检索结果-南通市图书馆

Depth-Guided Vision Transformer With Normalizing Flows for Monocular 3D Object Detection

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第3期11卷 673-689页

作者： Cong Pan Junran Peng Zhaoxiang Zhang the Center for Research on Intelligent Perception and computing(CRIPAC) National Laboratory of Pattern Recognition(NLPR)Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190 the School of Future Technology University of Chinese Academy of Sciences(UCAS)Beijing 100049China the Huawei Inc. Beijing 100085China IEEE the institute of Automation Chinese Academy of Sciences(CASIA)Beijing 100190 the University of Chinese Academy of Sciences(UCAS) Beijing 100049 the Centre for Artificial Intelligence and Robotics Hong Kong institute of Science&Innovation Chinese Academy of Sciences(HKISI CAS)Hong Kong 999077China

Monocular 3D object detection is challenging due to the lack of accurate depth *** methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input to augment the RGB ***-based methods attempt to convert estimated depth maps to pseudo-LiDAR and then use LiDAR-based object detectors or focus on the perspective of image and depth fusion ***,they demonstrate limited performance and efficiency as a result of depth inaccuracy and complex fusion mode with *** from these approaches,our proposed depth-guided vision transformer with a normalizing flows(NF-DVT)network uses normalizing flows to build priors in depth maps to achieve more accurate depth *** we develop a novel Swin-Transformer-based backbone with a fusion module to process RGB image patches and depth map patches with two separate branches and fuse them using cross-attention to exchange information with each ***,with the help of pixel-wise relative depth values in depth maps,we develop new relative position embeddings in the cross-attention mechanism to capture more accurate sequence ordering of input *** method is the first Swin-Transformer-based backbone architecture for monocular 3D object *** experimental results on the KITTI and the challenging Waymo Open datasets show the effectiveness of our proposed method and superior performance over previous counterparts.

关键词： Monocular 3D object detection normalizing flows Swin Transformer

Human intrusion detection for high-speed railway perimeter under all-weather condition

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Railway Sciences 2024年第1期3卷 97-110页

作者： Pengyue Guo Tianyun Shi Zhen Ma Jing Wang institute of Electronic computing Technology China Academy of Railway Sciences Corporation LimitedBeijingChina School of Information and Electronics Beijing Institute of TechnologyBeijingChina

Purpose – The paper aims to solve the problem of personnel intrusion identification within the limits of highspeed railways. It adopts the fusion method of millimeter wave radar and camera to improve the accuracy ofobject recognition in dark and harsh weather ***/methodology/approach – This paper adopts the fusion strategy of radar and camera linkage toachieve focus amplification of long-distance targets and solves the problem of low illumination by laser lightfilling of the focus point. In order to improve the recognition effect, this paper adopts the YOLOv8 algorithm formulti-scale target recognition. In addition, for the image distortion caused by bad weather, this paper proposesa linkage and tracking fusion strategy to output the correct alarm *** – Simulated intrusion tests show that the proposed method can effectively detect human intrusionwithin 0–200 m during the day and night in sunny weather and can achieve more than 80% recognitionaccuracy for extreme severe weather ***/value – (1) The authors propose a personnel intrusion monitoring scheme based on the fusion ofmillimeter wave radar and camera, achieving all-weather intrusion monitoring;(2) The authors propose a newmulti-level fusion algorithm based on linkage and tracking to achieve intrusion target monitoring underadverse weather conditions;(3) The authors have conducted a large number of innovative simulationexperiments to verify the effectiveness of the method proposed in this article.

关键词： High-speed rail perimeter Personnel invasion Object detection All-weather Radar-camera fusion

A Transfer Function Design for medical Volume Data Using a Knowledge Database Based on Deep image and Primitive Intensity Profile Features Retrieval

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2024年第2期39卷 320-335页

作者： Younhyun Jung Jim Kong 盛斌 Jinman Kim School of computing Gachon UniversitySeongnam 13120Korea School of Computer Science The University of SydneySydney 2006Australia Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China

Direct volume rendering(DVR)is a technique that emphasizes structures of interest(SOIs)within a volume visually,while simultaneously depicting adjacent regional information,e.g.,the spatial location of a structure concerning its *** DVR,transfer function(TF)plays a key role by enabling accurate identification of SOIs interactively as well as ensuring appropriate visibility of *** generation typically involves non-intuitive trial-and-error optimization of rendering parameters,which is time-consuming and *** at mitigating this manual process have led to approaches that make use of a knowledge database consisting of pre-designed TFs by domain *** these approaches,a user navigates the knowledge database to find the most suitable pre-designed TF for their input volume to visualize the *** these approaches potentially reduce the workload to generate the TFs,they,however,require manual TF navigation of the knowledge database,as well as the likely fine tuning of the selected TF to suit the *** this work,we propose a TF design approach,CBR-TF,where we introduce a new content-based retrieval(CBR)method to automatically navigate the knowledge *** of pre-designed TFs,our knowledge database contains volumes with SOI *** an input volume,our CBR-TF approach retrieves relevant volumes(with SOI labels)from the knowledge database;the retrieved labels are then used to generate and optimize TFs of the *** approach largely reduces manual TF navigation and fine *** our CBR-TF approach,we introduce a novel volumetric image feature which includes both a local primitive intensity profile along the SOIs and regional spatial semantics available from the co-planar images to the *** the regional spatial semantics,we adopt a convolutional neural network to obtain high-level image feature *** the intensity profile,we extend the dynamic time warping technique to address subtle alignment

关键词： data retrieval direct volume rendering ray analysis transfer function

Diffractive neural networks with improved expressive power for gray-scale image classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Photonics Research 2024年第6期12卷 1159-1166页

作者： MINJIA ZHENG WENZHE LIU LEI SHI JIAN ZI State Key Laboratory of Surface Physics Key Laboratory of Micro-and Nano-Photonic Structures(Ministry of Education)and Department of PhysicsFudan UniversityShanghai 200433China institute for Nanoelectronic Devices and Quantum computing Fudan UniversityShanghai 200433China Collaborative Innovation Center of Advanced Microstructures Nanjing UniversityNanjing 210093China Shanghai Research Center for Quantum Sciences Shanghai 210315China

In order to harness diffractive neural networks(DNNs)for tasks that better align with real-world computer vision requirements,the incorporation of gray scale is ***,DNNs are not powerful enough to accomplish gray-scale image processing tasks due to limitations in their expressive *** our work,we elucidate the relationship between the improvement in the expressive power of DNNs and the increase in the number of phase modulation layers,as well as the optimization of the Fresnel number,which can describe the diffraction *** demonstrate this point,we numerically trained a double-layer DNN,addressing the prerequisites for intensitybased gray-scale image ***,we experimentally constructed this double-layer DNN based on digital micromirror devices and spatial light modulators,achieving eight-level intensity-based gray-scale image classification for the MNIST and Fashion-MNIST data *** optical system achieved the maximum accuracies of 95.10%and 80.61%,respectively.

关键词： process mirror limitations

Enhancing Pneumonia Detection in Pediatric Chest X-Rays Using CGAN-Augmented Datasets and Lightweight Deep Transfer Learning Models

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Data Analysis and Information Processing 2024年第1期12卷 1-23页

作者： Coulibaly Mohamed Ronald Waweru Mwangi John M. Kihoro Department of Mathematics Pan African University Institute for Basic Sciences Technology and Innovation (PAUSTI) Nairobi Kenya Department of computing Jomo Kenyatta University of Agriculture and Technology Nairobi Kenya School of computing and Mathematics The Cooperative University of Kenya Nairobi Kenya

Pneumonia ranks as a leading cause of mortality, particularly in children aged five and under. Detecting this disease typically requires radiologists to examine chest X-rays and report their findings to physicians, a task susceptible to human error. The application of Deep Transfer Learning (DTL) for the identification of pneumonia through chest X-rays is hindered by a shortage of available images, which has led to less than optimal DTL performance and issues with overfitting. Overfitting is characterized by a model’s learning that is too closely fitted to the training data, reducing its effectiveness on unseen data. The problem of overfitting is especially prevalent in medical image processing due to the high costs and extensive time required for image annotation, as well as the challenge of collecting substantial datasets that also respect patient privacy concerning infectious diseases such as pneumonia. To mitigate these challenges, this paper introduces the use of conditional generative adversarial networks (CGAN) to enrich the pneumonia dataset with 2690 synthesized X-ray images of the minority class, aiming to even out the dataset distribution for improved diagnostic performance. Subsequently, we applied four modified lightweight deep transfer learning models such as Xception, MobileNetV2, MobileNet, and EfficientNetB0. These models have been fine-tuned and evaluated, demonstrating remarkable detection accuracies of 99.26%, 98.23%, 97.06%, and 94.55%, respectively, across fifty epochs. The experimental results validate that the models we have proposed achieve high detection accuracy rates, with the best model reaching up to 99.26% effectiveness, outperforming other models in the diagnosis of pneumonia from X-ray images.

关键词： Pneumonia Detection Pediatric Radiology CGAN (Conditional Generative Adversarial Networks) Deep Transfer Learning medical image Analysis

DPT‐tracker:Dual pooling transformer for efficient visual tracking

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第4期9卷 948-959页

作者： Yang Fang Bailian Xie Uswah Khairuddin Zijian Min Bingbing Jiang Weisheng Li Key Laboratory of Data Engineering and Visual computing Chongqing University of Posts and TelecommunicationsChongqingChina Department of Mechanical Precision Engineering Malaysia‐Japan International Institute of TechnologyUniversity of Technology MalaysiaKuala LumpurMalaysia Department of Electrical and Computer Engineering Inha UniversityIncheonRepublic of Korea School of Information Science and Technology Hangzhou Normal UniversityHangzhouChina

Transformer tracking always takes paired template and search images as encoder input and conduct feature extraction and target‐search feature correlation by self and/or cross attention operations,thus the model complexity will grow quadratically with the number of input *** alleviate the burden of this tracking paradigm and facilitate practical deployment of Transformer‐based trackers,we propose a dual pooling transformer tracking framework,dubbed as DPT,which consists of three components:a simple yet efficient spatiotemporal attention model(SAM),a mutual correlation pooling Trans-former(MCPT)and a multiscale aggregation pooling Transformer(MAPT).SAM is designed to gracefully aggregates temporal dynamics and spatial appearance information of multi‐frame templates along space‐time *** aims to capture multi‐scale pooled and correlated contextual features,which is followed by MAPT that aggregates multi‐scale features into a unified feature representation for tracking *** tracker achieves AUC score of 69.5 on LaSOT and precision score of 82.8 on Track-ingNet while maintaining a shorter sequence length of attention tokens,fewer parameters and FLOPs compared to existing state‐of‐the‐art(SOTA)Transformer tracking *** experiments demonstrate that DPT tracker yields a strong real‐time tracking baseline with a good trade‐off between tracking performance and inference efficiency.

关键词： human‐computer interfacing image motion analysis pattern recognition signal processing tracking

Alignment efficient image-sentence retrieval considering transferable cross-modal representation learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第1期18卷 77-91页

作者： Yang YANG Jinyi GUO Guangyu LI Lanyu LI Wenjie LI Jian YANG School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Department of computing Hong Kong Polytechnic UniversityHong Kong 100872China State Key Lab.for Novel Software Technology Nanjing UniversityNanjing 210094China 14th Research institute of China Electronics Technology Group Corporation Nanjing 210094China guangyu.li2017@***

Traditional image-sentence cross-modal retrieval methods usually aim to learn consistent representations of heterogeneous modalities,thereby to search similar instances in one modality according to the query from another modality in *** basic assumption behind these methods is that parallel multi-modal data(i.e.,different modalities of the same example are aligned)can be obtained in *** other words,the image-sentence cross-modal retrieval task is a supervised task with the alignments as ***,in many real-world applications,it is difficult to realign a large amount of parallel data for new scenarios due to the substantial labor costs,leading the non-parallel multi-modal data and existing methods cannot be used *** the other hand,there actually exists auxiliary parallel multi-modal data with similar semantics,which can assist the non-parallel data to learn the consistent ***,in this paper,we aim at“Alignment Efficient image-Sentence Retrieval”(AEIR),which recurs to the auxiliary parallel image-sentence data as the source domain data,and takes the non-parallel data as the target domain *** single-modal transfer learning,AEIR learns consistent image-sentence cross-modal representations of target domain by transferring the alignments of existing parallel ***,AEIR learns the image-sentence consistent representations in source domain with parallel data,while transferring the alignment knowledge across domains by jointly optimizing a novel designed cross-domain cross-modal metric learning based constraint with intra-modal domain adversarial ***,we can effectively learn the consistent representations for target domain considering both the structure and semantic ***,extensive experiments on different transfer scenarios validate that AEIR can achieve better retrieval results comparing with the baselines.

关键词： image-sentence retrieval transfer learning semantic transfer structure transfer

A Lightweight Convolutional Neural Network with Hierarchical Multi-Scale Feature Fusion for image Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer and Communications 2024年第2期12卷 173-200页

作者： Adama Dembele Ronald Waweru Mwangi Ananda Omutokoh Kube Department of Mathematics Pan African University Institute for Basic Sciences Technology and Innovation Nairobi Kenya Department of computing School of Computing and Information Technology Jomo Kenyatta University of Agriculture and Technology Nairobi Kenya Department of Mathematics and Actuarial Sciences Kenyatta University Nairobi Kenya

Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.

关键词： MobileNet image Classification Lightweight Convolutional Neural Network Depthwise Dilated Separable Convolution Hierarchical Multi-Scale Feature Fusion

A survey for light field super-resolution

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

High-Confidence computing 2024年第1期4卷 118-129页

作者： Mingyuan Zhao Hao Sheng Da Yang Sizhe Wang Ruixuan Cong Zhenglong Cui Rongshan Chen Tun Wang Shuai Wang Yang Huang Jiahao Shen State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Key Laboratory of Data Science and Intelligent computing International Innovation InstituteBeihang UniversityHangzhou 311115China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Compared to 2D imaging data,the 4D light field(LF)data retains richer scene’s structure information,which can significantly improve the computer’s perception capability,including depth estimation,semantic segmentation,and LF ***,there is a contradiction between spatial and angular resolution during the LF image acquisition *** overcome the above problem,researchers have gradually focused on the light field super-resolution(LFSR).In the traditional solutions,researchers achieved the LFSR based on various optimization frameworks,such as Bayesian and Gaussian *** learning-based methods are more popular than conventional methods because they have better performance and more robust generalization *** this paper,the present approach can mainly divided into conventional methods and deep learning-based *** discuss these two branches in light field spatial super-resolution(LFSSR),light field angular super-resolution(LFASR),and light field spatial and angular super-resolution(LFSASR),***,this paper also introduces the primary public datasets and analyzes the performance of the prevalent approaches on these ***,we discuss the potential innovations of the LFSR to propose the progress of our research field.

关键词： Light field super-resolution Convolutional neural network Transformer Sub-aperture image Epipolar-plane image