel and one-parallel systems, respectively.

关键词： bio-inspired computing numerical P system mobile robot membrane controller universality

Multi-sensor performance evaluation and management in integrated navigation based on observability analysis 31

学校读者我要写书评

暂无评论

Multi-sensor performance evaluation and management in integr...

31st Chinese control and Decision Conference, CCDC 2019

作者： Shen, Kai Wang, Meiling Yin, Zhang Neusypin, Konstantin A. School of Automation Beijing Institute of Technology Beijing 100081 China Faculty of Computer Science and Control Systems Bauman Moscow State Technical University Moscow 105005 Russian Federation

ISBN: (纸本)9781728101071;9781728101064

This paper presents a new way of multi-sensor performance evaluation and management in integrated navigation based on observability analysis. First, the general observability theory of linear systems was reviewed, and consequently a definition of local observability and local observability matrix were further introduced. Second, a scalar form of the degree of observability was present from the point of view of estimation quality. Third, the application of the degree of observability to integrated navigation systems was illustrated. As expected, the simulation results showed that the degree of observability can help us to gain the information about how observable a state-variable is, and can further function as an indicator to evaluate the performance of each navigation sensor and autonomously manage sensors in integrated navigation systems. © 2019 IEEE.

关键词： integrated navigation. multi-sensor management observability analysis performance evaluation the degree of observability

3D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose from Monocular Video

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Guangming Zhong, Jiquan Zhao, Shijie Wu, Wenhua Liu, Zhe Wang, Hesheng Department of Automation Institute of Medical Robotics Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China Department of Engineering Mechanics Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Technology University of Cambridge CambridgeCB2 1TN United Kingdom

Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video. A novel unsupervised training framework is proposed with 3D hierarchical refinement and augmentation using explicit 3D geometry. In this framework, the depth and pose estimations are hierarchically and mutually coupled to refine the estimated pose layer by layer. The intermediate view image is proposed and synthesized by warping the pixels in an image with the estimated depth and coarse pose. Then, the residual pose transformation can be estimated from the new view image and the image of the adjacent frame to refine the coarse pose. The iterative refinement is implemented in a differentiable manner in this paper, making the whole framework optimized uniformly. Meanwhile, a new image augmentation method is proposed for the pose estimation by synthesizing a new view image, which creatively augments the pose in 3D space but gets a new augmented 2D image. The experiments on KITTI demonstrate that our depth estimation achieves state-of-the-art performance and even surpasses recent approaches that utilize other auxiliary tasks. Our visual odometry outperforms all recent unsupervised monocular learning-based methods and achieves competitive performance to the geometry-based method, ORB-SLAM2 with back-end optimization. Copyright © 2021, The Authors. All rights reserved.

关键词： Robots

Enhanced gear fault diagnosis via heterodyne downconversion: Theoretical verification and optimized ultrasonic signal acquisition

学校读者我要写书评

暂无评论

Measurement 2025年 256卷

作者： Jingchao Zhang Shaoqun Zhang Yixue Dong Chen Li Guoqian Jiang Yingwei Li Xiaoli Li School of Information Science and Engineering Yanshan University Qinhuangdao 066004 China Hebei Key Laboratory of Information Transmission and Signal Processing Qinhuangdao 066004 China Intelligent Control System R&D Department Computer Application Technology Research Institute China Ordnance Industry Beijing 100089 China School of Electrical Engineering Yanshan University Qinhuangdao 066004 China School of Automation Science and Engineering South China University of Technology Guangzhou 510641 China Pazhou Lab Guangzhou 510330 China

Ultrasonic fault diagnosis has emerged as a promising technique for gear fault detection, owing to its capability to capture modulated high-frequency transients induced by incipient or localized defects. However, its practical application is constrained by the requirement for extremely high sampling rates. Heterodyne downconversion offers a potential solution by translating ultrasonic spectral components to lower frequencies, though its effectiveness in preserving diagnostic features remains insufficiently validated. This study conducts a theoretical analysis of the influence of heterodyne downconversion on ultrasonic signal characteristics and proposes an optimized heterodyne-based ultrasonic acquisition system with enhanced charge amplification and frequency conversion circuits. Experimental evaluations using a gear fault test platform demonstrate that the downconverted signals preserve the envelope spectral features of the original ultrasonic signals. Furthermore, comparative analyses indicate that the proposed method achieves superior fault detection sensitivity compared to conventional vibration-based techniques, particularly under high rotational speeds. These findings validate the feasibility and diagnostic advantages of the proposed heterodyne-based approach for efficient and accurate ultrasonic condition monitoring.

关键词：

A New Approach for Face Anti-Spoofing Using Handcrafted and Deep Network Features

学校读者我要写书评

暂无评论

A New Approach for Face Anti-Spoofing Using Handcrafted and ...

2019 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2019

作者： Das, Polash Kumar Hu, Bin Liu, Chang Cui, Kaixin Ranjan, Prabhat Xiong, Gang School of Electronic and Information Engineering South China University of Technology Guangzhou China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Science Beijing China College of Computer Science Sichuan University Chengdu China Cloud Computing Center Chinese Academy of Science Dongguan China

ISBN: (纸本)9781728128535

In biometrics, face recognition methods are achieving momentum with recent progress in the computer vision(CV). Face recognition is widely used in the identification of an individual's identity. Unfortunately, in recent research work has revealed this face biometrics system is unprotected to spoofing attacks using by very low price instrument such as printed 2D photos attack, 3D masking attack and taking videos using smart devices (reply attack). Therefore, a Liveness Attack Detection (LAD) approach is needed to improve the high-quality security of face recognition system. Most of the earlier worked LAD methods for face anti-spoofing methods have highlight on using the handcrafted features, which are developed by expert knowledge of researcher. As example Gabor filter, Histogram of Oriented Gradients, local ternary pattern, and the Local Binary Pattern. Because of that, the extracted features consider limited factors of the problem, yielding a capture accuracy that is very low and changes with the point of presentation in attack face images. The deep learning method has developed in the computer vision research community, which is proven to be suitable for automatically training. In this article, we approach to mix or combine the handcrafted features and deep neural network features to design the discriminant face spoofing detection. The handcrafted features were based on LBP analysis. We examine the features information from the brightness and the chrominance channels using LBP descriptor. In deep features, we present an approach based on pre-trained convolutional neural network VGG-16 model using static features to recognize video and printed(2D) photo attacks. By attaching this two types of image features on our dataset and public databases, we get good results to identify real and attack images feature, called hybrid features, which has better discrimination ability to understand spoofing image feature. © 2019 IEEE.

关键词： Local binary pattern

Switched-capacitor finite impulse response rotator filter

学校读者我要写书评

暂无评论

Switched-capacitor finite impulse response rotator filter

Signal Processing Algorithms, Architectures, Arrangements and Applications (SPA)

作者： Paweł Pawłowski Rafał Długosz Adam Dąbrowski Division of Signal Processing and Electronic Systems Jana Pawł a II 24 Poznan University of Technology Faculty of Control Robotics and Electrical Engineering and Institute of Automation and Robotics Poznań Poland Faculty of Telecommunication Computer Science and Electrical Engineering Kaliskiego 7 UTP University of Science and Technology Bydgoszcz Poland

ISBN: (数字)9788362065394

ISBN: (纸本)9781728177465

Design of the topology and layout for an analog finite impulse response (FIR) filter realized in the CMOS technology using the switched capacitor (SC) technique, is presented. The filter is based on the so called “rotator structure” supplemented with the programmable capacitor array. This array makes the on-line adjusting of the frequency response of the filter possible in a very wide range, thus, enlarges the area of applications of this circuit, e.g., to multi-standard wireless communication, software-defined radio, adaptive systems, etc. The presented circuit realizes filters of orders up to 15 (16 filter coefficients). The maximum frequency range approaches ca. 2 MHz. The circuit dissipates ca. 8 mW from the power supply.

关键词： Finite impulse response filters Capacitors IIR filters Clocks Operational amplifiers Switches Capacitance