检索结果-内蒙古大学图书馆

Random occlusion-recovery for person re-identification

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Wu, Di Zhang, Kun Cheng, Fei Zhao, Yang Liu, Qi Yuan, Chang-An Huang, De-Shuang Institute of Machine Learning and Systems Biology School of Electronics and Information Engineering Tongji University School of Computing Edinburgh Napier University 10 Colinton Road EdinburghEH10 5DT United Kingdom Science Computing and Intelligent Information Processing of Guang Xi Higher Education Key Laboratory Guangxi Teachers Education University Nanning Guangxi530001 China Beijing E-Hualu Info Technology Co. Ltd Beijing China

As a basic task of multi-camera surveillance system, person re-identification aims to re-identify a query pedestrian observed from non-overlapping multiple cameras or across different time with a single camera. Recently, deep learning-based person re-identification models have achieved great success in many benchmarks. However, these supervised models require a large amount of labeled image data, and the process of manual labeling spends much manpower and time. In this study, we introduce a method to automatically synthesize labeled person images and adopt them to increase the sample number per identity for person re-identification datasets. To be specific, we use block rectangles to randomly occlude pedestrian images. Then, a generative adversarial network (GAN) model is proposed to use paired occluded and original images to synthesize the de-occluded images that similar but not identical to the original image. Afterwards, we annotate the de-occluded images with the same labels of their corresponding raw images and use them to augment the number of samples per identity. Finally, we use the augmented datasets to train baseline model. The experiment results on CUHK03, Market-1501 and DukeMTMC-reID datasets show that the effectiveness of the proposed method. Copyright © 2018, The Authors. All rights reserved.

关键词： Generative adversarial networks

3d Surface Detection and Segmentation from Point Clouds Via Quadric Fits Based on Dbscan Clustering

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Xie, Tingting Chen, Hui Liu, Wanquan Zhou, Rongyu Li, Qilin College of Automation Engineering Shanghai University of Electric Power Shanghai200090 China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China School of Intelligent Systems Engineering Sun Yat-sen University Guangzhou510275 China School of Electrical Engineering Computing and Mathematical Sciences Curtin University BentleyWA Australia

Extracting surfaces from 3D point clouds is significant in reconstructing and transforming these discrete points into their corresponding models. Scannedpoint clouds are often accompanied by noise, and the existing methods mainly rely on local feature similarities for surface extractions. Errors in estimatingthe feature information may lead to incorrect surface detection. In this paper we propose a surface extraction and boundary detection method based onclustering technique. The method can be described in three steps: In the first step, a normal correction is carried out using the information from theneighbourhood of points with sharp features. The second step is to cluster the points that meet the coplanar condition of the local quadric surface (LQS).In the third step, surface merger is performed by merging the local surfaces satisfying the merging conditions. Experimental validation is carried outto determine the effectiveness of the proposed method. The experimental results show improved surface extraction accuracy of the proposed methodin comparison to RANSAC, RG, LCCP, C2NO and HT methods. © 2024, The Authors. All rights reserved.

关键词： Merging

Adjusting Dynamics of Hopfield Neural Network via Time-variant Stimulus

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Peng, Xuenan Li, Chengqing Zeng, Yicheng Li, Chun-Lai School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China Key Laboratory of Intelligent Computing & Information Processing the Ministry of Education Xiangtan University Hunan Xiangtan411105 China School of Physics and Optoelectronic Engineering Xiangtan University Hunan Xiangtan411105 China School of Computer Science Xiangtan University Hunan Xiangtan411105 China

As a paradigmatic model for nonlinear dynamics studies, the Hopfield Neural Network (HNN) demonstrates a high susceptibility to external disturbances owing to its intricate structure. This paper delves into the challenge of modulating HNN dynamics through time-variant stimuli. The effects of adjustments using two distinct types of time-variant stimuli, namely the Weight Matrix Stimulus (WMS) and the State Variable Stimulus (SVS), along with a Constant Stimulus (CS) are reported. The findings reveal that deploying four WMSs enables the HNN to generate either a four-scroll or a coexisting two-scroll attractor. When combined with one SVS, four WMSs can lead to the formation of an eight-scroll or four-scroll attractor, while the integration of four WMSs and multiple SVSs can induce grid-multi-scroll attractors. Moreover, the introduction of a CS and an SVS can significantly disrupt the dynamic behavior of the HNN. Consequently, suitable adjustment methods are crucial for enhancing the network’s dynamics, whereas inappropriate applications can lead to the loss of its chaotic characteristics. To empirically validate these enhancement effects, the study employs an FPGA hardware platform. Subsequently, an image encryption scheme is designed to demonstrate the practical application benefits of the dynamically adjusted HNN in secure multimedia communication. This exploration into the dynamic modulation of HNN via time-variant stimuli offers insightful contributions to the advancement of secure communication *** Codes 68T07 Copyright © 2024, The Authors. All rights reserved.

关键词： Dynamics

Design and Implementation of Telemedicine System Using Light Fidelity and PIC16F877A Microcontroller

学校读者我要写书评

暂无评论

Design and Implementation of Telemedicine System Using Light...

International Conference on information Science and Technology (ICIST)

作者： M.R. Ezilarasan Man-Fai Leung Xiangguang Dai Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Instituteof Science and Technology Chennai India Faculty of Science and Engineering School of Computing and Information Science Anglia Ruskin University Cambridge United Kingdom Key Laboratory of Intelligent Information Processing and Control of Chongqing Municipal Institutions of Higher Education Chongqing Three Gorges University Wanzhou Chongqing China

ISBN: (数字)9798350353334

ISBN: (纸本)9798350353341

Medical Body Area Networks (MBANs) increasingly utilize wireless communication technologies to enhance the freedom and convenience for patients and caregivers. Currently, radio frequency (RF) is the prevalent medium in healthcare applications; however, the potential for electromagnetic interference with precision medical equipment remains a concern. This study introduces a novel design and implementation of a medical healthcare information system using the newly developed Wireless Visible Light Communication (VLC) technology, also known as Light Fidelity (Li-Fi). Visible Light Emitting Diodes (LEDs), expected to soon surpass traditional incandescent and fluorescent bulbs as the primary light source due to their energy efficiency, facilitate this technology. In this research, patient health is monitored using sensors, with results displayed on an LCD. An LED lightbulb transmits the data as light signals, which are captured by a photo-detector at the receiver's end. This setup not only displays the output on an LCD but also alerts caregivers through an auditory signal, beeping every 15 seconds for respiration and every 30 seconds for heart rate monitoring. Moreover, these lighting fixtures serve dual functions: illumination and wireless data transmission, using the rapid switching capability of LEDs. This prototype VLC-based system offers a promising alternative for data services and monitoring in hospital areas where RF use is restricted.

关键词： Wireless communication Radio frequency Wireless sensor networks Lighting Light emitting diodes Light fidelity Liquid crystal displays Communication system security Monitoring Visible light communication

Optimal combination of conflicting evidence based on genetic algorithm

学校读者我要写书评

暂无评论

ICIC Express Letters 2011年第4 A期5卷 1145-1150页

作者： Jiang, Wen Peng, Jinye Deng, Yong School of Electronics and Information Northwestern Polytechnical University No. 127 Youyixi Road Xi'an 710072 China Hangzhou Key Lab of E-Business and Information Security Hangzhou Normal University No. 16 Xuelin Street Xiasha Higher Education Zone Hanzhou 310036 China Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Xiangtan University Xiangtan 411105 China School of Computer and Information Sciences Southwest University No. 2 Tiansheng Road Beibei District Chongqing 400715 China School of Electronics and Information Technology Shanghai Jiao Tong University No. 800 Dongchuan Road Shanghai 200240 China

The Dempster-Shafer (D-S) evidence theory is widely used in many fields of information fusion. However, counter-intuitive results may be obtained by the classical Dempster combination rule when collected evidences are highly in conflict with each other. So an optimal weighted average information fusion method is proposed. Firstly, the global distance of the weighted evidence is presented based on the distance function. Secondly, the optimal weight of every evidence body was acquired by genetic algorithm, while the global distance is the minimum. Finally, the weighted average of the masses is combined by classical Dempster's rule. Compared with existing methods, the proposed optimal method can effectively handle conflicting evidence with better performance of convergence. Numerical examples are illustrated the effectiveness of the proposed method. ICIC International © 2011.

关键词： Genetic algorithms

Gradually Vanishing Gap in Prototypical Network for Unsupervised Domain Adaptation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Shanshan Zhou, Hao Yang, Xun He, Zhenwei Wang, Mengzhu Zhang, Xingyi Wang, Meng The Information Materials and Intelligent Sensing Laboratory of Anhui Province Institutes of Physical Science and Information Technology Anhui University Hefei230601 China The Department of Electronic Engineering and Information Science School of Information Science and Technology University of Science and Technology of China Hefei230026 China The College of Computer Science and Engineering Chongqing University of Technology Chongqing400054 China The School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China The School of Artificial Intelligence Hebei University of Technology Tianjin China The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education The School of Computer Science and Technology Anhui University Hefei230601 China

Unsupervised domain adaptation (UDA) is a critical problem for transfer learning, which aims to transfer the semantic information from labeled source domain to unlabeled target domain. Recent advancements in UDA models have demonstrated significant generalization capabilities on the target domain. However, the generalization boundary of UDA models remains unclear. When the domain discrepancy is too large, the model can not preserve the distribution structure, leading to distribution collapse during the alignment. To address this challenge, we propose an efficient UDA framework named Gradually Vanishing Gap in Prototypical Network (GVG-PN), which achieves transfer learning from both global and local perspectives. From the global alignment standpoint, our model generates a domain-biased intermediate domain that helps preserve the distribution structures. By entangling cross-domain features, our model progressively reduces the risk of distribution collapse. However, only relying on global alignment is insufficient to preserve the distribution structure. To further enhance the inner relationships of features, we introduce the local perspective. We utilize the graph convolutional network (GCN) as an intuitive method to explore the internal relationships between features, ensuring the preservation of manifold structures and generating domain-biased prototypes. Additionally, we consider the discriminability of the inner relationships between features. We propose a pro-contrastive loss to enhance the discriminability at the prototype level by separating hard negative pairs. By incorporating both GCN and the pro-contrastive loss, our model fully explores fine-grained semantic relationships. Experiments on several UDA benchmarks validated that the proposed GVG-PN can clearly outperform the SOTA models. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

Structural information Guided Multimodal Pre-training for Vehicle-centric Perception

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Xiao Wu, Wentao Li, Chenglong Zhao, Zhicheng Chen, Zhe Shi, Yukai Tang, Jin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei230601 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Hefei230601 China School of Computer Science and Technology Anhui University Hefei230601 China School of Artificial Intelligence Anhui University Hefei230601 China School of Computing Engineering and Mathematical Sciences La Trobe University Australia School of Information Engineering Guangdong University of Technology Guangzhou China

Understanding vehicles in images is important for various applications such as intelligent transportation and self-driving system. Existing vehicle-centric works typically pre-train models on large-scale classification datasets and then fine-tune them for specific downstream tasks. However, they neglect the specific characteristics of vehicle perception in different tasks and might thus lead to suboptimal performance. To address this issue, we propose a novel vehicle-centric pre-training framework called VehicleMAE, which incorporates the structural information including the spatial structure from vehicle profile information and the semantic structure from informative high-level natural language descriptions for effective masked vehicle appearance reconstruction. To be specific, we explicitly extract the sketch lines of vehicles as a form of the spatial structure to guide vehicle reconstruction. The more comprehensive knowledge distilled from the CLIP big model based on the similarity between the paired/unpaired vehicle image-text sample is further taken into consideration to help achieve a better understanding of vehicles. A large-scale dataset is built to pre-train our model, termed Autobot1M, which contains about 1M vehicle images and 12693 text information. Extensive experiments on four vehicle-based downstream tasks fully validated the effectiveness of our VehicleMAE. The source code and pre-trained models will be released at https://***/EventAHU/VehicleMAE. Copyright © 2023, The Authors. All rights reserved.

关键词： Large dataset

Sample hardness based gradient loss for long-tailed cervical cell detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Minmin Li, Xuechen Gao, Xiangbo Chen, Junliang Shen, Linlin Wu, Huisi Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China University of California Irvine United States

Due to the difficulty of cancer samples collection and annotation, cervical cancer datasets usually exhibit a long-tailed data distribution. When training a detector to detect the cancer cells in a WSI (Whole Slice Image) image captured from the TCT (Thinprep Cytology Test) specimen, head categories (e.g. normal cells and inflammatory cells) typically have a much larger number of samples than tail categories (e.g. cancer cells). Most existing state-of-the-art long-tailed learning methods in object detection focus on category distribution statistics to solve the problem in the long-tailed scenario, without considering the "hardness" of each sample. To address this problem, in this work we propose a Grad-Libra Loss that leverages the gradients to dynamically calibrate the degree of hardness of each sample for different categories, and re-balance the gradients of positive and negative samples. Our loss can thus help the detector to put more emphasis on those hard samples in both head and tail categories. Extensive experiments on a long-tailed TCT WSI image dataset show that the mainstream detectors, e.g. RepPoints, FCOS, ATSS, YOLOF, etc. trained using our proposed Gradient-Libra Loss, achieved much higher (7.8%) mAP than that trained using cross-entropy classification loss. Copyright © 2022, The Authors. All rights reserved.

关键词： Cytology

Some bounds on the cardinality of the b-symbol weight spectrum of codes

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhu, Hongwei Li, Shitao Shi, Minjia Xia, Shu-Tao Solé, Patrick Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen518055 China School of Mathematical Sciences Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Mathematical Sciences Anhui University Hefei230601 China Centrale Marseille CNRS I2M Aix Marseille University Marseille13009 France State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China

The size of the Hamming distance spectrum of a code has received great attention in recent research. The main objective of this paper is to extend these significant theories to the b-symbol distance spectrum. We examine this question for various types of codes, including unrestricted codes, additive codes, linear codes, and cyclic codes, successively. For the first three cases, we determine the maximum size of the b-symbol distance spectra of these codes smoothly. For the case of cyclic codes, we introduce three approaches to characterize the upper bound for the cardinality of the b-symbol weight spectrum of cyclic codes, namely the period distribution approach, the primitive idempotent approach, and the b-symbol weight formula approach. As two by-products of this paper, the maximum number of symplectic weights of linear codes is determined, and a basic inequality among the parameters [n, k, dH(C)]q of cyclic codes is provided. © 2024, CC0.

关键词： Hamming distance